agentleFS
Sign inStart free
ThinkFlowLabThinkFlowLab/agentdescent/.claude/skills/fix-issue/SKILL.md

fix-issue

Skill203 starsChanged 6 days agoMITView on GitHub

Fix one AgentDescent issue end to end - claim, fresh clone, a test that fails on main, gates, PR, self-review at the tip, merge by tier, cleanup.

  • Reads credentials

53 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use prepare-release, document and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • ShopifySkill

    prepare-release

    Prepare the changeset-release/main branch for release by syncing version.ts files and running pnpm install

    Also in 4 projects that use this

  • nicolasestremSkill

    document

    Create focused documentation for specific components or features

    Also in 4 projects that use this

  • GitHubSkill

    refactor

    Surgical code refactoring to improve maintainability without changing behavior. Covers extracting functions, renaming variables, breaking down god functions, improving type safety, eliminating code smells, and applying design patterns. Less drastic than repo-rebuilder; use for gradual improvements.

    Also in 5 projects that use this

  • SentrySkill

    write-tests

    Write tests following project conventions. Use when adding new tests or modifying existing ones.

    Also in 3 projects that use this

  • AWSSkill

    ship

    Finalize dev work on an issue branch — update docs, push, and open a PR.

    Also in 6 projects that use this

  • Microsoft AzureSkill

    build

    Build the TypeSpec Rust emitter from source. Run this after cloning the repo, after pulling changes, or when TypeScript source files have been modified.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 1 is distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 51 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

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

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

    Read AGENTS.md, CODE_STANDARDS.md and LESSONS.md from origin/main.

    line 15
  2. Distinctive:

    Write the test first and run it on the unchanged main: it must fail.

    line 29
  3. Very specific:

    Wait for the required checks (build, test (3.9)..test (3.13)) to be green at the tip, then review with review-pr in a fresh session and …

    line 56
  4. Very specific:

    T2/T3: add awaiting-approval and stop.

    line 64
  5. Very specific:

    Never --admin, never the ruleset bypass.

    line 65
  6. Very specific:

    Remove the run directory. Do not delete remote branches by hand (merged branches are deleted automatically).

    line 69

“Common” is measured: kept by at least 6 in 10 of the 51 edited versions of this file we could read. “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

AgentDescent fix-issue

One agent-ready issue, one fresh clone, one branch, one PR. This skill grants no merge authority beyond AGENTS.md › Merge policy.

0. Before anything

  • AGENT_PAUSE is not true (gh variable list -R ThinkFlowLab/agentdescent).
  • The issue is agent-ready, not hold, and nobody else is assigned.
  • Read AGENTS.md, CODE_STANDARDS.md and LESSONS.md from origin/main.
  • Claim: assign Birfy, add agent-working, comment with the branch name.

1. Fresh clone

RUN=<run-root>/$(date +%Y%m%d-%H%M%S)-<issue>
git clone https://github.com/ThinkFlowLab/agentdescent "$RUN/repo" && cd "$RUN/repo"
git checkout -b agent/<issue>-<slug> origin/main
python3 -m venv "$RUN/venv" && "$RUN/venv/bin/pip" install -e ".[dev,mcp]"

2. Red, then green

  1. Write the test first and run it on the unchanged main: it must fail.
  2. Fix the class (every host, every adapter, both evolve() and async_evolve() when the loop is involved), not the sample.
  3. Public API changed → python -m tools.gen_api_docs. User-visible change → changelog.d/<issue>-<slug>.md.

3. Gates at the tip you will link

pytest -q
python -m tools.gen_api_docs --check
python -m tools.changelog_fragments check
mkdocs build --strict          # docs changes only

Real-model (Ark) checks only with ARK_API_KEY already in the environment; never write the key anywhere.

4. PR

  • Push the branch (never main, never --force), open the PR with the template: imperative title, Fixes #N, short body, Tip SHA: / Ran: / Not run:. Assign Birfy; labels agent-pr + type + area.
  • Tier: python3 .github/scripts/risk_gate.py --pr <n>.

5. Review at the tip

Wait for the required checks (build, test (3.9)..test (3.13)) to be green at the tip, then review with review-pr in a fresh session and post the report. A finding → fix, push, and review the new tip from scratch (a new commit voids the PASS).

6. Merge by tier

  • T0/T1: gh pr merge <n> -R ThinkFlowLab/agentdescent --auto --squash --match-head-commit <sha>.
  • T2/T3: add awaiting-approval and stop; Danyang clicks merge.
  • Never --admin, never the ruleset bypass.

7. Cleanup

Remove the run directory. Do not delete remote branches by hand (merged branches are deleted automatically). File follow-ups as issues, not TODOs. Stopping without a PR: unassign, remove agent-working, comment why.

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