agentleFS
Sign inStart free
attilaszaszattilaszasz/sdd-pilot/.claude/skills/sddp-implement-qc-loop/SKILL.md

sddp-implement-qc-loop

Skill98 starsChanged 26 days agoMITView on GitHub

Run implement and QC in a continuous loop.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    When either sub-skill says Delegate, use the Task tool to invoke the corresponding sub-agent:

    line 19

≈ “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

Command category: orchestration Prerequisites: spec, plan, tasks

You are starting an Implement + QC loop workflow. Your sole purpose is to repeatedly implement tasks and run quality control until QC passes or the safety limit is reached. Disregard any prior specification or planning discussion from this conversation. Focus exclusively on the implement → QC cycle.

Load and follow the workflow in .github/sddp/workflows/implement-qc-loop/WORKFLOW.md.

The loop skill will instruct you to load and execute two sub-skills inline:

  • Implement → .github/sddp/workflows/implement-tasks/WORKFLOW.md
  • QC → .github/sddp/workflows/quality-control/WORKFLOW.md

When either sub-skill says Delegate, use the Task tool to invoke the corresponding sub-agent:

  • Delegate: Context Gatherer → delegate to sddp-context-gatherer
  • Delegate: Task Tracker → delegate to sddp-task-tracker
  • Delegate: Developer → delegate to sddp-developer
  • Delegate: Checklist Reader → delegate to sddp-checklist-reader
  • Delegate: Test Evaluator → delegate to sddp-test-evaluator
  • Delegate: Technical Researcher → delegate to sddp-technical-researcher
  • Delegate: QC Auditor → delegate to sddp-qc-auditor
  • Delegate: Story Verifier → delegate to sddp-story-verifier
  • Delegate: Tasks Validator → delegate to sddp-tasks-validator
  • Delegate: Spec Validator → delegate to sddp-spec-validator
  • Delegate: Plan Validator → delegate to sddp-plan-validator
  • Delegate: Policy Auditor → delegate to sddp-policy-auditor
  • Delegate: ADR Author → delegate to sddp-adr-author

Report progress to the user at each iteration boundary — summarize what was fixed and what remains.

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