MCPInstall

implement

Implement a piece of work based on a spec or set of tickets.

Installs
761
Last 24h
+22
Trending rank
#5331
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/timschoch/mattpocock-skills --skill implement
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads implement automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Implement the work described by the user in the spec or tickets on a separate worktree, based off of the current branch.

If the user passes a ticket reference, fetch it from the issue tracker and state its title before starting. If the reference is ambiguous, ask.

Claim the issue first

Before editing any files, claim the issue you are implementing so a colliding agent skips it (see docs/agents/triage-labels.md). If the work maps to an issue number N:

First, check for an existing claim with gh issue view N --json labels,comments. If in-progress is already set, another agent may be on it: read the latest 🤖 in-progress comment, inspect that branch's real state (open PR? commits? or an empty/abandoned branch?), and skip or coordinate instead of duplicating. Claim only if the issue is free, or the prior claim is clearly abandoned (no open linked PR, the reaper's rule).

Then claim:

gh issue edit N --add-label in-progress --remove-label ready-for-agent
gh issue comment N --body "🤖 in-progress: <branch> (<session>) <date>"

Idempotent: re-running /implement on the same issue must not error: adding a present label, dropping an absent ready-for-agent, and re-commenting are all tolerated. The claim comment must name the working branch (a colliding agent inspects that branch's state, not a lingering worktree).

Release the claim

When you open the PR (work handed to review), release the claim: gh issue edit N --remove-label in-progress. If the flow ends without opening a PR, leave the label; the cleanup-merged-branches reaper releases abandoned claims. Do not restore ready-for-agent on success; the issue closes on merge.

Call the Skill tool with "tdd" where possible, at pre-agreed seams.

Run typechecking regularly, single test files regularly, and the full test suite once at the end.

Commit your work to the current branch.

Once committed, call the Skill tool with "code-review" to review the work. It reads committed work only.

FAQ

What does the implement skill do?

Implement a piece of work based on a spec or set of tickets.

How do I install implement?

Run npx skills add https://github.com/timschoch/mattpocock-skills --skill implement in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/implement/ (personal) or .claude/skills/implement/ (project).

Which AI agents can use implement?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is implement safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains implement?

It is published by timschoch in timschoch/mattpocock-skills. It has 761 recorded installs.

More from timschoch/mattpocock-skills

View all →

domain-modeling

timschoch/mattpocock-skills

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.

ask-matt

timschoch/mattpocock-skills

Ask which skill or flow fits your situation. A router over the skills in this repo.

779 installs

codebase-design

timschoch/mattpocock-skills

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

code-review

timschoch/mattpocock-skills

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

grilling

timschoch/mattpocock-skills

Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

Testing & QA776 installs

diagnosing-bugs

timschoch/mattpocock-skills

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

Popular code quality & workflow skills

View category →

grill-me

mattpocock/skills

A relentless interview to sharpen a plan or design.

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

handoff

mattpocock/skills

Compact the current conversation into a handoff document for another agent to pick up.

domain-modeling

mattpocock/skills

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.

codebase-design

mattpocock/skills

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

diagnosing-bugs

mattpocock/skills

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.