Implement a spec

Implements a spec and its tickets on one integration branch: a fresh implementer subagent per ticket in its own worktree, run in parallel along the blocking graph, then a code review and one fix pass. Use when the tickets from to-tickets are ready.

CodingPack: Matt Pocock's skills42 linesimplement-spec
Author
Source
mattpocock/skills/skills/engineering/implement-spec @ abeeaf9
License
MIT · Copyright (c) 2026 Matt Pocock

About this skill

What it does

Implement spec turns a spec and its tickets into code on one integration branch, with the agent acting as coordinator. It reads the tickets as a task graph with blocking edges, so there is always a frontier of tickets ready to start. An optional explorer subagent leaves notes outside the repo for the rest. Each ticket goes to a fresh implementer subagent in its own worktree and branch, in the background, several at once. An implementer checks its base, builds the ticket with the tdd skill and merges the integration tip in before reporting. A merger subagent then brings the work into the integration branch, and tickets this unblocks get their own implementers.

Once every ticket is in, the agent runs the code-review skill on the integration branch and hands all findings to one fresh implementer. If the tracker closes work through PRs, or you ask for one, a draft PR opens after the first merge and is marked ready at the end; otherwise the tickets are closed the tracker's way. Worktrees are removed last. Subagents pass pointers to the spec, tickets, notes and commits, not pasted text.

The folder holds SKILL.md, the licence and agents/openai.yaml, which also turns off implicit invocation in Codex.

When to use it, and when not

Use it when the spec and its tickets already exist, written by to-spec and to-tickets, and your tool can run background subagents in separate worktrees.

Without tickets there is no graph to work, so write them first. A change that fits in one ticket is simpler to build with tdd directly.

How to run it

The install command below puts the whole folder in place. The frontmatter sets disable-model-invocation: true, so the agent never starts it by itself; you call it:

  • Claude Code: only the /implement-spec command — naming the skill in a message will not start it.
  • Codex: $implement-spec.
  • Cursor: type / in the Agent chat and pick implement-spec.

Example: /implement-spec The spec is issue #120 and its sub-issues are the tickets. Use feat/csv-export as the integration branch.

The skill expects the project's issue tracker to be known. The author's setup-matt-pocock-skills sets that up; it is not in our catalog, and you can just tell the agent which tracker holds the spec and tickets. Install tdd and code-review alongside: the skill calls both.

How it differs from similar skills

Subagent-driven development also gives each task a fresh implementer, but strictly one at a time from a plan file, with a review after every task. Implement spec runs implementers in parallel along the ticket graph and reviews once at the end. Incremental implementation is slice-test-verify discipline for one agent, with no orchestration. Executing plans works through a plan file in the current session, task by task, with no implementer subagents and one review of the whole branch at the end. Dispatching parallel agents also runs subagents side by side, but on independent problems such as unrelated test failures, with no tickets, worktrees or blocking graph.

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/implement-spec/SKILL.md https://anymodel.org/en/skills/matt-pocock/implement-spec/SKILL.md -o ~/.claude/skills/implement-spec/LICENSE https://anymodel.org/en/skills/matt-pocock/implement-spec/LICENSE -o ~/.claude/skills/implement-spec/agents/openai.yaml https://anymodel.org/en/skills/matt-pocock/implement-spec/agents/openai.yaml
Codex, Cursor — macOS, Linux
curl -fsSL --create-dirs -o ~/.agents/skills/implement-spec/SKILL.md https://anymodel.org/en/skills/matt-pocock/implement-spec/SKILL.md -o ~/.agents/skills/implement-spec/LICENSE https://anymodel.org/en/skills/matt-pocock/implement-spec/LICENSE -o ~/.agents/skills/implement-spec/agents/openai.yaml https://anymodel.org/en/skills/matt-pocock/implement-spec/agents/openai.yaml
Claude Code — Windows PowerShell
foreach ($f in 'SKILL.md','LICENSE','agents/openai.yaml') { $p = Join-Path "$HOME\.claude\skills\implement-spec" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/matt-pocock/implement-spec/$f" -UseBasicParsing -OutFile $p }
Codex, Cursor — Windows PowerShell
foreach ($f in 'SKILL.md','LICENSE','agents/openai.yaml') { $p = Join-Path "$HOME\.agents\skills\implement-spec" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/matt-pocock/implement-spec/$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/implement-spec/SKILL.md

SKILL.md

Raw

You have been provided a spec. This spec should have tickets associated with it, describing how to implement the spec.

The issue tracker should have been provided to you. If not, tell the user to run /setup-matt-pocock-skills.

The goal is the entire spec implemented on a single integration branch, with every ticket resolved the way the issue tracker closes work.

The tickets are not a list of steps. They are a task graph with blocking relationships between them. This means there is always a frontier of tickets which are ready to be grabbed.

Start every subagent with a fresh context window.

Communication to and from subagents should be sparse. Communicate primarily through context pointers: to the spec, tickets, research notes, and previous commits. Don't duplicate information already available via pointers.

Implementer subagents should be run in the background where possible for maximum concurrency.

Steps

  1. Read the spec and tickets to understand the task graph.

  2. (optional) Use an exploration subagent to conduct any exploration required by the tickets - relevant codebase files or external documentation. Ensure the exploration subagent can save files - it should save its markdown notes in a directory outside the repo, accessible by all future subagents. This lets implementer subagents focus on implementation rather than exploration.

  3. Create the integration branch. If the issue tracker closes work through PRs, or the user asks for one, open a draft PR after the first merge in step 5 (a branch with no commits ahead of main can't open one), marked as closing the spec and tickets.

  4. Use a fresh implementer subagent for each ticket, each in its own worktree on its own branch. Each implementer subagent:

    • confirms its worktree is based on the integration branch before starting, and resets onto it if not;
    • calls the Skill tool with tdd to build the ticket;
    • merges the integration branch tip into its own branch before reporting done
  5. Once an implementer subagent completes, merge its work to the integration branch with a merger subagent.

  6. If this changes the frontier of available tickets, kick off more implementer subagents to work on the new tickets. This allows for maximum concurrency.

  7. Once all tickets are complete, call the Skill tool with code-review on the integration branch. Fix all issues raised by the code review in a single fresh implementer subagent.

  8. If a draft PR exists, mark it ready for review. Otherwise, resolve each ticket the way the issue tracker closes work, and report the integration branch.

  9. Clean up all implementer subagent worktrees.

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 Matt Pocock's skills

Code review against standards and spec

Reviews the diff since a commit, branch or tag on two axes in parallel subagents: the repo's written standards plus a baseline of Fowler code smells, and the originating spec or issue. Use when a branch or PR needs checking against its spec.

Deep module design

Fixes a shared vocabulary for deep modules (interface, seam, adapter, depth, leverage), with the deletion test, dependency categories and a design-it-twice pattern on parallel subagents. Use when designing a module's interface or deciding where a seam goes.

Diagnosing hard bugs

Diagnoses hard bugs and slowdowns by first building a fast, deterministic command that reproduces the exact symptom, then minimising it, ranking falsifiable hypotheses and adding a regression test at a real seam. Use when something fails, throws or got slow.

Domain modeling

Sharpens a project's domain language during design: challenges fuzzy or conflicting terms, writes resolved ones to GLOSSARY.md at once and offers a short ADR only for hard-to-reverse trade-offs. Use when discussing terminology or recording an ADR.

Improve codebase architecture

Finds shallow modules worth deepening, starting from the code that changes most, shows the candidates in an HTML report with before/after diagrams and grills the chosen one with you. Use when a codebase has grown hard to test or navigate.

Throwaway prototype

Builds throwaway code to answer one design question: a single-file clickable HTML demo for a state model, or several structurally different UI variants on one route switched by a URL param. Use when checking whether logic holds or how a page should look.

Coding session retrospective

Reviews a finished coding session from its logs and proposes changes to the agent's environment: navigation pointers, lint rules, pre-commit and CI checks, reviewer standards, tool use. Use when an agent session went slowly or made avoidable mistakes.

TDD with integration tests

Drives test-first work through public interfaces: agrees the seams to test with the user, runs one red-green cycle per test, mocks only at system boundaries and leaves refactoring to review. Use when building a feature or fixing a bug test-first.

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.

Spec to tickets

Splits a spec, plan or conversation into tracer-bullet tickets, vertical slices that each fit one agent session, with blocking edges, and publishes them as local files or tracker issues. Use when work is too big for one session and needs a task graph.

Issue and PR triage

Triages issues and external PRs on the tracker: gives each a category and a state, checks for existing code and past rejections, reproduces bugs and writes agent briefs for ready work. Use when a maintainer works through incoming issues and PRs.

Wayfinder for huge work

Charts work too big for one agent session as a map issue with child decision tickets on the tracker, then resolves one ticket per session until the route to the goal is clear. Use when a large effort has open questions that block a spec or plan.

Bash wizard for manual steps

Generates an interactive bash script that walks a person through manual steps such as dashboard setup, API keys and CI secrets, opening each URL and saving values to .env and GitHub secrets. Use when setup or a migration needs steps only a human can take.

Git guardrails for Claude Code

Installs a Claude Code PreToolUse hook that stops the usual forms of git push, reset --hard, clean -f, branch -D and checkout or restore of the whole tree, for one project or all, then tests it. Use when you want a safety net against an agent pushing or discarding work on its own.

Migrate tests to shoehorn

Replaces as and as unknown as casts in TypeScript tests with fromPartial and fromAny from @total-typescript/shoehorn, adds the imports and runs the type check. Use when tests fake whole objects or cast partial test data to satisfy the compiler.

Pre-commit hooks setup

Sets up Husky and lint-staged in a Node repo so each commit runs Prettier on staged files, then the typecheck and test scripts, matched to the lockfile, and makes the first commit through the hook. Use when a repo has no commit-time checks.

Grilling a plan

Questions the user about a plan or decision in rounds of numbered questions with recommended answers, looks facts up itself through subagents and stops only when no decision is left assumed. Use when a plan needs stress-testing before work starts.

Teach me a topic

Runs a multi-session course in the current folder: a mission, trusted sources, short HTML lessons with quizzes, reference sheets and learning records that set the next lesson. Use when the user wants to learn a topic over time, not get one answer.

Decision questionnaire

Writes a Markdown questionnaire for someone who holds knowledge the user lacks, after asking only who it goes to and what answers are needed, with the most important questions first. Use when a decision depends on facts from another person.

Writing for agents

Gives the rules for writing text agents read: skill descriptions as context pointers, what to keep inline and what to move to a separate file, completion criteria, leading words and pruning. Use when creating or editing a skill, AGENTS.md or CLAUDE.md.