Conversation to spec
Turns the current conversation and codebase into a spec with user stories, implementation and testing decisions, and publishes it to the issue tracker as ready-for-agent, without interviewing the user. Use when a discussed feature needs writing up.
to-spec- Author
- Matt Pocock
- Source
- mattpocock/skills/skills/engineering/to-spec @ abeeaf9
- License
- MIT · Copyright (c) 2026 Matt Pocock
About this skill
What it does
To-spec writes up what you and the agent have already discussed as a spec and publishes it to the project's issue tracker. There is no interview: the agent explores the repo, uses the glossary terms, respects ADRs and synthesises. It only checks with you the seams where the feature will be tested: existing ones first, as high as possible, ideally one.
The template is fixed: the problem and the solution from the user's side, a long numbered list of user stories ("As an <actor>, I want…, so that…"), implementation decisions (modules, interfaces, schema changes, API contracts), testing decisions with prior art from the codebase, out of scope and further notes. File paths and code are left out because they go stale, except a prototype snippet that pins a decision, such as a state machine or a type shape, better than prose. The issue gets the ready-for-agent label.
When to use it, and when not
Use it at the end of a design discussion, when the decisions should land in the tracker.
Skip it while the idea is still vague: the skill fills no gaps by asking, so run Grilling a plan first. It also expects the agent to know the tracker and its labels. The author's setup-matt-pocock-skills configures that but is not in our catalog; you can just tell the agent which tracker and label to use.
How to run it
The install command below puts the folder in place: SKILL.md with the template, the licence and the Codex manifest agents/openai.yaml. With disable-model-invocation: true the agent never starts it on its own; call it:
- Claude Code: only the
/to-speccommand — naming the skill in a message will not start it. - Codex:
$to-spec. - Cursor: type
/in the Agent chat and pickto-spec.
Example: /to-spec Write up what we agreed about CSV export as a GitHub issue.
Next in the author's chain: Spec to tickets splits the spec, Implement a spec builds it. Install all three.
How it differs from similar skills
Spec-first kickoff starts from a raw idea, asks up to five questions with defaults and writes a one-page spec with a short plan, saved as SPEC.md if you agree. Spec-driven development also asks and lists assumptions, covers commands, structure, code style and boundaries, and keeps the spec in the repo. To-spec comes later: the questions are behind you, the output is an issue, and the weight is on user stories and test seams. Document co-authoring workflow builds a document with you from the start: numbered questions, options for each section, then a test on a subagent that sees only the text; nothing goes to a tracker.
Install
Run one command — it saves SKILL.md and the files it uses into your agent's skills folder. Claude Code and Codex pick up a new skill without a restart; if it does not show up, restart the agent.
curl -fsSL --create-dirs -o ~/.claude/skills/to-spec/SKILL.md https://anymodel.org/en/skills/matt-pocock/to-spec/SKILL.md -o ~/.claude/skills/to-spec/LICENSE https://anymodel.org/en/skills/matt-pocock/to-spec/LICENSE -o ~/.claude/skills/to-spec/agents/openai.yaml https://anymodel.org/en/skills/matt-pocock/to-spec/agents/openai.yaml
curl -fsSL --create-dirs -o ~/.agents/skills/to-spec/SKILL.md https://anymodel.org/en/skills/matt-pocock/to-spec/SKILL.md -o ~/.agents/skills/to-spec/LICENSE https://anymodel.org/en/skills/matt-pocock/to-spec/LICENSE -o ~/.agents/skills/to-spec/agents/openai.yaml https://anymodel.org/en/skills/matt-pocock/to-spec/agents/openai.yaml
foreach ($f in 'SKILL.md','LICENSE','agents/openai.yaml') { $p = Join-Path "$HOME\.claude\skills\to-spec" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/matt-pocock/to-spec/$f" -UseBasicParsing -OutFile $p }foreach ($f in 'SKILL.md','LICENSE','agents/openai.yaml') { $p = Join-Path "$HOME\.agents\skills\to-spec" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/matt-pocock/to-spec/$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/matt-pocock/to-spec/SKILL.md
SKILL.md
This skill takes the current conversation context and codebase understanding and produces a spec. Do NOT interview the user; just synthesize what you already know.
The issue tracker and triage label vocabulary should have been provided to you. If not, tell the user to run /setup-matt-pocock-skills.
Process
Explore the repo to understand the current state of the codebase, if you haven't already. Use the project's domain glossary vocabulary throughout the spec, and respect any ADRs in the area you're touching.
Sketch out the seams at which you're going to test the feature. Existing seams should be preferred to new ones. Use the highest seam possible. If new seams are needed, propose them at the highest point you can. The fewer seams across the codebase, the better - the ideal number is one.
Check with the user that these seams match their expectations.
- Write the spec using the template below, then publish it to the project issue tracker. Apply the
ready-for-agenttriage label - no need for additional triage.
<spec-template>
Problem Statement
The problem that the user is facing, from the user's perspective.
Solution
The solution to the problem, from the user's perspective.
User Stories
A LONG, numbered list of user stories. Each user story should be in the format of:
- As an <actor>, I want a <feature>, so that <benefit>
<user-story-example>
- As a mobile bank customer, I want to see balance on my accounts, so that I can make better informed decisions about my spending </user-story-example>
This list of user stories should be extremely extensive and cover all aspects of the feature.
Implementation Decisions
A list of implementation decisions that were made. This can include:
- The modules that will be built/modified
- The interfaces of those modules that will be modified
- Technical clarifications from the developer
- Architectural decisions
- Schema changes
- API contracts
- Specific interactions
Do NOT include specific file paths or code snippets. They may end up being outdated very quickly.
Exception: if a prototype produced a snippet that encodes a decision more precisely than prose can (state machine, reducer, schema, type shape), inline it within the relevant decision and note briefly that it came from a prototype. Trim to the decision-rich parts, not a working demo, just the important bits.
Testing Decisions
A list of testing decisions that were made. Include:
- A description of what makes a good test (only test external behavior, not implementation details)
- Which modules will be tested
- Prior art for the tests (i.e. similar types of tests in the codebase)
Out of Scope
A description of the things that are out of scope for this spec.
Further Notes
Any further notes about the feature.
</spec-template>
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.
AnyModel