Skip to content
SkillModel-led106 tokens in use

Implement

Builds the work in a spec or ticket by driving TDD at pre-agreed seams, then runs code-review and commits to the current branch.

328,754 stars on the repository MIT Licensemattpocock/skills · skills/engineering/implement
claude plugin install mattpocock-skills@claude-plugins-official
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Implement costs

16tokens idle
106tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts and code blocks. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Needs attention
  • Frontmatter8/15
  • Structure0/25
  • Examples0/15
  • Output0/15
  • Size15/15
  • Resources0/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity96
  • Maintenance100
  • Community56
  • Maturity32
  • Momentum40

Implement takes the work described in a spec or tickets and builds it. If you pass a ticket reference it fetches the ticket from the issue tracker and states its title first, and it asks when the reference is ambiguous.

It calls the tdd skill where possible at pre-agreed seams, runs typechecking and single test files regularly and the full suite once at the end, calls code-review, and commits.

What You Get

  • The ticket title stated back to you before work starts
  • Code built test-first through the tdd skill
  • Typechecks, single-file test runs and one full test run at the end
  • A code-review pass over the result
  • A commit on the current branch

Common Use Cases

  • Working through local ticket files blockers-first, one fresh session each
  • Building a small change in the same context window where it was grilled
  • Picking up an agent-ready issue produced by triage

What Makes It Unique

It is deliberately short and delegates: test-first building to tdd and review to code-review. It handles one ticket in one context window and pairs with implement-spec for running a whole spec at once. The test cadence is explicit: typecheck and single test files often, the full suite once.

Under The Hood

SKILL.md is a short Markdown instruction with no scripts. The model fetches a ticket from your configured issue tracker, runs typecheck and test commands, invokes the tdd and code-review skills through the Skill tool, edits files in your working tree and commits to the current branch. Automatic model invocation is disabled, so it runs only when you call it.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers