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

Q1009 Capa

ASecurity

Define the corrective and preventive actions a nonconformance owes under ECSS-Q-ST-10-09C clause 5.3. Use when a proposed action set has to be judged against the root causes it claims to remove, when containment is being offered as the fix, or when a recurring or systemic cause needs prevention as well as correction: rank the control each action installs, check that every cause carries a corrective action stronger than added inspection, demand prevention wherever the mechanism reaches further...

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

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 q1009-capa --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Q1009 Capa?

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

Security grade badge for Q1009 Capa
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ashfordeou-q1009-capa/badge)](https://www.skillsdirectory.com/skills/ashfordeou-q1009-capa)

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

Download with Pro
Files
SKILL.md
---
name: q1009-capa
description: "Define the corrective and preventive actions a nonconformance owes under ECSS-Q-ST-10-09C clause 5.3. Use when a proposed action set has to be judged against the root causes it claims to remove, when containment is being offered as the fix, or when a recurring or systemic cause needs prevention as well as correction: rank the control each action installs, check that every cause carries a corrective action stronger than added inspection, demand prevention wherever the mechanism reaches further hardware, and record the rationale behind each choice. Trigger: ecss, q-st-10-09c, corrective-action-selection, preventive-action-selection, root-cause-coverage, recurrence-prevention, containment-versus-correction, capa-rationale-record."
license: Apache-2.0
compliance: STANDARDS-REF
standards:
  - id: ecss
    reference-only: true
gated: false
domain: space-systems
pack: space-systems
compatibility: "agentskills.io SKILL.md; any SKILL.md host (Claude Code, Hermes, OpenClaw)"
metadata:
  domain: space-systems
  subdomain: ecss
  tags: [ecss, q-st-10-09c-nonconformance-scope, q1009-capa, corrective-action-selection, preventive-action-selection, root-cause-coverage, recurrence-prevention, containment-versus-correction, capa-rationale-record]
  version: 0.1.0
  author: Aero Agent Skills
---

# ECSS Nonconformance Control — Corrective and Preventive Action (space-systems/ecss/q1009-capa)

Use when the task is the action-definition step of ECSS-Q-ST-10-09C
clause 5.3 — deciding which actions a nonconformance actually earns,
whether they reach its root causes, and whether recurrence has been
stopped rather than merely detected next time.

## Domain quick reference

- Three kinds of action follow a nonconformance and only two of them
  are what the clause asks for. Containment stops the escape now:
  segregate, impound, screen the built stock. Corrective action removes
  a cause that has already produced a nonconformance. Preventive action
  removes a cause before it produces one, wherever the same mechanism
  can reach.
- Containment is not correction. An action set made only of containment
  holds the escape and leaves every cause in place, so it closes
  nothing.
- An action is worth the control it installs. Eliminating the
  possibility outranks a substitution, which outranks an engineering
  control, which outranks a written procedure or a training session,
  which outranks an added inspection. Added inspection detects the
  defect again; it has not removed the cause, so it never closes one on
  its own.
- Some causes reach further than the item in hand. A design, process,
  procedure, training or supplier cause is systemic by nature, and a
  cause that has now occurred more than once has demonstrated it, so
  both owe a preventive action as well as a corrective one.
- Every cause needs evidence behind it. A cause asserted from opinion
  gives the action set nothing to be effective against, and the
  effectiveness check downstream has nothing to measure.
- The rationale is part of the record. An action chosen without a
  stated reason cannot be re-argued when it fails to hold, and the next
  occurrence starts the same investigation from nothing.

## Workflow

1. Take the root causes with their categories, occurrence counts and
   supporting evidence; reject an empty or duplicated cause set rather
   than proceeding against an unknown target.
2. Mark the causes that owe prevention: every systemic category, plus
   any cause whose occurrence count has reached the recurrence
   threshold the programme declares.
3. Validate each proposed action — identifier, type, the control it
   installs, the cause it addresses and its rationale. A corrective or
   preventive action pointing at a cause outside the set is an input
   error, not a weak action.
4. Map corrective actions onto causes and keep the strongest control
   per cause. Name any cause with no corrective action at all, and any
   cause whose only cover is added detection.
5. Compare the preventive actions against the causes that owe one and
   report the gaps by cause, not as a single count.
6. Report the weakest corrective control in the set: it is the action
   most likely to be the one that fails the effectiveness check later.
7. Close with an adequacy verdict and the named gaps, so the
   implementation step downstream tracks actions that are worth
   tracking.

## Pitfalls

- Recording a screening campaign as the corrective action. Screening is
  containment; it finds the units already affected and changes nothing
  about why they were affected.
- Adding an inspection step and calling the cause closed. The
  inspection detects the same defect on the next unit, so the cause is
  still producing nonconformances and the only change is that the
  programme pays to find them.
- Writing one action against several causes and counting it once per
  cause. Coverage is per cause, and an action that removes one
  mechanism does not remove the others because it was listed against
  them.
- Answering a second occurrence with the same one-off correction. A
  repeat is evidence that the cause is systemic, and what it owes is a
  preventive action across the family, not a second repair.
- Assigning training as the standing answer to a workmanship cause.
  Training is a weak control by rank; where a fixture, a tool change or
  a design change can remove the possibility, the stronger control is
  the one the clause is asking for.
- Leaving the rationale out because the action is obvious. Obvious
  actions are exactly the ones that get reversed quietly later, with
  nothing in the record to say what they were for.

## Behavior contract (gate 3)

The cause validation, recurrence marking, action validation, coverage
mapping, preventive-gap detection and adequacy verdict are exercised by
the gate 3 contract test: scripts/test_q1009_capa.py against
scripts/q1009_capa_logic.py (stdlib unittest, offline).
Run: python3 scripts/test_q1009_capa.py

## Compliance

- ECSS standards are freely downloadable (ESA); cite the source and
  paraphrase 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 →