agentleFS
Sign inStart free
lxyerlxyer/multi-agent-collaboration-system/.agents/skills/improve-ut/SKILL.md

improve-ut

Skill1 starsChanged 7 months agoMITView on GitHub

Analyzes changed files and improves unit test coverage using project-specific testing conventions from .trellis/spec/ unit-test specs. Determines test scope (unit vs integration vs regression), adds or updates tests following existing patterns, and runs validation. Use when code changes need test coverage, after implementing a feature, after fixing a bug, or when test gaps are identified.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill to improve test coverage after code changes.

    line 8
  2. Very specific:

    Look for packages with unit-test spec layer in the output.

    line 25
  3. Distinctive:

    Add/update tests using existing project test patterns

    line 38

≈ “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

Improve Unit Tests (UT)

Use this skill to improve test coverage after code changes.

Usage

$improve-ut

Source of Truth

Discover and read unit-test specs dynamically:

# Discover available packages and their spec layers
python3 ./.trellis/scripts/get_context.py --mode packages

Look for packages with unit-test spec layer in the output. For each discovered unit-test/ directory, read all relevant spec files inside it (for example index.md, conventions.md, integration-patterns.md, mock-strategies.md).

If this skill conflicts with the unit-test specs, the specs win.

Execution Flow

  1. Inspect changed files:
    • git diff --name-only
  2. Decide test scope using unit-test specs:
    • unit vs integration vs regression
    • mock vs real filesystem flow
  3. Add/update tests using existing project test patterns
  4. Run validation:
pnpm lint
pnpm typecheck
pnpm test
  1. Summarize decisions, updates, and remaining test gaps.

Output Format

## UT Coverage Plan
- Changed areas: ...
- Test scope (unit/integration/regression): ...

## Test Updates
- Added: ...
- Updated: ...

## Validation
- pnpm lint: pass/fail
- pnpm typecheck: pass/fail
- pnpm test: pass/fail

## Gaps / Follow-ups
- <none or explicit rationale>

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.

Check your setup, free