agentleFS
Sign inStart free
theDRElabstheDRElabs/opencode-config/skills/project-feedback/SKILL.md

project-feedback

Skill1 starsChanged 3 months agoMITView on GitHub

Define and run a project's deterministic format, lint, typecheck, test, build, migration, E2E, startup, and test-data checks. Use when implementing an issue, preparing a pre-merge result, or recording unavailable verification.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use HARNESS-PROJECT-FEEDBACK.md as the global contract and project-local instructions as the command source of truth.

    line 8
  2. Distinctive:

    Run fast checks for the changed surface.

    line 18
  3. Distinctive:

    Run the full pre-merge sequence for the complete change.

    line 20
  4. Very specific:

    Stop completion on any FAIL, including typecheck, tests, lint, and build.

    line 22

≈ “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

Project Feedback

Use HARNESS-PROJECT-FEEDBACK.md as the global contract and project-local instructions as the command source of truth.

Workflow

  1. Discover the repository's package manager, lockfile, project instructions, scripts, migration tooling, Playwright configuration, startup command, and deterministic test-data setup.
  2. Classify each check as applicable or unavailable before running it. Never invent a command. An unknown command is UNAVAILABLE, not PASS.
  3. Run fast checks for the changed surface. Add affected migrations, build, E2E, startup, or test-data checks when the issue requires them.
  4. Run the full pre-merge sequence for the complete change.
  5. Capture complete command output, exit codes, and artifact locations.
  6. Stop completion on any FAIL, including typecheck, tests, lint, and build. Record BLOCKED or UNAVAILABLE with owner and residual risk.

Pipeline Selection

  • Eligible heavy web projects use pipeline-init and the reusable GitHub CI/Playwright/Vercel pipeline.
  • Tiny or local-only projects do not receive deployment infrastructure.
  • Android/Gradle projects use only their repo-local Java 17/Gradle workflow; never run pipeline-init.

Result Shape

Return one row per applicable check containing name, command, cwd, exit_code, result, and evidence. For unavailable checks also include reason, substitute, owner, and residual_risk. A terse green summary is not sufficient when full logs exist.

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