agentleFS
Sign inStart free
BlakeemBlakeem/aipromptguide-workflows/skills/debug/SKILL.md

debug

Skill1 starsChanged 8 days agoMITView on GitHub

Run the AIPG debug workflow, which reviews a repo or change for production defects and then fixes the triaged issue files with develop's fix mode. Use only when the user explicitly asks for the AIPG debug workflow.

192 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-discord, add-slack 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.
  • MicrosoftSkill

    add-discord

    Add Discord bot channel integration via Chat SDK.

    Also in 11 projects that use this

  • MicrosoftSkill

    add-slack

    Add Slack channel integration via Chat SDK.

    Also in 11 projects that use this

  • +10 more from microsoft

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 175 edited versions we read keep these.

  • 1

    Distinctive

    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. Very specific:

    Read ${CLAUDE_PLUGIN_ROOT}/workflows/audit/CLAUDE.md and follow it exactly, through its scope section and its defects kind section.

    line 20
  2. Distinctive:

    Use these paths wherever the guide says "this checkout" or "the tool's own directory":

    line 23

“Common” is measured: kept by at least 6 in 10 of the 175 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

The user wants to run the debug dynamic workflow (review, then fix) on the task below. It is the audit workflow's defects kind.

First, before any step of the guide, run the setup check node "${CLAUDE_PLUGIN_ROOT}/tools/onboard.mjs" check --root "${CLAUDE_PLUGIN_DATA}" --repo <target.repo>, where <target.repo> is the repo the run works on. When the task does not name that repo, ask the user for it, since the working directory may be another repo. On ready, go on. On ask, ask the questions it prints in one AskUserQuestion call and run the save command it prints with the answers. The save prints ready once nothing is missing. When either command exits 1, show the user its message, which names the cause, and run it again once the cause is fixed. The Workflow tool launches only engines the session can read, which is what the access question settles. When the user declines it, the user runs the /add-dir command that question names for this session, and you pass --access session to the save and to each later check in this session. A user who declines both gets no run, since the Workflow tool cannot read the engine.

Read ${CLAUDE_PLUGIN_ROOT}/workflows/audit/CLAUDE.md and follow it exactly, through its scope section and its defects kind section. Work the checklist's defects lists top to bottom. Use these paths wherever the guide says "this checkout" or "the tool's own directory":

  • Review engine scriptPath: ${CLAUDE_PLUGIN_ROOT}/workflows/audit/audit.mjs, launched with kind: defects
  • Fix engine scriptPath (develop in fix mode, guide ${CLAUDE_PLUGIN_ROOT}/workflows/develop/CLAUDE.md): ${CLAUDE_PLUGIN_ROOT}/workflows/develop/develop-cycle.mjs
  • develop's blockTool arg: the args tool below prints it, so the spread args carry it, and develop throws without it. Never pass it by hand.
  • Args, status and triage tool (operator-side): ${CLAUDE_PLUGIN_ROOT}/tools/plan-edit.mjs
  • Onboarding tool (operator-side): ${CLAUDE_PLUGIN_ROOT}/tools/onboard.mjs
  • Project-settings tool (operator-side): ${CLAUDE_PLUGIN_ROOT}/tools/project-settings.mjs
  • Worktree tool (operator-side): ${CLAUDE_PLUGIN_ROOT}/tools/wt.mjs
  • Unit slicer (plain Node, run directly): ${CLAUDE_PLUGIN_ROOT}/workflows/audit/gen-units.mjs
  • root arg: ${CLAUDE_PLUGIN_DATA}. Runs land in its runs/<runId>/. Never the plugin install dir, which is version-swapped on update.

$ARGUMENTS

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