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

Q2007 Tf Config

ASecurity

Verify that a test facility is under configuration control as ECSS-Q-ST-20-07 clause 5.6.2 asks, and say what the state of the baseline obliges the test centre to do. Use when a campaign is about to run in a facility whose hardware, software, fluid lines and fixed instrumentation have moved since the last baseline: refuse a facility never baselined, check that every configuration item carries an identification, replay the approved and applied change records from the baseline version forward, ...

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 q2007-tf-config --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Q2007 Tf Config?

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

Security grade badge for Q2007 Tf Config
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ashfordeou-q2007-tf-config/badge)](https://www.skillsdirectory.com/skills/ashfordeou-q2007-tf-config)

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

Download with Pro
Files
SKILL.md
---
name: q2007-tf-config
description: "Verify that a test facility is under configuration control as ECSS-Q-ST-20-07 clause 5.6.2 asks, and say what the state of the baseline obliges the test centre to do. Use when a campaign is about to run in a facility whose hardware, software, fluid lines and fixed instrumentation have moved since the last baseline: refuse a facility never baselined, check that every configuration item carries an identification, replay the approved and applied change records from the baseline version forward, and report any item whose as-run configuration that chain does not reach. Trigger: ecss, q-st-20-07-test-facility-clause-5-6-2, test-facility-configuration-baseline, test-facility-as-run-configuration-drift, test-facility-unapproved-change-applied, test-facility-configuration-item-identification."
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-20-07-test-centre-scope, q2007-tf-config, q-st-20-07-test-facility-clause-5-6-2, test-facility-configuration-baseline, test-facility-as-run-configuration-drift, test-facility-unapproved-change-applied, test-facility-configuration-item-identification, test-facility-change-chain-replay]
  version: 0.1.0
  author: Aero Agent Skills
---

# ECSS Test Centres — Test Facility Configuration Control (space-systems/ecss/q2007-tf-config)

Use when the task is clause 5.6.2 of ECSS-Q-ST-20-07: a test facility is
about to carry a campaign, its configuration has to be identified and
its changes controlled, and the question is whether the facility
standing in the hall today is the one the baseline describes.

## Domain quick reference

- A facility is a configuration, not a room. Chambers, shakers, fluid
  lines, fixed instrumentation, control software and the fixtures that
  hold the article are each configuration items, and a facility with no
  item list has nothing for a change to be controlled against.
- Identification is what makes an item controllable. An item on the list
  with no identification cannot be pointed at by a change record, so
  identification coverage is measured across the whole baseline rather
  than assumed from the presence of a list.
- A change is a move between two versions, not an event. A record that
  does not advance the version it names says nothing about what the
  facility became, and is an input error rather than a finding.
- Approved and applied are two different flags and both matter. A change
  approved and not yet applied is work in front of the campaign; a
  change applied and not approved is the control failure the clause
  exists to catch, and it outranks everything downstream of it.
- The as-run configuration is the evidence. Replaying the approved and
  applied changes from the baseline version gives the configuration the
  records say the facility should be in; an item the chain does not
  reach is drift, whichever direction it drifted in.
- A chain that breaks part way is not a smaller chain. An approved and
  applied change whose from-version no other record produces means the
  records are inconsistent, and reading only the changes that happen to
  link up would hide exactly that.

## Workflow

1. Validate the configuration policy first: the identification coverage
   the facility owes and how many changes may sit pending approval while
   a campaign runs. A coverage outside zero to one is refused.
2. Refuse a facility with no baseline; that closes the assessment on the
   facility not being baselined rather than on any later finding.
3. Validate the baseline items: a label and a whole version each, no
   item twice. Carry the identification string, blank or not, because
   the blank ones are the coverage measurement.
4. Validate the change records: a change identifier, the item it names,
   a from-version strictly below its to-version, and both flags as real
   booleans. Refuse the same change identifier twice.
5. Separate the applied-and-not-approved records; if any exist, close
   there, naming them.
6. Replay the approved and applied changes per item from the baseline
   version, refusing a chain whose remaining records do not link.
7. Compare the replayed version with the as-run record item by item.
   Refuse an as-run item the baseline never declared; collect the rest
   as drift.
8. Close on one verdict in order: not baselined, unapproved change
   applied, configuration drift, identification incomplete, changes
   pending approval, or configuration under control.

## Pitfalls

- Reading a change log as a configuration. The log says what was
  proposed; only the replay from the baseline says what the facility
  should now be, and only the as-run record says what it is.
- Treating an unapplied approved change as drift. It is planned work,
  and folding it into the expected version makes a controlled facility
  look uncontrolled while hiding the records that are genuinely wrong.
- Skipping a change whose from-version does not link. That silently
  repairs an inconsistent record set; the break is the finding.
- Measuring identification on the items that have it. Coverage is over
  the whole baseline, so the unidentified items have to stay in the
  denominator.
- Letting a drift finding outrank an unapproved applied change. The
  drift is a symptom; the uncontrolled change is the clause failure, and
  reporting the symptom first sends the correction to the wrong place.

## Behavior contract (gate 3)

The policy validation, baseline validation, identification coverage, the
change-record validation, the unapproved-applied separation, the change
chain replay and its break refusal, the as-run drift comparison and the
verdict ordering are exercised by the gate 3 contract test:
scripts/test_q2007_tf_config.py against
scripts/q2007_tf_config_logic.py (stdlib unittest, offline). Run:
python3 scripts/test_q2007_tf_config.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 →