Skill writer by the Agent Skills spec

Creates and improves agent skills by Sentry's workflow: sources with provenance, the simplest execution shape, SPEC.md and SOURCES.md, precision passes after each change and a structural validator. Use when building a skill that a team will maintain.

DocumentationPack: Sentry skills156 linesskill-writer
Author
Source
getsentry/skills/skills/skill-writer @ a582c51
License
Apache-2.0 · Copyright 2025 Functional Software, Inc. dba Sentry

About this skill

What it does

Skill writer is Sentry's single workflow for creating, updating and improving agent skills, and it treats research as the main job. Before writing, the agent picks the path (create, update, synthesize or iterate), the skill's class and its execution shape: inline guidance, reference-backed, script-backed, router, subagent fork, hook-backed and a few more. It defaults to the simplest shape that works and records why simpler ones were rejected. Sources are collected with provenance and a coverage list; writing starts only when gaps are known.

A finished skill has SKILL.md as a short router to flat references/ files, a SPEC.md maintenance contract and a SOURCES.md with sources, decisions and open gaps. Before adding a rule, the agent checks whether narrowing, moving or deleting an existing one would do, and repeats this precision pass after every change, reporting the outcome. A skill that generates other artifacts must carry three worked examples: the happy path, a robust variant, and an anti-pattern with its fix. The description is tuned against should-trigger and should-not-trigger queries. The answer comes as Summary, Changes Made, Validation Results and Open Gaps.

The folder holds 37 flat references (paths, layouts, workflow patterns, Claude Code mechanics such as frontmatter, arguments, context: fork and hooks, example profiles) and scripts/quick_validate.py, a structural check of frontmatter, name and referenced files. EVAL.md and evals/ test the skill itself with AXIS (npx @netlify/axis) driving Codex; using the skill does not need them.

When to use it, and when not

Use it for a skill meant to last: one built from docs or an upstream prompt, one a team maintains, or a fix driven by bad outputs.

For a short personal skill, SPEC, SOURCES and precision passes are overhead. It was written for Sentry's skills repository; elsewhere it follows the layout it finds and defaults to .agents/skills/<name>/.

How to run it

The install command below puts the whole folder in place. The validator runs with uv run scripts/quick_validate.py <skill-dir>. The agent picks the skill up by its description; to call it yourself:

  • Claude Code: /skill-writer, or ask for the skill by name.
  • Codex: $skill-writer.
  • Cursor: type / in the Agent chat and pick skill-writer.

Example: /skill-writer Turn the runbook in docs/deploy.md into a skill; keep it inline if that is enough.

How it differs from similar skills

Skill creator with evals from Anthropic centres on test runs: with-skill and baseline subagents per test case, a viewer for the results and a loop that tunes the description on trigger queries. Writing skills tests a skill on subagents under pressure until they comply. Writing for agents is a wording reference with no procedure. Skill writer puts the weight on sources and structure. To check a skill from elsewhere, use Agent skill security scanner.

Install

Run one command — it saves SKILL.md and the files it uses into your agent's skills folder. Claude Code and Codex pick up a new skill without a restart; if it does not show up, restart the agent.

