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.
implement-spec- Author
- Matt Pocock
- 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-speccommand — naming the skill in a message will not start it. - Codex:
$implement-spec. - Cursor: type
/in the Agent chat and pickimplement-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.
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
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
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 $p }foreach ($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
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
Read the spec and tickets to understand the task graph.
(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.
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.
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
tddto build the ticket; - merges the integration branch tip into its own branch before reporting done
Once an implementer subagent completes, merge its work to the integration branch with a merger subagent.
If this changes the frontier of available tickets, kick off more implementer subagents to work on the new tickets. This allows for maximum concurrency.
Once all tickets are complete, call the Skill tool with
code-reviewon the integration branch. Fix all issues raised by the code review in a single fresh implementer subagent.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.
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.
AnyModel