implement-spec

An agent skill by mattpocock, from mattpocock/skills. Tags: code, delivery, development, spec, workflow.

What it does

Implement the result of /to-spec and /to-tickets in code.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add mattpocock/skills --skill implement-spec

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/mattpocock/skills
cp -r skills/skills/engineering/implement-spec ~/.claude/skills/implement-spec

Safety box score

Grade C, moderate risk: 25 of 100 risk points, rated 2026-10-16. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill orchestrates end-to-end code implementation on an integration branch, using worktrees, subagents, merges, code review, and optional draft PRs. The main risks are broad autonomous repo changes and publishing work to a remote tracker; the skill files themselves contain no scripts, secrets handling, or hidden code.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	0 (none)	`SKILL.md` does not define any shell commands, scripts, or code execution; it only references other skills by name (`tdd`, `code-review`).
Network access	2 (moderate)	It can open a draft PR and later mark it ready (`"open a draft PR"`, `"mark it ready for review"`), which publishes work to a remote service when enabled.
Filesystem reach	2 (moderate)	It explicitly creates branches and per-ticket worktrees, and asks exploration subagents to save notes outside the repo (`"each in its own worktree"`, `"save its markdown notes in a directory outside the repo"`).
Secrets & credentials	0 (none)	The skill does not ask for tokens, passwords, `.env` files, keychains, or browser sessions.
Privilege & persistence	0 (none)	No sudo, global installs, services, shell startup edits, or other privilege changes are requested.
Instruction hijack surface	0 (none)	There are no instructions to ignore higher-level policy, hide actions, or follow remote instructions; the text is workflow guidance only.
Irreversible actions	3 (high)	The skill directs an agent to implement the entire spec, merge ticket work, run code review, resolve issues, and optionally publish via PR (`"entire spec implemented"`, `"merge its work"`, `"call ... code-review"`).
Transparency	0 (none)	The provided files are plain text Markdown/YAML; there are no binaries, minified blobs, or runtime-decoded content.

Before installing

Confirm you are okay with an agent creating branches, worktrees, and merging into an integration branch in your local repo.
Check whether your workflow allows draft PR creation and later publication to your remote host.
Note that exploration notes may be written outside the repo; make sure that shared directory is acceptable on your machine.

Rated 2026-10-16 by an automated review of 2 files from the skill's repository.

Source

Repository: mattpocock/skills (all skills from this repository)
Path: skills/engineering/implement-spec/SKILL.md
Branch: main
Updated: 2026-10-05

implement — Implement a piece of work based on a spec or set of tickets.
tdd — Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
expo-project-structure — Framework (OSS). Folder structure for a new Expo app.
new-branch-and-pr — Create a fresh branch, complete work, and open a pull request
Poteto Mode — poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work.
principle-never-block-on-the-human — Apply when tempted to ask 'should I do X?' on reversible work. Proceed, present the result, let the human course-correct after the fact.