agentleFS
jisuzzzzjisuzzzz/haechi/skills/implement-work/SKILL.md

implement-work

Skill17 starsChanged 14 days agoMITView on GitHub

Implement an assigned change and report behavior evidence. Use for delegated implementation with a task brief and explicit file ownership.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Follow assigned file ownership exactly.

    line 10
  2. Distinctive:

    Follow AGENTS.md and surrounding conventions.

    line 11

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Implement assigned work

Apply the common work contract, including its implementation, evidence reuse, verification, review and completion requirements. Reuse its current delivered body; this method adds worker-specific duties below.

  • Follow assigned file ownership exactly. Report needed changes elsewhere; other agents may be editing concurrently. The main owns Git: never commit, stash, checkout, reset or switch branches.
  • Follow AGENTS.md and surrounding conventions. Match local style; do not reformat untouched lines. For UI changes, inspect the selected reference, existing components, tokens, extension points and consumers. Prefer reuse or compatible extension; explain a new component when existing options do not fit.
  • Own the tests the authorized change needs. Update tests broken by an intended change and test new observable behavior. Fix a supplied bug reproduction at the cause; never weaken it to pass. Do not wait for a later adversarial tester to supply required coverage.
  • Use the supplied repo verify/single-test commands within ownership, respect forbidden commands and address their failures. Apply the common contract's evidence-validity rules rather than rerunning every suite after every edit. Report behavior tests separately from rendered design/interaction checks; missing browser/reference access leaves affected visual claims unverified.
  • Resolve routine choices from the brief, accepted requirements and repo conventions. Make reversible in-scope choices. Report consequential missing information or conflicts to the main, including effects on other contracts/jobs; continue independent authorized work.
  • Return the packet identifier, changed files, what changed and why, actual commands/results, applicable reused evidence, open questions and deliberate omissions. Link required behavior to assertions/interactions on the final relevant state. Missing proof is unverified; unresolved expectations need a decision. Existing tool outputs suffice; a new report file or recorder is not required unless the assignment requests one.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.