Claude Code — macOS, Linux
curl -fsSL --create-dirs -o ~/.claude/skills/skill-writer/SKILL.md https://anymodel.org/en/skills/sentry/skill-writer/SKILL.md -o ~/.claude/skills/skill-writer/EVAL.md https://anymodel.org/en/skills/sentry/skill-writer/EVAL.md -o ~/.claude/skills/skill-writer/LICENSE https://anymodel.org/en/skills/sentry/skill-writer/LICENSE -o ~/.claude/skills/skill-writer/SOURCES.md https://anymodel.org/en/skills/sentry/skill-writer/SOURCES.md -o ~/.claude/skills/skill-writer/SPEC.md https://anymodel.org/en/skills/sentry/skill-writer/SPEC.md -o ~/.claude/skills/skill-writer/evals/axis.config.json https://anymodel.org/en/skills/sentry/skill-writer/evals/axis.config.json -o ~/.claude/skills/skill-writer/evals/scenarios/iteration-from-bad-output.json https://anymodel.org/en/skills/sentry/skill-writer/evals/scenarios/iteration-from-bad-output.json -o ~/.claude/skills/skill-writer/evals/scenarios/reference-backed-integration.json https://anymodel.org/en/skills/sentry/skill-writer/evals/scenarios/reference-backed-integration.json -o ~/.claude/skills/skill-writer/evals/scenarios/small-inline-workflow.json https://anymodel.org/en/skills/sentry/skill-writer/evals/scenarios/small-inline-workflow.json -o ~/.claude/skills/skill-writer/references/authoring-path.md https://anymodel.org/en/skills/sentry/skill-writer/references/authoring-path.md -o ~/.claude/skills/skill-writer/references/claude-argument-substitutions.md https://anymodel.org/en/skills/sentry/skill-writer/references/claude-argument-substitutions.md -o ~/.claude/skills/skill-writer/references/claude-dynamic-context.md https://anymodel.org/en/skills/sentry/skill-writer/references/claude-dynamic-context.md -o ~/.claude/skills/skill-writer/references/claude-frontmatter-invocation.md https://anymodel.org/en/skills/sentry/skill-writer/references/claude-frontmatter-invocation.md -o ~/.claude/skills/skill-writer/references/claude-hook-backed.md https://anymodel.org/en/skills/sentry/skill-writer/references/claude-hook-backed.md -o ~/.claude/skills/skill-writer/references/claude-subagent-fork.md https://anymodel.org/en/skills/sentry/skill-writer/references/claude-subagent-fork.md -o ~/.claude/skills/skill-writer/references/description-optimization.md https://anymodel.org/en/skills/sentry/skill-writer/references/description-optimization.md -o ~/.claude/skills/skill-writer/references/design-principles.md https://anymodel.org/en/skills/sentry/skill-writer/references/design-principles.md -o ~/.claude/skills/skill-writer/references/example-documentation-skill.md https://anymodel.org/en/skills/sentry/skill-writer/references/example-documentation-skill.md -o ~/.claude/skills/skill-writer/references/example-hook-backed-skill.md https://anymodel.org/en/skills/sentry/skill-writer/references/example-hook-backed-skill.md -o ~/.claude/skills/skill-writer/references/example-router-skill.md https://anymodel.org/en/skills/sentry/skill-writer/references/example-router-skill.md -o ~/.claude/skills/skill-writer/references/example-subagent-fork-skill.md https://anymodel.org/en/skills/sentry/skill-writer/references/example-subagent-fork-skill.md -o ~/.claude/skills/skill-writer/references/example-workflow-process-skill.md https://anymodel.org/en/skills/sentry/skill-writer/references/example-workflow-process-skill.md -o ~/.claude/skills/skill-writer/references/execution-shapes.md https://anymodel.org/en/skills/sentry/skill-writer/references/execution-shapes.md -o ~/.claude/skills/skill-writer/references/iteration-evidence.md https://anymodel.org/en/skills/sentry/skill-writer/references/iteration-evidence.md -o ~/.claude/skills/skill-writer/references/iteration-path.md https://anymodel.org/en/skills/sentry/skill-writer/references/iteration-path.md -o ~/.claude/skills/skill-writer/references/layout-argument-driven-skill.md https://anymodel.org/en/skills/sentry/skill-writer/references/layout-argument-driven-skill.md -o ~/.claude/skills/skill-writer/references/layout-asset-template-skill.md https://anymodel.org/en/skills/sentry/skill-writer/references/layout-asset-template-skill.md -o ~/.claude/skills/skill-writer/references/layout-inline-skill.md https://anymodel.org/en/skills/sentry/skill-writer/references/layout-inline-skill.md -o ~/.claude/skills/skill-writer/references/layout-reference-backed-skill.md https://anymodel.org/en/skills/sentry/skill-writer/references/layout-reference-backed-skill.md -o ~/.claude/skills/skill-writer/references/layout-script-backed-workflow.md