Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Corrective Action

ASecurity

Use when you must drive a corrective action (CAPA) record for a manufacturing nonconformance to closure: run the eight-discipline (8D) problem-solving workflow, check that a containment action is recorded, validate the five-whys root cause chain, and confirm the corrective action and the effectiveness evidence before the record closes. Produces the closure stage verdict, the missing items, and the effectiveness pass or fail that gate the nonconformance closure. Trigger: corrective action, cap...

2 stars
0 votes
0 copies
0 views
Added 9/27/2026
ai-agentspython

Works with

claude code

Security Analysis

A100/100

Scanned 9/27/2026

Install to Claude Code

$npx -y skills add ashfordeOU/aero-agent-skills --skill corrective-action --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Corrective Action?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Corrective Action
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ashfordeou-corrective-action/badge)](https://www.skillsdirectory.com/skills/ashfordeou-corrective-action)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: corrective-action
description: "Use when you must drive a corrective action (CAPA) record for a manufacturing nonconformance to closure: run the eight-discipline (8D) problem-solving workflow, check that a containment action is recorded, validate the five-whys root cause chain, and confirm the corrective action and the effectiveness evidence before the record closes. Produces the closure stage verdict, the missing items, and the effectiveness pass or fail that gate the nonconformance closure. Trigger: corrective action, capa record, 8d report, five whys, root cause analysis, containment action, effectiveness verification, problem solving."
license: Apache-2.0
compliance: STANDARDS-REF
standards:
  - id: as9100
    reference-only: true
gated: false
domain: manufacturing-quality
pack: manufacturing-quality
compatibility: "agentskills.io SKILL.md; any SKILL.md host (Claude Code, Hermes, OpenClaw)"
metadata:
  domain: manufacturing-quality
  subdomain: as9100
  tags: [corrective-action, capa-record, 8d-report, five-whys, root-cause-analysis, containment-action, effectiveness-verification, preventive-action, problem-solving]
  version: 0.1.0
  author: Aero Agent Skills
---

# Corrective Action (manufacturing-quality/as9100/corrective-action)

Use when the task is closing a corrective action record for a
manufacturing nonconformance: containment, five-whys root cause
analysis, corrective action, and effectiveness evidence must all be
in place before the record closes per AS9100 practice.

## Domain quick reference

- The closure state machine walks four stages in order: containment,
  root-cause, corrective-action, effectiveness.
- Containment is the immediate action that isolates the effect of a
  nonconformance; a placeholder answer (none, n/a, unknown) does not
  count as a recorded containment.
- The five-whys root cause chain needs at least 3 recorded levels,
  each non-empty and distinct from the previous answer; a repeated
  adjacent answer is circular and fails the chain.
- Corrective action removes the root cause; preventive action
  prevents recurrence. A blank or placeholder corrective action
  cannot close the record.
- Effectiveness evidence must describe an observed result and must
  not restate the root cause text, which would be circular evidence.
- record_status returns one of: containment-missing,
  root-cause-incomplete, corrective-action-missing,
  effectiveness-pending, closed. closure_verdict adds the missing
  items for the current stage.
- AS9100 frames corrective action as the required response that
  closes a nonconformance; the stage machine here is a practical
  summary, not clause text.

## Workflow

1. Record the problem statement as the record problem.
2. Record the containment action and check it with
   containment_ok (no placeholders).
3. Build the five-whys chain and validate it with
   root_cause_chain_ok (depth, empty answers, circularity).
4. Record the corrective action and the preventive action; check
   the corrective action with corrective_action_ok.
5. Record effectiveness evidence and check it with
   effectiveness_evidence_ok against the root cause statement.
6. Call record_status for the stage and closure_verdict for the
   missing items; close only at status closed.

## Pitfalls

- Placeholder answers: none, n/a, na, no, unknown, and not-applicable
  fail containment_ok, corrective_action_ok, and the whys chain.
- Circular why chains: the same answer twice in a row means the
  analysis stopped; the chain needs a new level each time.
- Circular effectiveness evidence: evidence that repeats the root
  cause statement proves nothing and keeps the record pending.
- Closing without effectiveness: a record with containment, whys,
  and corrective action but no evidence stays effectiveness-pending.
- Containment versus corrective action: containment isolates the
  effect, corrective action removes the cause; one does not replace
  the other.
- Missing keys: record_status raises ValueError when problem,
  containment, whys, or corrective_action is absent.

## Behavior contract (gate 3)

The closure stage logic is exercised by the gate 3 contract test:
scripts/test_corrective_action.py against
scripts/corrective_action_logic.py (stdlib unittest, offline). Run:
python3 scripts/test_corrective_action.py

## Compliance

- Standards referenced, not reproduced: AS9100 corrective action is
  summarized as a stage machine and workflow, common aerospace
  problem-solving practice per standards-map.yaml.
- compliance: STANDARDS-REF, gated: false.

Attribution

ashfordeOUashfordeOU
View sourceMore from ashfordeOU →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

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 (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

694821 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →