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

Q80 Compliance Matrix

ASecurity

Build a clause-by-clause compliance matrix against ECSS-Q-ST-80C Rev.2 as a draft for human sign-off: join the clause list to an evidence index of document, section, status and justification, set each clause to compliant, partially compliant, not compliant or not applicable, pre-fill clauses tailored out for the software category, raise gaps such as missing evidence, compliance claimed without a reference and not-applicable claims that contradict the tailoring, summarise coverage, and render ...

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

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 q80-compliance-matrix --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Q80 Compliance Matrix?

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

Security grade badge for Q80 Compliance Matrix
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ashfordeou-q80-compliance-matrix/badge)](https://www.skillsdirectory.com/skills/ashfordeou-q80-compliance-matrix)

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

Download with Pro
Files
SKILL.md
---
name: q80-compliance-matrix
description: "Build a clause-by-clause compliance matrix against ECSS-Q-ST-80C Rev.2 as a draft for human sign-off: join the clause list to an evidence index of document, section, status and justification, set each clause to compliant, partially compliant, not compliant or not applicable, pre-fill clauses tailored out for the software category, raise gaps such as missing evidence, compliance claimed without a reference and not-applicable claims that contradict the tailoring, summarise coverage, and render Markdown or CSV ending at the stop line. Use when a supplier answers the Q-80 compliance matrix or a customer audits one. Trigger: q80-compliance-matrix, software-product-assurance-compliance, clause-by-clause-compliance, evidence-index, compliance-gap-list, statement-of-compliance."
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)"
clauses:
  - standard: ECSS-Q-ST-80C Rev.2
    clause: 5.2.1.5
    items: [a, b]
    relation: implements
metadata:
  domain: space-systems
  subdomain: ecss
  tags: [ecss, q-st-80c, q80-compliance-matrix, software-product-assurance-compliance, clause-by-clause-compliance, evidence-index, compliance-gap-list, statement-of-compliance]
  version: 0.1.0
  author: Aero Agent Skills
---

# ECSS-Q-ST-80C Compliance Matrix (space-systems/ecss/q80-compliance-matrix)

Use when a software product assurance (PA) manager has to answer
ECSS-Q-ST-80C Rev.2 (30 April 2025) clause by clause: the compliance matrix
that closes the Software Product Assurance Plan (SPAP) and that customers
ask for at the system requirements review, or an audit of one received from
a supplier. The skill turns a clause list and an evidence index into the
matrix, a coverage summary and the gap list, and stops at a human sign-off.

## Domain quick reference

- Four statuses and no others: compliant, partially compliant, not
  compliant, not applicable. Every status other than compliant needs a
  justification; every status other than not applicable needs an evidence
  reference down to the section of the document.
- A clause with no evidence is open, not compliant by default. Silence is
  never compliance.
- Compliance claimed without a document reference is downgraded to
  partial and raised as a gap: a claim nobody can check is not evidence.
- Not applicable has two sources. The category tailoring removes some
  requirements outright, and those rows are pre-filled with that reason.
  A not-applicable claim on a clause the tailoring keeps is a deviation
  and needs the customer's agreement, so it is raised as a gap.
- Several evidence rows on one clause combine to the weakest status. One
  audit finding outweighs a compliant claim in the plan.
- Evidence mapped to a clause that is not in the list usually means a
  clause was mistyped or the list is from another revision; it is
  reported, not dropped.
- Coverage is two numbers: the compliant fraction of the applicable
  clauses, and the fraction with an evidence reference. A high first
  number with a low second one is a matrix of promises.

## Workflow

1. Take the clause list: the customer's, or the full requirement list of
   the standard for the software category. The matrix covers every
   assurance requirement that applies to the project or the contract, one
   row each, and is delivered together with the software product
   assurance plan (as its last section or beside it).
2. Load the evidence index (CSV or rows) and normalise the status
   vocabulary; refuse anything outside the four statuses.
3. Build the matrix with `build_matrix` and the category, so tailored-out
   rows pre-fill and contradictions surface. Every row other than not
   applicable must point at the document, down to the section, where that
   requirement's expected output is found; a row with no such reference is
   a gap. Where the requirement is to follow a document requirements
   definition, one general statement of compliance with it is enough.
4. Read the coverage summary and the gap list; resolve what can be
   resolved from existing documents, and list the rest as open.
5. Render the matrix with the draft banner and the stop line.
6. Hand it to the responsible human. Only that person records the sign-off,
   and approving over open gaps has to be an explicit choice.

## Obligations

| Item | Step |
|---|---|
| ECSS-Q-ST-80C Rev.2 5.2.1.5a | 1 |
| ECSS-Q-ST-80C Rev.2 5.2.1.5b | 3 |

## Pitfalls

- Marking a clause compliant because the plan promises it. A promise is
  evidence for the plan clause, not for the activity clause.
- Pointing at a document without a section. The reviewer then re-does the
  mapping, and usually finds it missing.
- Using not applicable as a softer not compliant.
- Answering against the wrong revision. Rev.2 renumbered and deleted
  requirements; clauses from an older list show up as unknown or orphan
  evidence here.
- Letting the matrix leave the building as a statement of compliance
  before a named person has signed it.

## Stop gate: human sign-off required

The agent drafts; it does not decide. Stop and hand the draft to a named
human before any of these leave the working folder:

- The compliance matrix, in any format, sent to a customer or supplier.
- Any not-applicable claim that departs from the category tailoring.
- Any statement of compliance built on the matrix.

The matrix is always produced with status DRAFT. Mark every such output as
a draft, list the open gaps for the reviewer, and end with the line: STOP:
human sign-off required before submission.

## Behavior contract (gate 3)

The clause id and status normalisation, the tailored status per category
with security-driven clauses, the CSV evidence parsing with loose headers,
the row rules (no evidence, missing reference, weakest status wins,
not-applicable conflicts), orphan evidence, the coverage summary, the
Markdown and CSV rendering with the draft marker and stop line, and the
sign-off that refuses an unnamed signatory and silent approval over open
gaps are exercised by the gate 3 contract test:
scripts/test_q80_compliance_matrix.py against
scripts/q80_compliance_matrix_logic.py (stdlib unittest, offline). Run:
python3 scripts/test_q80_compliance_matrix.py

## Compliance

- ECSS standards are freely downloadable (ESA); cite ECSS-Q-ST-80C Rev.2
  (30 April 2025) as 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 →