← Search

Implement
Development 📌 Pinned version: commit 5beb35b
⚙ Needs: Before you start: read this whole install prompt…

Implement

A short, user-invoked engineering workflow that carries out a piece of work described by a spec or a set of tickets: it resolves a ticket reference through the user's own issue tracker when one is passed

At a glance
What
A short, user-invoked engineering workflow that carries out a piece of work described by a spec or a set of tickets: it resolves a ticket reference through the user's own issue tracker when one is passed
Cost
Free
Needs
Before you start: read this whole install prompt, tell me in a few lines what this skill does and what installing it involves, and wait for my go-ahead before you do anything else.
Install
Copy the installer prompt below into your Muse — your agent does the rest.

Version:

⌁

Install

Copy the install package below, then paste it into Muse📌 Pinned version: commit 5beb35b

Before you start: read this whole install prompt, tell me in a few lines what this skill does and what installing it involves, and wait for my go-ahead before you do anything else. Prerequisites — None to install this skill — no account, no key, no payment, and no script in its folder. Two things to know before using it: first, at use time it calls the separate tdd and code-review skills from the same repository, so those need to be installed too for its workflow to run as written; second, using it does real work in my project — it writes code, runs typechecking and tests, fetches a ticket from my own issue tracker if I pass a reference, and commits the finished work to my current branch, exactly as its instructions say. It is user-invoked only: it starts when I invoke it, never on its own. Install "Implement" for me. When I invoke it with a spec or a set of tickets, it implements that work: if I pass a ticket reference it fetches the ticket from my issue tracker and states its title before starting (and asks me if the reference is ambiguous), it builds with the tdd skill at seams we agreed in advance, runs typechecking and single test files regularly and the full test suite once at the end, then calls the code-review skill to review the work, and commits it to my current branch. Its folder is only those instructions plus its agent policy file, which marks it user-invoked only. Repository: https://github.com/mattpocock/skills (the skill is the whole skills/engineering/implement/ folder at the pinned commit: SKILL.md plus 1 companion files, 2 files in total) Pinned version: install the code at commit 5beb35b040e3de97e54fa9e386d7e42d15c295c2 exactly. Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Clone https://github.com/mattpocock/skills into a temporary folder, check out commit 5beb35b040e3de97e54fa9e386d7e42d15c295c2, and copy the skills/engineering/implement/ folder from that checkout. Then compare every file in the folder with the fingerprints recorded for this listing on 2026-10-22: [FINGERPRINTS] - SKILL.md: SHA-256 483bdc4ccf4ac31d86ac7beeaa0d0db80313e71e120bb8c59b3196ae5decd53d - agents/openai.yaml: SHA-256 8970a8596ade0c28ab427f41a4ea242d6bdf6186c59ebf55e1238dbecaab79dc If a file does not match, it changed since the listing was prepared: do not install it yet, tell me what you found and let me decide. 2. Read SKILL.md in full, and tell me in plain words: what the skill does when used, what it connects to, whether it reads or sends any personal information or credentials, and anything that seems unusual. Stop on any red flag and tell me before going further. Confirm these points from the files: - The skill folder holds 2 files only: a 622-byte SKILL.md with the workflow above, and agents/openai.yaml declaring its display name and its user-only invocation policy. There is no script and no other code in it. - Nothing is sent anywhere during installation itself; the only download at install time is the skill folder from GitHub at the pinned commit. - At use time, the work happens in my own project and conversation: code is written and tests are run locally, a ticket reference I pass is fetched from my own issue tracker, and the finished work is committed to my current branch — all of it disclosed in the prerequisites above. This install does none of that: no project is touched, no ticket is fetched, no test is run and no commit is made. - Do not implement anything, do not call the tdd or code-review skills, and do not use the skill in any way during this install: using it is a separate step that only starts when I invoke it later. 3. When I say "yes, install", install it as a skill: copy the whole implement folder into the agent's skills directory, in a folder named exactly "implement", keeping its 2 files in their original relative layout (SKILL.md at its root). 4. Verify with no network calls: frontmatter valid (name: implement), the 2 files in place with matching fingerprints. Do not run anything from the folder and do not use the skill to verify. 5. Report what was installed, where, and what I still need to do myself (for example: that the separate tdd and code-review skills from the same repository should also be installed for its workflow, and that using it writes code, runs tests and commits to my current branch — using it is a separate step that only starts when I invoke it). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.

🔒 Security, provenance and what this touches
🧭 What this touches
Based on the install prompt we scanned, this build does not run commands, make third-party network calls, install packages, write files, or ask for API keys.
Install prompt analysis · 2026-10-22
🔒 Security and provenance
📌 Pinned version: commit 5beb35b · 2026-10-22
🔎 Last checked · Oct 23, 2026 : no change detected in the files linked by this install prompt
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Wanna be extra careful?

The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?

How to check a build before installing →

?

Questions

How do I install a build?

Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.

Where does my money go?

Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.

What does the ✓ next to a creator’s name mean?

It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.