https://anymodel.org/en/skills/sentry/skill-writer/references/layout-script-backed-workflow.md -o ~/.claude/skills/skill-writer/references/mode-selection.md https://anymodel.org/en/skills/sentry/skill-writer/references/mode-selection.md -o ~/.claude/skills/skill-writer/references/output-contracts.md https://anymodel.org/en/skills/sentry/skill-writer/references/output-contracts.md -o ~/.claude/skills/skill-writer/references/reference-architecture.md https://anymodel.org/en/skills/sentry/skill-writer/references/reference-architecture.md -o ~/.claude/skills/skill-writer/references/registration-validation.md https://anymodel.org/en/skills/sentry/skill-writer/references/registration-validation.md -o ~/.claude/skills/skill-writer/references/skill-evals.md https://anymodel.org/en/skills/sentry/skill-writer/references/skill-evals.md -o ~/.claude/skills/skill-writer/references/source-adaptation.md https://anymodel.org/en/skills/sentry/skill-writer/references/source-adaptation.md -o ~/.claude/skills/skill-writer/references/source-discovery.md https://anymodel.org/en/skills/sentry/skill-writer/references/source-discovery.md -o ~/.claude/skills/skill-writer/references/spec-template.md https://anymodel.org/en/skills/sentry/skill-writer/references/spec-template.md -o ~/.claude/skills/skill-writer/references/structure-troubleshooting.md https://anymodel.org/en/skills/sentry/skill-writer/references/structure-troubleshooting.md -o ~/.claude/skills/skill-writer/references/synthesis-path.md https://anymodel.org/en/skills/sentry/skill-writer/references/synthesis-path.md -o ~/.claude/skills/skill-writer/references/workflow-orchestrator-workers.md https://anymodel.org/en/skills/sentry/skill-writer/references/workflow-orchestrator-workers.md -o ~/.claude/skills/skill-writer/references/workflow-parallel.md https://anymodel.org/en/skills/sentry/skill-writer/references/workflow-parallel.md -o ~/.claude/skills/skill-writer/references/workflow-plan-validate-execute.md https://anymodel.org/en/skills/sentry/skill-writer/references/workflow-plan-validate-execute.md -o ~/.claude/skills/skill-writer/references/workflow-prompt-chaining.md https://anymodel.org/en/skills/sentry/skill-writer/references/workflow-prompt-chaining.md -o ~/.claude/skills/skill-writer/references/workflow-routing.md https://anymodel.org/en/skills/sentry/skill-writer/references/workflow-routing.md -o ~/.claude/skills/skill-writer/references/workflow-validation-loops.md https://anymodel.org/en/skills/sentry/skill-writer/references/workflow-validation-loops.md -o ~/.claude/skills/skill-writer/scripts/quick_validate.py https://anymodel.org/en/skills/sentry/skill-writer/scripts/quick_validate.py
Codex, Cursor — macOS, Linux
curl -fsSL --create-dirs -o ~/.agents/skills/skill-writer/SKILL.md https://anymodel.org/en/skills/sentry/skill-writer/SKILL.md -o ~/.agents/skills/skill-writer/EVAL.md https://anymodel.org/en/skills/sentry/skill-writer/EVAL.md -o ~/.agents/skills/skill-writer/LICENSE https://anymodel.org/en/skills/sentry/skill-writer/LICENSE -o ~/.agents/skills/skill-writer/SOURCES.md https://anymodel.org/en/skills/sentry/skill-writer/SOURCES.md -o ~/.agents/skills/skill-writer/SPEC.md https://anymodel.org/en/skills/sentry/skill-writer/SPEC.md -o ~/.agents/skills/skill-writer/evals/axis.config.json https://anymodel.org/en/skills/sentry/skill-writer/evals/axis.config.json -o ~/.agents/skills/skill-writer/evals/scenarios/iteration-from-bad-output.json https://anymodel.org/en/skills/sentry/skill-writer/evals/scenarios/iteration-from-bad-output.json -o ~/.agents/skills/skill-writer/evals/scenarios/reference-backed-integration.json https://anymodel.org/en/skills/sentry/skill-writer/evals/scenarios/reference-backed-integration.json -o ~/.agents/skills/skill-writer/evals/scenarios/small-inline-workflow.json https://anymodel.org/en/skills/sentry/skill-writer/evals/scenarios/small-inline-workflow.json -o ~/.agents/skills/skill-writer/references/authoring-path.md https://anymodel.org/en/skills/sentry/skill-writer/references/authoring-path.md -o ~/.agents/skills/skill-writer/references/claude-argument-substitutions.md https://anymodel.org/en/skills/sentry/skill-writer/references/claude-argument-substitutions.md -o ~/.agents/skills/skill-writer/references/claude-dynamic-context.md https://anymodel.org/en/skills/sentry/skill-writer/references/claude-dynamic-context.md -o ~/.agents/skills/skill-writer/references/claude-frontmatter-invocation.md https://anymodel.org/en/skills/sentry/skill-writer/references/claude-frontmatter-invocation.md -o ~/.agents/skills/skill-writer/references/claude-hook-backed.md https://anymodel.org/en/skills/sentry/skill-writer/references/claude-hook-backed.md -o ~/.agents/skills/skill-writer/references/claude-subagent-fork.md https://anymodel.org/en/skills/sentry/skill-writer/references/claude-subagent-fork.md -o ~/.agents/skills/skill-writer/references/description-optimization.md https://anymodel.org/en/skills/sentry/skill-writer/references/description-optimization.md -o ~/.agents/skills/skill-writer/references/design-principles.md https://anymodel.org/en/skills/sentry/skill-writer/references/design-principles.md -o ~/.agents/skills/skill-writer/references/example-documentation-skill.md https://anymodel.org/en/skills/sentry/skill-writer/references/example-documentation-skill.md -o ~/.agents/skills/skill-writer/references/example-hook-backed-skill.md https://anymodel.org/en/skills/sentry/skill-writer/references/example-hook-backed-skill.md -o ~/.agents/skills/skill-writer/references/example-router-skill.md https://anymodel.org/en/skills/sentry/skill-writer/references/example-router-skill.md -o ~/.agents/skills/skill-writer/references/example-subagent-fork-skill.md https://anymodel.org/en/skills/sentry/skill-writer/references/example-subagent-fork-skill.md -o ~/.agents/skills/skill-writer/references/example-workflow-process-skill.md https://anymodel.org/en/skills/sentry/skill-writer/references/example-workflow-process-skill.md -o ~/.agents/skills/skill-writer/references/execution-shapes.md https://anymodel.org/en/skills/sentry/skill-writer/references/execution-shapes.md -o ~/.agents/skills/skill-writer/references/iteration-evidence.md https://anymodel.org/en/skills/sentry/skill-writer/references/iteration-evidence.md -o ~/.agents/skills/skill-writer/references/iteration-path.md https://anymodel.org/en/skills/sentry/skill-writer/references/iteration-path.md -o ~/.agents/skills/skill-writer/references/layout-argument-driven-skill.md https://anymodel.org/en/skills/sentry/skill-writer/references/layout-argument-driven-skill.md -o ~/.agents/skills/skill-writer/references/layout-asset-template-skill.md https://anymodel.org/en/skills/sentry/skill-writer/references/layout-asset-template-skill.md -o ~/.agents/skills/skill-writer/references/layout-inline-skill.md https://anymodel.org/en/skills/sentry/skill-writer/references/layout-inline-skill.md -o ~/.agents/skills/skill-writer/references/layout-reference-backed-skill.md https://anymodel.org/en/skills/sentry/skill-writer/references/layout-reference-backed-skill.md -o ~/.agents/skills/skill-writer/references/layout-script-backed-workflow.md https://anymodel.org/en/skills/sentry/skill-writer/references/layout-script-backed-workflow.md -o ~/.agents/skills/skill-writer/references/mode-selection.md https://anymodel.org/en/skills/sentry/skill-writer/references/mode-selection.md -o ~/.agents/skills/skill-writer/references/output-contracts.md https://anymodel.org/en/skills/sentry/skill-writer/references/output-contracts.md -o ~/.agents/skills/skill-writer/references/reference-architecture.md https://anymodel.org/en/skills/sentry/skill-writer/references/reference-architecture.md -o ~/.agents/skills/skill-writer/references/registration-validation.md https://anymodel.org/en/skills/sentry/skill-writer/references/registration-validation.md -o ~/.agents/skills/skill-writer/references/skill-evals.md https://anymodel.org/en/skills/sentry/skill-writer/references/skill-evals.md -o ~/.agents/skills/skill-writer/references/source-adaptation.md https://anymodel.org/en/skills/sentry/skill-writer/references/source-adaptation.md -o ~/.agents/skills/skill-writer/references/source-discovery.md https://anymodel.org/en/skills/sentry/skill-writer/references/source-discovery.md -o ~/.agents/skills/skill-writer/references/spec-template.md https://anymodel.org/en/skills/sentry/skill-writer/references/spec-template.md -o ~/.agents/skills/skill-writer/references/structure-troubleshooting.md https://anymodel.org/en/skills/sentry/skill-writer/references/structure-troubleshooting.md -o ~/.agents/skills/skill-writer/references/synthesis-path.md https://anymodel.org/en/skills/sentry/skill-writer/references/synthesis-path.md -o ~/.agents/skills/skill-writer/references/workflow-orchestrator-workers.md https://anymodel.org/en/skills/sentry/skill-writer/references/workflow-orchestrator-workers.md -o ~/.agents/skills/skill-writer/references/workflow-parallel.md https://anymodel.org/en/skills/sentry/skill-writer/references/workflow-parallel.md -o ~/.agents/skills/skill-writer/references/workflow-plan-validate-execute.md https://anymodel.org/en/skills/sentry/skill-writer/references/workflow-plan-validate-execute.md -o ~/.agents/skills/skill-writer/references/workflow-prompt-chaining.md https://anymodel.org/en/skills/sentry/skill-writer/references/workflow-prompt-chaining.md -o ~/.agents/skills/skill-writer/references/workflow-routing.md https://anymodel.org/en/skills/sentry/skill-writer/references/workflow-routing.md -o ~/.agents/skills/skill-writer/references/workflow-validation-loops.md https://anymodel.org/en/skills/sentry/skill-writer/references/workflow-validation-loops.md -o ~/.agents/skills/skill-writer/scripts/quick_validate.py https://anymodel.org/en/skills/sentry/skill-writer/scripts/quick_validate.py
Claude Code — Windows PowerShell
foreach ($f in 'SKILL.md','EVAL.md','LICENSE','SOURCES.md','SPEC.md','evals/axis.config.json','evals/scenarios/iteration-from-bad-output.json','evals/scenarios/reference-backed-integration.json','evals/scenarios/small-inline-workflow.json','references/authoring-path.md','references/claude-argument-substitutions.md','references/claude-dynamic-context.md','references/claude-frontmatter-invocation.md','references/claude-hook-backed.md','references/claude-subagent-fork.md','references/description-optimization.md','references/design-principles.md','references/example-documentation-skill.md','references/example-hook-backed-skill.md','references/example-router-skill.md','references/example-subagent-fork-skill.md','references/example-workflow-process-skill.md','references/execution-shapes.md','references/iteration-evidence.md','references/iteration-path.md','references/layout-argument-driven-skill.md','references/layout-asset-template-skill.md','references/layout-inline-skill.md','references/layout-reference-backed-skill.md','references/layout-script-backed-workflow.md','references/mode-selection.md','references/output-contracts.md','references/reference-architecture.md','references/registration-validation.md','references/skill-evals.md','references/source-adaptation.md','references/source-discovery.md','references/spec-template.md','references/structure-troubleshooting.md','references/synthesis-path.md','references/workflow-orchestrator-workers.md','references/workflow-parallel.md','references/workflow-plan-validate-execute.md','references/workflow-prompt-chaining.md','references/workflow-routing.md','references/workflow-validation-loops.md','scripts/quick_validate.py') { $p = Join-Path "$HOME\.claude\skills\skill-writer" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/sentry/skill-writer/$f" -UseBasicParsing -OutFile $p }
Codex, Cursor — Windows PowerShell
foreach ($f in 'SKILL.md','EVAL.md','LICENSE','SOURCES.md','SPEC.md','evals/axis.config.json','evals/scenarios/iteration-from-bad-output.json','evals/scenarios/reference-backed-integration.json','evals/scenarios/small-inline-workflow.json','references/authoring-path.md','references/claude-argument-substitutions.md','references/claude-dynamic-context.md','references/claude-frontmatter-invocation.md','references/claude-hook-backed.md','references/claude-subagent-fork.md','references/description-optimization.md','references/design-principles.md','references/example-documentation-skill.md','references/example-hook-backed-skill.md','references/example-router-skill.md','references/example-subagent-fork-skill.md','references/example-workflow-process-skill.md','references/execution-shapes.md','references/iteration-evidence.md','references/iteration-path.md','references/layout-argument-driven-skill.md','references/layout-asset-template-skill.md','references/layout-inline-skill.md','references/layout-reference-backed-skill.md','references/layout-script-backed-workflow.md','references/mode-selection.md','references/output-contracts.md','references/reference-architecture.md','references/registration-validation.md','references/skill-evals.md','references/source-adaptation.md','references/source-discovery.md','references/spec-template.md','references/structure-troubleshooting.md','references/synthesis-path.md','references/workflow-orchestrator-workers.md','references/workflow-parallel.md','references/workflow-plan-validate-execute.md','references/workflow-prompt-chaining.md','references/workflow-routing.md','references/workflow-validation-loops.md','scripts/quick_validate.py') { $p = Join-Path "$HOME\.agents\skills\skill-writer" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/sentry/skill-writer/$f" -UseBasicParsing -OutFile $p }

