Skip to content
Skills Library
Programming · Building & coding

implement

/implement

Research, test, implement, document and validate a cargo-fallow feature, fix or repository change. Use when asked to build or change cargo-fallow.

Licence
MIT
Last repository change
10.11.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 10.11.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Research, test, implement, document and validate a cargo-fallow feature, fix or repository change. Use when asked to build or change cargo-fallow.

Original author description

Research, test, implement, document and validate a cargo-fallow feature, fix or repository change. Use when asked to build or change cargo-fallow.

How it works

  1. Definition of done
Original SKILL.md headings · 58 lines, 431 words
SKILL.md preview
---
name: implement
description: Research, test, implement, document and validate a cargo-fallow feature, fix or repository change. Use when asked to build or change cargo-fallow.
---

# Implement

Deliver the change through the lifecycle of this repository:
`implement`, then `review`, then `ship`, then `sweep`.

1. Read `AGENTS.md`, `CONTRIBUTING.md` and the page in `docs/` of each
   command that the change touches.
2. Check the branch, the worktree, the open pull requests and `origin/main`.
   Other workers can use the same checkout. Make a worktree from the newest
   `origin/main` with a branch `<type>/<slug>`. The type is a conventional
   commit type.
3. Look at how fallow does the same thing for TypeScript. Keep its names,
   flags, JSON fields and exit codes where they make sense for Rust.
4. Write a failing test first. For a bug, get a command that fails before
   you change the code. A Rust test goes under `tests/`. A script test is
   `scripts/<name>.test.mjs`.
5. Write the code. Keep the module layout of `AGENTS.md`. A file over 2000
   lines must not grow, so move new code to a new module.
6. Validate a change to the analysis on real workspaces: the corpus in
   `tests/corpus/README.md` and cargo-fallow itself. A false positive is
   not acceptable. When the syntax cannot decide, give credit and do not
   report.
7. Update `README.md`, `docs/`, `docs/output-schema.json`,
   `action/README.md` and `docs/gitlab.md` where the behavior shows.
8. Add a changelog fragment `changelog.d/<slug>.md` for a change that a
   user can see. The check reads only the top level of `changelog.d/`, so
   the name has no `/`. Do not edit `CHANGELOG.md`. `changelog.d/README.md` gives
   the format.
9. Run the gates:

   ```bash
   cargo fmt --check
   cargo clippy --all-targets --locked -- -D warnings
   cargo nextest run --locked
   npm run lint:js && npm run fmt:js:check && npm run test:scripts
   npm run check:agent-adapters
   node scripts/changelog-fragments.mjs check --base origin/main
   node scripts/check-file-size.mjs --base origin/main
   ```

   The Quality gates table in `CONTRIBUTING.md` lists every other gate.
   Run each gate of that table that the change touches.
10. Commit signed with `git commit -S -s` and a conventional prefix. Push
    and open a pull request. Write each open item in the body.
11. Continue with `review`, `ship` and `sweep` in the same session. Do not
    stop at an open pull request. Stop only for a decision of the owner.

## Definition of done

- Each pull request of the objective is merged to `main`, and CI on the
  merged commit is green.
- Pinned auto-merge was armed before each CI wait. In a T3 Code thread,
  each merge was by hand at a wake (see `ship`).
- Each follow-up is fixed in a pull request or filed as an issue in
  `fallow-rs/cargo-fallow`. A note in an ignored file, in `/tmp` or in the
  chat does not track a follow-up.

Versions

RepositoryScoreLicence
This page · fallow-rs/cargo-fallow100MIT
ericrisco/rsc-harness100MIT
yonatangross/orchestkit100MIT
sentimony/agentic-workflow100MIT
moberghr/mtk-agent-toolkit100MIT
michielvandermeer/skills100MIT
rossumai/claude-marketplace100MIT
userKael/rastro100MIT
yonatangross/orchestkit100MIT

Database snapshot: 13.11.2026 · package version b086062c3d8c (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100cargo-fallow
    Codebase analysis for Rust workspaces with `cargo fallow`. Finds unused dependencies, unused source files, `pub` items that can be private, boundary violations, large files and functions, complex functions, duplicated code and public API changes, and runs mutation testing. Use…
  • 100fallow-mutation
    Mutation testing for TypeScript and JavaScript with `fallow mutation`. Use when asked to improve, strengthen or check the tests of a change, a PR, a branch or a file, to check whether a test can fail at all, to find behavior that the tests do not protect, to find redundant…
  • 100cargo-fallow-release
    Release cargo-fallow, bump its version, publish the crate, tag a version, or publish the GitHub Action to the Marketplace. Use when asked to release or to cut a version.
  • 100fallow-codex-onboarding
    Set up the Fallow app in Codex after the plugin is installed: check the fallow installation, choose the default analysis scope, run the first analysis, and show the user where the dashboard, the Code Health tab, @Fallow mentions and the config editor are. Use when the user…
  • 90cargo-workflows
    Use when managing Cargo workspaces, feature flags, build scripts, CI caching, dependency auditing, or Cargo.lock with Rust.
  • 100cargo-test
    Expert Cargo test assistance covering Rust unit tests, integration tests, and benchmarks. Use when running `cargo test`, writing unit tests in Rust, or debugging test failures.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.