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

Q7001 Cleanliness Margin Management

ASecurity

Manage the cleanliness margin a programme still holds against its allocated contamination budgets under ECSS-Q-ST-70-01C. Use when molecular and particulate allocations have to be tracked phase by phase from cleanroom build through test, storage, launch and orbit, or when a review asks how much of the end-of-life budget is already spent: check the apportionment against the top-level budget and the reserve held back, compute the margin and margin fraction each phase still carries, derive a con...

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 q7001-cleanliness-margin-management --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Q7001 Cleanliness Margin Management?

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

Security grade badge for Q7001 Cleanliness Margin Management
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ashfordeou-q7001-cleanliness-margin-management/badge)](https://www.skillsdirectory.com/skills/ashfordeou-q7001-cleanliness-margin-management)

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

Download with Pro
Files
SKILL.md
---
name: q7001-cleanliness-margin-management
description: "Manage the cleanliness margin a programme still holds against its allocated contamination budgets under ECSS-Q-ST-70-01C. Use when molecular and particulate allocations have to be tracked phase by phase from cleanroom build through test, storage, launch and orbit, or when a review asks how much of the end-of-life budget is already spent: check the apportionment against the top-level budget and the reserve held back, compute the margin and margin fraction each phase still carries, derive a consumption rate from the phases already complete, forecast the end-of-programme figure, and name the phase that eroded the margin. Trigger: ecss, q-st-70-01c-cleanliness-scope, contamination-budget-apportionment, cleanliness-margin-tracking, molecular-contamination-allocation, particulate-obscuration-allocation, contamination-budget-reserve, end-of-programme-contamination-forecast."
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-70-01c-cleanliness-scope, q7001-cleanliness-margin-management, contamination-budget-apportionment, cleanliness-margin-tracking, molecular-contamination-allocation, particulate-obscuration-allocation, contamination-budget-reserve, end-of-programme-contamination-forecast]
  version: 0.1.0
  author: Aero Agent Skills
---

# ECSS Cleanliness — Margin Management Against the Contamination Budget (space-systems/ecss/q7001-cleanliness-margin-management)

Use when the task is the cleanliness data duty of ECSS-Q-ST-70-01C —
holding a contamination budget open across the whole programme, phase
by phase, and saying at any moment how much of it is left.

## Domain quick reference

- A cleanliness budget is an end-of-life figure, not a delivery figure.
  The number that matters is what sits on the surface when the mission
  needs it clean, so every phase between cleaning and that moment
  spends part of the same allowance.
- Two budgets run in parallel and never convert into one another.
  Molecular deposition is an areal mass, quoted in milligrams per
  square metre; particulate fallout is an obscuration, quoted as
  percentage area coverage. A programme comfortable on one can be out
  of budget on the other.
- Apportionment comes before tracking. The top-level budget is split
  into phase allocations with a reserve held at programme level, and
  the split is only valid while the allocations plus the reserve fit
  inside the budget. An over-subscribed apportionment is already
  non-compliant before any hardware is built.
- Margin is per phase and per programme at once. A phase inside its own
  allocation can still leave the programme short if an earlier phase
  overran, so both are reported and the programme figure governs.
- A consumption rate is only meaningful over completed phases. Dividing
  everything spent so far by every phase in the plan flatters the
  forecast, because the phases not yet started have spent nothing.
- The reserve is not margin. It is held against phases nobody has
  costed yet, so a programme reporting margin by counting the reserve
  is reporting the same allowance twice.
- The useful output is not a number but a name: the phase whose
  overrun, if it were recovered, would put the programme back inside
  its budget.

## Workflow

1. Take the contaminant kind, the top-level budget, the reserve
   fraction and the phase apportionment, and reject a case that cannot
   name them rather than defaulting them.
2. Check the apportionment: every allocation non-negative, the sum of
   allocations plus the reserve no greater than the budget, and report
   an over-subscription as a finding rather than scaling it away.
3. Compute each phase margin as its allocation less what it consumed,
   with a margin fraction against the allocation, and categorize the
   phase as healthy, thin or overrun.
4. Roll the phases up: total consumed, programme margin against the
   budget less the reserve, and the programme margin fraction.
5. Derive the consumption rate over the completed phases only, and
   forecast the end-of-programme total by carrying the remaining
   allocations at their allocated value.
6. Name the worst phase by absolute overrun, and state the recovery
   that would return the programme to compliance.
7. Report the verdict on the programme figure, never on the phase
   figures alone.

## Pitfalls

- Reporting margin against the full budget while a reserve is held.
  The reserve is committed to unknowns, so subtracting it is what turns
  an allowance into a margin.
- Mixing the molecular and the particulate ledger. They have different
  units and different limits, and a rollup that adds them produces a
  figure with no physical meaning and no owner.
- Extrapolating a consumption rate across phases that have not started.
  The rate is a property of what has actually been spent, and spreading
  it over the whole plan hides an overrun until it is unrecoverable.
- Treating a phase inside its own allocation as a programme pass. The
  programme figure is the sum, and a compliant phase downstream of an
  overrun does not undo it.
- Comparing a margin fraction against a threshold by bare arithmetic. A
  phase that lands exactly on its allocation produces a fraction that
  can miss zero by a few units in the last place, so the comparison
  absorbs that representation error rather than reporting a phantom
  overrun.

## Behavior contract (gate 3)

The apportionment check, per-phase margin, programme rollup,
consumption rate, end-of-programme forecast, worst-phase naming and
the compliance verdict are exercised by the gate 3 contract test:
scripts/test_q7001_cleanliness_margin_management.py against
scripts/q7001_cleanliness_margin_management_logic.py (stdlib unittest,
offline). Run:
python3 scripts/test_q7001_cleanliness_margin_management.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 →