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

E1002 Method Rod

ASecurity

Use when verify a requirement's compliance under the review-of-design method of ECSS-E-ST-10-02C clause 5.2.2.4: classify each design-evidence item (drawing, analysis report, design description, supplier certificate, heritage data, similarity data) as direct or heritage evidence, apply the admissibility rule for a safety-critical requirement backed only by heritage evidence, roll up each item's compliant, non_compliant, open, or not_applicable disposition into an overall requirement status, a...

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

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 e1002-method-rod --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of E1002 Method Rod?

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

Security grade badge for E1002 Method Rod
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ashfordeou-e1002-method-rod/badge)](https://www.skillsdirectory.com/skills/ashfordeou-e1002-method-rod)

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

Download with Pro
Files
SKILL.md
---
name: e1002-method-rod
description: "Use when verify a requirement's compliance under the review-of-design method of ECSS-E-ST-10-02C clause 5.2.2.4: classify each design-evidence item (drawing, analysis report, design description, supplier certificate, heritage data, similarity data) as direct or heritage evidence, apply the admissibility rule for a safety-critical requirement backed only by heritage evidence, roll up each item's compliant, non_compliant, open, or not_applicable disposition into an overall requirement status, and assemble a review-of-design report entry per requirement while flagging any requirement absent from the report. Trigger: ecss, e-st-10-02c, review of design, rod, design evidence, heritage data, similarity data, verification report, requirement close-out."
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, e-st-10-02c, review-of-design, verification-method, design-evidence, heritage-data, verification-report]
  version: 0.1.0
  author: Aero Agent Skills
---

# ECSS Review-of-Design Verification Method (space-systems/ecss/e1002-method-rod)

Use when the task is closing out a requirement by the review-of-design
method of ECSS-E-ST-10-02C clause 5.2.2.4 -- examining already-existing
design documentation against the requirement, rather than generating
new test or measurement data for this verification action.

## Domain quick reference

- Clause 5.2.2.4 describes review of design as a documented
  examination of existing design data -- drawings, analysis reports,
  design descriptions, supplier certificates, or heritage/similarity
  records from a qualified prior design -- against the requirement
  text, closed out by a review-of-design report. It does not itself
  generate new test or measurement data; that is what distinguishes it
  from the test and analysis methods.
- Evidence items split into two families: direct evidence (drawing,
  analysis report, design description, supplier certificate) speaks to
  the current design itself, while heritage evidence (heritage data,
  similarity data) draws on the qualification history of a prior
  design or a documented similarity assessment. An evidence item
  outside both families is rejected before it enters the review.
- A safety-critical requirement backed only by heritage evidence (no
  direct evidence item at all) is not admissible for review-of-design
  close-out unless a similarity assessment has been explicitly
  approved to extend that heritage to the safety-critical case; this
  mirrors the sibling e10-req-verif-methods rule that safety-critical
  requirements should not be closed by review of design alone.
- Each evidence item carries a disposition -- compliant, non_compliant,
  open (still under review), or not_applicable -- and the requirement's
  overall status rolls up from the full evidence set: any non_compliant
  item fails the requirement outright; failing that, any open item
  keeps the requirement open; failing that, at least one compliant item
  closes it compliant; a set containing only not_applicable items
  closes nothing and is itself a finding (no evidence actually
  demonstrated compliance).

## Workflow

1. For each requirement assigned the review-of-design method, gather
   its evidence items and classify each one as direct or heritage
   evidence; reject an evidence item of an unrecognized type before it
   enters the review.
2. Check the evidence set's admissibility: a safety-critical
   requirement with heritage evidence only, and no approved similarity
   assessment extending it, is flagged rather than closed.
3. Record a disposition (compliant, non_compliant, open, not_applicable)
   for every evidence item, then roll the set up into one overall
   requirement status by the non_compliant > open > compliant >
   no_compliant_evidence precedence.
4. Assemble the review-of-design report: one entry per requirement,
   carrying its evidence set, admissibility issues, rolled-up status,
   and the reviewer of record; a report entry without a reviewer of
   record is rejected.
5. Confirm every requirement assigned the review-of-design method has a
   report entry; flag any requirement id missing from the report
   rather than treating silence as compliance.
6. Only treat a requirement as closed when its rolled-up status is
   compliant and it carries no outstanding admissibility issue; carry
   every other case forward to engineering disposition.

## Pitfalls

- Accepting a heritage-only evidence set for a safety-critical
  requirement without an approved similarity assessment -- heritage
  data from a different design does not automatically transfer to a
  safety-critical claim.
- Reading "no non_compliant item" as closed -- an open item still means
  the review is incomplete, and a set of only not_applicable items
  never demonstrated compliance in the first place.
- Treating a compliant rolled-up status as sufficient to close the
  requirement while an admissibility issue is still outstanding on the
  same entry.
- Leaving a requirement out of the review-of-design report and
  interpreting its absence as a pass; clause 5.2.2.4 closes a
  requirement through a documented report entry, not through silence.

## Behavior contract (gate 3)

The evidence-classification, admissibility, status-rollup, and
report-completeness logic is exercised by the gate 3 contract test:
scripts/test_e1002_method_rod.py against
scripts/e1002_method_rod_logic.py (stdlib unittest, offline). Run:
python3 scripts/test_e1002_method_rod.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 →