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

Q7022 Re Test Procedure

ASecurity

Prepare the re-test a stored material owes before its shelf life is extended under ECSS-Q-ST-70-22, and grade what comes back: take the property set from the material family, take the specimen count from the lot size, derive each acceptance threshold from the as-manufactured value and a declared retention fraction in the direction that property may drift, compare with a relative tolerance so a result on the limit passes everywhere, and keep a failed re-test distinct from an incomplete one. Us...

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

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 q7022-re-test-procedure --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Q7022 Re Test Procedure?

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

Security grade badge for Q7022 Re Test Procedure
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ashfordeou-q7022-re-test-procedure/badge)](https://www.skillsdirectory.com/skills/ashfordeou-q7022-re-test-procedure)

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

Download with Pro
Files
SKILL.md
---
name: q7022-re-test-procedure
description: "Prepare the re-test a stored material owes before its shelf life is extended under ECSS-Q-ST-70-22, and grade what comes back: take the property set from the material family, take the specimen count from the lot size, derive each acceptance threshold from the as-manufactured value and a declared retention fraction in the direction that property may drift, compare with a relative tolerance so a result on the limit passes everywhere, and keep a failed re-test distinct from an incomplete one. Use when an extension request needs test evidence. Trigger: ecss, q-st-70-22, shelf-life-re-test-plan, re-test-acceptance-threshold, re-test-property-retention, re-test-specimen-count, re-test-incomplete-versus-failed."
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-70-22-limited-shelf-life-materials, q-st-70-22, q7022-re-test-procedure, shelf-life-re-test-plan, re-test-acceptance-threshold, re-test-property-retention, re-test-specimen-count, re-test-incomplete-versus-failed]
  version: 0.1.0
  author: Aero Agent Skills
---

# ECSS Limited Shelf Life — Re-Test Procedure and Acceptance (space-systems/ecss/q7022-re-test-procedure)

Use when the task is the re-test that carries a shelf-life extension under
ECSS-Q-ST-70-22: which properties to test, on how many specimens, against what
acceptance, and what the results entitle the lot to.

## Domain quick reference

- The property set comes from the material family, not from convenience. A
  paste adhesive is re-tested on the properties that move in storage —
  viscosity, gel time and a bonded strength — because those are the ones whose
  drift predicts a bad joint. Testing whatever the lab has a fixture for proves
  nothing about the mechanism that degrades.
- Every property has a direction. A strength may only fall so far, a viscosity
  or a volatile content may only rise so far, and a banded property such as gel
  time or resin content is out of family in either direction. One two-sided
  rule applied to all of them passes material that has thickened past use.
- The acceptance threshold is derived from the value recorded at manufacture
  for that lot, scaled by a declared retention fraction. It is not a fresh
  specification limit, because the question is drift in storage, not whether
  the material was ever any good.
- A result meant to sit exactly on the limit will not: the threshold is a
  product of a declared fraction and a recorded value, and it lands either side
  of the intended number depending on the platform. The comparison carries a
  relative tolerance so the same data gives the same verdict everywhere.
- A failed re-test and an incomplete one are different outcomes. A property
  tested and out of acceptance is evidence about the material; a property
  nobody tested, or tested on too few specimens, is a gap in the evidence. Only
  the first justifies scrapping the lot.

## Workflow

1. Take the required properties from the family and refuse an unknown family
   rather than falling back to a generic set.
2. Take the specimens owed per property from the lot size bracket.
3. For each property, derive the acceptance bounds from the as-manufactured
   value and the retention fraction, in that property's own direction.
4. Grade each reported specimen against its bounds with the relative tolerance;
   a single specimen outside acceptance fails that property.
5. Flag a property reported on fewer specimens than the plan requires, and do
   not read it as a pass.
6. Split the outcome into failed properties, missing properties, under-sampled
   properties and results reported outside the plan.
7. Close with failed, then incomplete, then passed, and report the extension
   period the re-test can carry — zero for anything but a pass.

## Pitfalls

- Applying one symmetric band to every property. A viscosity that has halved
  and a viscosity that has doubled are not the same finding.
- Grading against the original specification rather than the lot's recorded
  as-manufactured value. That measures the supplier, not the storage.
- Accepting a property because its mean is inside acceptance. The specimen
  outside it is the one that will be in the joint.
- Reading an under-sampled property as a pass because nothing failed. Too few
  specimens is missing evidence, and it belongs with the incomplete outcome.
- Comparing a result with a bare inequality against a computed threshold. A
  value intended to sit on the limit lands either side of it, and the same
  dataset then passes on one machine and fails on another.
- Reporting extension days off an incomplete re-test. Until the evidence is
  complete the supported period is zero, not the requested number.

## Behavior contract (gate 3)

The family property set, lot-size specimen brackets, direction-aware threshold
derivation, tolerance-carrying comparison, under-sampling detection and the
failed / incomplete / passed precedence are exercised by the gate 3 contract
test: scripts/test_q7022_re_test_procedure.py against
scripts/q7022_re_test_procedure_logic.py (stdlib unittest, offline). Run:
python3 scripts/test_q7022_re_test_procedure.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 →