Any other agent: save the file into its skills folder, or give it the link to the file: https://anymodel.org/en/skills/sentry/skill-writer/SKILL.md

SKILL.md

Raw

Skill Writer

Use this as the single canonical workflow for skill creation and improvement. Primary success condition: maximize high-value input coverage before authoring while minimizing wasted runtime tokens.

Follow the workflow steps in order. Load only the reference files required for the step you are on. SKILL.md is the primary router: every bundled reference file should be flat under references/ and listed here with a direct "open when..." reason.

Core Workflow References

Open when you need to... Read
choose the minimum workflow path for create, update, iterate, or research-first work references/mode-selection.md
choose the simplest adequate execution shape before deciding files references/execution-shapes.md
apply writing constraints for depth, concision, and portability references/design-principles.md
decide what belongs in SKILL.md, references/, SPEC.md, or supporting files references/reference-architecture.md
create or update the maintenance contract for a skill references/spec-template.md
find missing high-signal sources, including history and regressions references/source-discovery.md
adapt an upstream prompt, workflow, rubric, benchmark, or docs into a skill references/source-adaptation.md
run the full synthesis pass with coverage checks and source capture references/synthesis-path.md
author or update SKILL.md, SPEC.md, and supporting files references/authoring-path.md
improve trigger language and false-positive/false-negative behavior references/description-optimization.md
iterate from positive, negative, or fix examples references/iteration-path.md
store persistent working and holdout examples for future revisions references/iteration-evidence.md
choose a response template, schema, or output contract references/output-contracts.md
add or update evals for a skill's generated outputs or runtime behavior references/skill-evals.md
troubleshoot overloaded layouts, hidden refs, or other structure failures references/structure-troubleshooting.md
register the skill and run final validation checks references/registration-validation.md

Artifact Layout References

Open when you need to... Read
keep the whole skill inline in one coherent SKILL.md references/layout-inline-skill.md
split optional deep knowledge into focused routed references references/layout-reference-backed-skill.md
add scripts for deterministic automation or validation references/layout-script-backed-workflow.md
define a skill that is usually invoked with explicit arguments references/layout-argument-driven-skill.md
ship reusable templates, schemas, or other static assets references/layout-asset-template-skill.md

Workflow Mechanic References

Open when you need to... Read
break a task into fixed ordered steps references/workflow-prompt-chaining.md
classify requests and route them to different downstream paths references/workflow-routing.md
split independent work into parallel units or votes references/workflow-parallel.md
discover work units dynamically and coordinate worker outputs references/workflow-orchestrator-workers.md
run validate-fix-repeat checks during authoring or execution references/workflow-validation-loops.md
validate a plan before executing a risky action references/workflow-plan-validate-execute.md

Claude Code References

Open when you need to... Read
use Claude-specific frontmatter or invocation controls references/claude-frontmatter-invocation.md
use Claude argument fields or substitution variables references/claude-argument-substitutions.md
build a skill that runs in isolated context: fork references/claude-subagent-fork.md
build a skill that uses Claude hooks for deterministic enforcement references/claude-hook-backed.md
use Claude shell preprocessing for dynamic context injection references/claude-dynamic-context.md

Example Profiles

Open when you need to... Read
see the expected depth for a documentation-heavy skill references/example-documentation-skill.md
see the expected depth for a workflow-process skill references/example-workflow-process-skill.md
see what a good routed skill looks like references/example-router-skill.md
see what a good subagent-fork skill looks like references/example-subagent-fork-skill.md
see what a good hook-backed skill looks like references/example-hook-backed-skill.md

Step 1: Resolve target, path, and shape

  1. Resolve the intended operation (create, update, synthesize, iterate) and inspect workspace prior art before choosing where files belong.
  2. Choose the target skill root from observed conventions. If the canonical location is still unclear after inspection, ask one direct question before editing files.
  3. Read references/mode-selection.md to choose the minimum required workflow paths.
  4. Read references/execution-shapes.md to choose the primary execution shape.
  5. Default to the simplest adequate shape. If selecting a more complex shape, record why simpler shapes were rejected.
  6. Load only the exact artifact-layout, workflow-mechanic, and provider-specific leaf files required by that shape.
  7. Before adding guidance, identify what existing rule, section, or file should be narrowed, replaced, or removed.
  8. Record portability implications before using provider-specific mechanics.

Step 2: Run synthesis when needed

Read references/synthesis-path.md.

  1. Use this path for new skills, material changes, and research-first planning.
  2. Collect and score relevant sources with provenance.
  3. Read references/source-discovery.md when source material is thin, stale, or ambiguous.
  4. Read references/source-adaptation.md when adapting an upstream prompt, workflow, rubric, benchmark, or docs.
  5. Produce source-backed decisions and coverage/gap status, including the class and execution-shape choice.
  6. Load example profiles only when they add concrete depth for the selected class or shape.
  7. If the skill uses provider-specific mechanics, include current official provider docs and capture usage constraints.
  8. Do not move to authoring until required coverage is understood or gaps are explicit.

Step 3: Run iteration first when improving from outcomes/examples

Read references/iteration-path.md first when selected path includes iteration (for example operation iterate).

  1. Capture and anonymize examples with provenance.
  2. Read references/iteration-evidence.md when examples should persist beyond the current turn.
  3. Review skill behavior against working and holdout slices.
  4. Propose improvements from positive/negative/fix evidence.
  5. Carry concrete behavior deltas into authoring.

Skip this step when selected path does not include iteration.

Step 4: Author or update skill artifacts

Read references/authoring-path.md.

  1. Write or update SKILL.md in imperative voice with trigger-rich description.
  2. Keep SKILL.md as the runtime router, not an encyclopedia.
  3. Run the pre-edit precision check in references/authoring-path.md before creating new sections or files.
  4. Read references/reference-architecture.md before adding bulk instructions or new reference files.
  5. Create or update SPEC.md using references/spec-template.md when creating a new skill or materially changing its contract.
  6. Create focused reference files, scripts, and assets only when each one has a clear "open when..." reason and cannot be handled by tightening an existing file.
  7. If you add a bundled reference file, add a direct routing entry for it in this SKILL.md.
  8. Prefer checklists, tables, templates, and input/output examples over explanatory prose.
  9. Follow only the specific artifact-layout, workflow-mechanic, Claude-specific, and output-contract references selected for this skill.
  10. For advanced execution shapes, add the required routing, delegation, or safety contracts before considering the skill complete.
  11. For authoring/generator skills, include transformed examples in references:
  • happy-path
  • secure/robust variant
  • anti-pattern + corrected version
  1. Read references/skill-evals.md when the request asks for evals, regression cases, benchmark cases, or model-graded quality checks for the skill being authored.
  2. After any skill artifact changes, run the post-change precision pass in references/authoring-path.md before description optimization or validation.

Step 5: Optimize description quality

Read references/description-optimization.md.

  1. Validate should-trigger and should-not-trigger query sets.
  2. Reduce false positives and false negatives with targeted description edits.
  3. Keep trigger language generic across providers unless the skill is intentionally provider-specific.

Step 6: Register and validate

Read references/registration-validation.md.

