Skip to content
Back to skills

Qc Checklist

ASecurity

Turn a process description into an operational quality-control checklist — binary pass/fail checks, acceptance criteria, critical-vs-routine tiers, and failure modes with catch-points. Use when the user says "build a QC checklist", "standardize how we review X", "acceptance criteria for this process", or describes quality varying by who does the work.

  • 381 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added August 30, 2026
ai-agentsgoshellgit

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned August 30, 2026

npx -y skills add sgharlow/claude-code-recipes --skill qc-checklist --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Qc Checklist?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Qc Checklist
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/sgharlow-qc-checklist/badge)](https://www.skillsdirectory.com/skills/sgharlow-qc-checklist)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: qc-checklist
description: Turn a process description into an operational quality-control checklist — binary pass/fail checks, acceptance criteria, critical-vs-routine tiers, and failure modes with catch-points. Use when the user says "build a QC checklist", "standardize how we review X", "acceptance criteria for this process", or describes quality varying by who does the work.
---

# Quality Control Checklist

Convert "experienced people just know" into checks anyone can run. A good check is binary
(pass/fail), observable (no judgment calls hidden inside), and placed at the point where the
failure it catches actually happens.

## Steps

1. Get the process: what's produced, the steps, who performs it, and — most important —
   what has actually gone wrong before. Real past failures anchor the checklist; ask for
   2–3 if none are offered.
2. Draft the failure-mode inventory first: for each step, what can go wrong, how it would be
   detected, and the cost of missing it. Every checklist item must trace to a failure mode —
   a check that catches nothing is process theater.
3. Build the checklist in two tiers:
   - **Critical (stop-the-line):** failures that are costly or invisible downstream. These
     are never skippable and each states its acceptance criterion measurably.
   - **Routine:** consistency checks that tolerate an occasional miss.
   Phrase every item as a verifiable pass/fail question with the evidence to look at —
   "Invoice total matches PO total (compare field X to field Y)", not "check invoice".
4. Add the operating shell: when the checklist runs (per unit / per batch / per release),
   who signs off, where results are recorded, and the escalation when a critical check
   fails. A checklist without a recorded result is a suggestion.
5. Verify by dry-run: walk one recent real work product through the draft. Every past
   failure the user named must be caught by some item; items that catch nothing on the
   dry-run get justified or cut. Then hand over with a 90-day review note — checklists
   drift as processes change.

## Constraints

- No item without a named failure mode it exists to catch.
- Acceptance criteria are measurable ("≤ 2 business days", "all 4 fields populated") — no
  "appropriate", "sufficient", or "high quality".
- Keep it runnable: if the full list exceeds ~15 items per tier, split by role or stage
  rather than shipping a wall nobody completes under time pressure.

Full walkthrough, examples, and variations: `recipes/Recipe-048-Quality-Control-Checklists-Standards.md`.
For enforcing checks on AI-assisted code specifically, the same philosophy is implemented in
[ai-control-framework](https://github.com/sgharlow/ai-control-framework).

Files in this skill

  • SKILL.md2.7 KB
  • evals/failure-mode-tracing.md973 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.