agentleFS
Codagent-AICodagent-AI/agent-skills/skills/task-compliance/SKILL.md

task-compliance

Skill31 starsChanged 6 months agoMITView on GitHub

Review an implementation against task file requirements. Checks every spec scenario and Done When criterion, identifies gaps, and reports them. Use when the user says "task compliance", "check compliance", "review against the task", or to verify implementation completeness before shipping.

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    Report only: Do not fix gaps — surface them for the human to decide how to proceed.

    line 53

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Task Compliance

Review the implementation against the task file(s). Extract every spec scenario (WHEN/THEN) and every Done When criterion, then verify each one was addressed. Report what's missing.

Review Process

1. Extract Checklist

From each task file, extract every:

  • Spec scenario (WHEN/THEN)
  • Done When criterion
  • Explicit instruction in the Background or Goal sections

This is your checklist. Every item must be accounted for.

2. Check Compliance

For each checklist item, check whether the implementation addresses it.

Classify each item:

  • Addressed — the implementation covers this
  • Missed — no evidence this was addressed
  • Partially addressed — attempted but incomplete or incorrect

When you're unsure, read the actual code in the repository to verify before classifying. Do not mark something as missed without checking the code first.

3. Report

Present your findings:

## Task Compliance

### Addressed
- [Scenario/criterion] — [evidence]

### Gaps
- [Scenario/criterion] — [what's missing or incomplete]

Guardrails

  • Do not mark a scenario as missed without checking the code first. It may have been implemented without being narrated in the conversation.
  • Report only. Do not fix gaps — surface them for the human to decide how to proceed.

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.