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

Q7021 Manned Areas Interface

ASecurity

Assess whether a material may be installed in a crewed compartment from its ECSS-Q-ST-70-21C flammability entry, applying the result to the habitable-volume material control of ECSS-Q-ST-70C. Use when a recorded rating must become a usage decision and the cabin atmosphere is not the atmosphere the specimen saw. Compares tested oxygen partial pressure against the cabin, treats a milder test as no evidence, checks installed thickness against the tested band, weighs exposed area and mass, and re...

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 q7021-manned-areas-interface --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Q7021 Manned Areas Interface?

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

Security grade badge for Q7021 Manned Areas Interface
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ashfordeou-q7021-manned-areas-interface/badge)](https://www.skillsdirectory.com/skills/ashfordeou-q7021-manned-areas-interface)

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

Download with Pro
Files
SKILL.md
---
name: q7021-manned-areas-interface
description: "Assess whether a material may be installed in a crewed compartment from its ECSS-Q-ST-70-21C flammability entry, applying the result to the habitable-volume material control of ECSS-Q-ST-70C. Use when a recorded rating must become a usage decision and the cabin atmosphere is not the atmosphere the specimen saw. Compares tested oxygen partial pressure against the cabin, treats a milder test as no evidence, checks installed thickness against the tested band, weighs exposed area and mass, and returns accepted, accepted-with-containment, needs-assessment or rejected. Trigger: ecss, q-st-70-21, crewed-compartment-material-control, habitable-volume-flammability, flammability-use-atmosphere-coverage, flammability-exposed-area-limit, flammability-containment-mitigation."
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-70-21-flammability-scope, q7021-manned-areas-interface, crewed-compartment-material-control, habitable-volume-flammability, flammability-use-atmosphere-coverage, flammability-exposed-area-limit, flammability-containment-mitigation]
  version: 0.1.0
  author: Aero Agent Skills
---

# ECSS Flammability — Crewed Compartment Interface (space-systems/ecss/q7021-manned-areas-interface)

Use when the task is the interface step that hands an ECSS-Q-ST-70-21C
flammability result to the material control of a habitable compartment
under ECSS-Q-ST-70C — turning a recorded rating into an installation
decision for a named location, and rolling those decisions up.

## Domain quick reference

- An entry is evidence only inside the atmosphere it was obtained in.
  The compartment's oxygen partial pressure is what the tested partial
  pressure has to bound. Thirty percent oxygen at 70 kPa is milder than
  sea-level air, so a result that looks enriched can still be no
  evidence at all for a normal cabin.
- An entry is evidence only for the configuration tested. An installed
  thickness outside the tested band is a different configuration and
  the entry does not speak for it; that is an assessment, not a pass.
- A propagating material is not automatically excluded from a crewed
  compartment. It is excluded from open installation. Sealed
  non-combustible containment keeps it away from cabin air; a quantity
  small enough that there is nothing to propagate through still needs a
  written assessment rather than a silent pass.
- A vented metal housing is not a seal. It stops dripping material
  reaching what is below; it does not stop a flame front reaching cabin
  air, and treating the two as one mitigation is the common error.
- A material that self-extinguishes but drips burning material is safe
  above nothing and unsafe above something ignitable. The geometry of
  the installation, not the rating alone, decides.
- A compartment is more than its worst item. Exposed area of everything
  only acceptable with containment, or still under assessment, is
  summed against a budget, because ten small exceptions make one large
  one and nobody reviews the tenth.

## Workflow

1. Validate the entry: a recorded rating from the known set, a tested
   oxygen partial pressure, a tested thickness.
2. Validate the usage: location, cabin oxygen fraction and total
   pressure, installed thickness, exposed area, mass, whether anything
   ignitable sits below, and the containment form.
3. Compute the compartment's oxygen partial pressure and compare it
   with the tested value; a milder test is a reason, not a pass.
4. Compare installed thickness with the tested band inside its
   tolerance.
5. With either check failed, the usage needs assessment and no rating
   shortcut applies.
6. Otherwise apply the rating: propagating goes to containment, to the
   quantity limit with an assessment, or to rejection; a drip
   restriction goes to the geometry below the item; a clean rating is
   accepted.
7. Sum exposed area across contained and unresolved items and compare
   it with the compartment budget.
8. Report every location with its disposition and reasons, the
   governing disposition, the exception area and the findings.

## Pitfalls

- Comparing oxygen percentages instead of partial pressures. It passes
  a reduced-pressure enriched test as evidence for sea-level air.
- Reading a pass at one thickness as a pass at every thickness. The
  tested band is part of the evidence.
- Treating a vented housing as a seal for a propagating material.
- Exempting a small propagating item silently. Small is a reason to
  assess, not a reason to skip the record.
- Judging the compartment by its worst item alone and never summing
  what was let through with a mitigation.
- Accepting a dripping material because it self-extinguished, without
  looking at what is mounted underneath it.

## Behavior contract (gate 3)

Entry and usage validation, partial-pressure comparison, configuration
coverage, the quantity exemption, containment handling, the four
dispositions, the severity roll-up and the compartment exception budget
are exercised by the gate 3 contract test:
scripts/test_q7021_manned_areas_interface.py against
scripts/q7021_manned_areas_interface_logic.py (stdlib unittest,
offline). Run:
python3 scripts/test_q7021_manned_areas_interface.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 →