  1. Apply repository registration steps for the active layout you verified in the workspace.
  2. Run quick validation for structural checks.
  3. Review validator warnings, precision-pass results, and coverage gaps with judgment before completion.

Output format

Return:

  1. Summary
  2. Changes Made
  3. Validation Results
  4. Open Gaps

Connect through AnyModel API

This skill runs on whatever model your agent uses. Point Claude Code, Codex or Cursor at AnyModel to run it on Claude, GPT, Gemini and more with one key — pay per token, no subscription.

More from the pack Sentry skills

AGENTS.md and CLAUDE.md writer

Writes or trims a repository's AGENTS.md to under 60 lines of commands, conventions and pointers to existing docs, checks every path, and makes CLAUDE.md a symlink to it. Use when a repo needs agent instructions or its current file has grown long or stale.

Claude Code settings audit

Detects a repository's stack and proposes a Claude Code settings.json allow list of read-only commands for the tools it actually uses, plus docs domains and Sentry or Linear MCP entries. Use when setting up Claude Code permissions or auditing existing ones.

Code review, Sentry practices

Reviews a change by Sentry's guidelines: runtime errors, performance and N+1 queries, side effects, compatibility, security, design and tests, with a polite tone and approval once only minor issues remain. Use when reviewing a pull request or branch.

Code simplifier

Simplifies recently changed code without changing behaviour: less nesting, no nested ternaries, clearer names, no redundant abstractions, while following CLAUDE.md conventions. Use when code works but reads heavier than it should and needs a cleanup pass.

Conventional commit messages

Commits in Sentry's Conventional Commits style: a feature branch instead of main, a typed capitalised subject up to 70 characters, Fixes or Refs footers, no personal data. Use when asked to commit changes or draft a commit message.

Django access control review

Audits Django and DRF code for IDOR and broken access control by learning the app's authorization model and tracing each endpoint from ID to query, reporting only confirmed gaps with enforcing fixes. Use when reviewing views, viewsets or tenant isolation.

Find bugs in branch changes

Reviews the commits on the current branch for security holes, bugs and quality issues with an eleven-item checklist and reports verified findings with file, line, severity and fix, without editing code. Use when you want a security-first pass before a PR.

GitHub Actions security review

Audits GitHub Actions workflows for attacks an outsider without write access can run: pwn requests, expression injection, comment commands, token theft, poisoned agent configs, unpinned actions. Use when reviewing CI security or changing workflows.

Iterate a PR until CI is green

Drives an open PR to green: fixes failing CI and high and medium review comments, verifies locally, commits, pushes and repeats, stopping at human approval or draft gates. Use when a PR is red or has review feedback to work through.

PR title and description writer

Writes or refreshes a PR title in Sentry's conventional format and a short reviewer-facing description without template headings or test logs, then opens a draft or updates the PR. Use when opening a PR or after commits change its scope.

Prompt optimizer

Writes, repairs or ports system and agent prompts against a small eval set, comparing candidate rewrites on the same cases and checking the winner on held-out ones. Use when a prompt is unreliable, moves to another model family or needs evals.

Secret leaks through serialization

Finds secrets that leak when a credential field on a dataclass, pydantic model or JS object meets code that logs or traces whole objects, searching the whole repository for the other half. Use when a change adds such a field or a wholesale sink.

SECURITY_MODEL.md for review tools

Writes and maintains SECURITY_MODEL.md, telling security review tools a repository's exposure, invariants, reportable finding classes and owner-confirmed exclusions, with a script that flags stale references. Use when preparing a repo for automated review.

Agent skill security scanner

Audits an agent skill before installation: a static scan for prompt injection, hidden Unicode, secrets, risky scripts and structural traps, then a review of intent and permissions ending in a verdict. Use when a skill comes from an outside source.

Security review, Sentry

Reviews a file, diff or component for exploitable vulnerabilities with OWASP-based references, researches the codebase before flagging and reports only findings reached by attacker-controlled input. Use when a change needs a low-noise security review.

Django performance review

Reviews Django and DRF code for N+1 queries, unbounded querysets, missing indexes and write loops, validating table size and hot paths before reporting. Use when a Django view or endpoint is slow or a change touches large tables.