agentleFS
jamesblackwelljamesblackwell/falcondeck/.agents/skills/verified-bug-campaign/SKILL.md

verified-bug-campaign

Skill7 starsChanged 8 days agoMITView on GitHub

Run an explicitly requested long-running campaign to find and fix verified bugs across client and backend code, with regression evidence and Autoreview on every commit. Not for one-off debugging.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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:

    Use only when the user explicitly asks to start or continue a broad bug-fixing campaign.

    line 8
  2. Distinctive:

    Read AGENTS.md, repository documentation, manifests, tests, and existing working-tree changes.

    line 13
  3. Distinctive:

    Use the requested target, defaulting to 100, and create a durable goal with this skill's verification rules and stopping conditions.

    line 16
  4. Distinctive:

    Run broader tests after each subsystem and before completion.

    line 26
  5. Distinctive:

    Follow repository commit conventions.

    line 32
  6. Distinctive:

    Stop when the target is reached, every mapped area is exhausted, the user pauses the goal, or missing access or product intent prevents …

    line 37

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Verified Bug Campaign

Use only when the user explicitly asks to start or continue a broad bug-fixing campaign. Explaining or editing the campaign does not authorize starting it.

Campaign

  1. Read AGENTS.md, repository documentation, manifests, tests, and existing working-tree changes.
  2. Read references/verification.md.
  3. Use the requested target, defaulting to 100, and create a durable goal with this skill's verification rules and stopping conditions.
  4. Inventory every executable client, backend service, worker, integration, and shared runtime package. Track each as NOT STARTED, IN PROGRESS, EXHAUSTED, or BLOCKED.
  5. Work systematically through the inventory, completing one verified defect at a time: reproduce, fix the root cause, add regression proof, run relevant checks, commit, then run the installed autoreview skill against that commit.
  6. Independently verify and address accepted review findings. Count the bug only after its final proof, tests, commit, and Autoreview pass.
  7. Run broader tests after each subsystem and before completion.

Maintain this ledger in goal progress, not the repository:

ID | Area | Trigger | Pre-fix proof | Post-fix proof | Commit | Autoreview

Follow repository commit conventions. Preserve unrelated changes. Do not create branches or pull requests unless requested.

Stop

Stop when the target is reached, every mapped area is exhausted, the user pauses the goal, or missing access or product intent prevents further verification.

The target is an aim. Never manufacture weak findings to reach it.

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.