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

E2040 Device Phase Review Conduct

ASecurity

Evaluate the customer-led phase review of ECSS-E-ST-20-40C clause 5.1.4 against the evidence the development phase actually produced: confirm the review named is the one that closes that phase, check the board is chaired by the customer side, separate the mandatory data items delivered and mature from those still outstanding, fold every review observation onto a severity and a disposition, and let the open major observations and the missing mandatory items decide whether the phase closes, clo...

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 e2040-device-phase-review-conduct --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of E2040 Device Phase Review Conduct?

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

Security grade badge for E2040 Device Phase Review Conduct
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ashfordeou-e2040-device-phase-review-conduct/badge)](https://www.skillsdirectory.com/skills/ashfordeou-e2040-device-phase-review-conduct)

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

Download with Pro
Files
SKILL.md
---
name: e2040-device-phase-review-conduct
description: "Evaluate the customer-led phase review of ECSS-E-ST-20-40C clause 5.1.4 against the evidence the development phase actually produced: confirm the review named is the one that closes that phase, check the board is chaired by the customer side, separate the mandatory data items delivered and mature from those still outstanding, fold every review observation onto a severity and a disposition, and let the open major observations and the missing mandatory items decide whether the phase closes, closes with actions, or is repeated. Use when a phase review is prepared, chaired or dispositioned at the end of a device development phase. Trigger: ecss, e-st-20-40-device-scope, device-phase-review-conduct, phase-review-board-chair, review-observation-disposition, mandatory-data-item-readiness, phase-closure-verdict, review-action-closure."
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-20-40-device-scope, e2040-device-phase-review-conduct, device-phase-review-conduct, phase-review-board-chair, review-observation-disposition, mandatory-data-item-readiness, phase-closure-verdict, review-action-closure]
  version: 0.1.0
  author: Aero Agent Skills
---

# ECSS Device Requirements — Phase Review Conduct (space-systems/ecss/e2040-device-phase-review-conduct)

Use when the task is the review duty of ECSS-E-ST-20-40C clause 5.1.4 --
holding the customer-led review that closes a device development phase,
and deciding from the outputs actually on the table whether the phase is
finished, finished with actions, or has to be run again.

## Domain quick reference

- A phase review is named for the phase it closes, not for the date it
  happens on. A review identifier that belongs to a different phase is
  the cheapest defect to find and the most expensive to leave, because
  the entry criteria and the mandatory output list both follow the
  phase rather than the meeting.
- The review is customer-led. The board chair sits on the customer
  side; a supplier-chaired board is a design walkthrough, and calling
  it a phase review lets the supplier disposition observations raised
  against its own work.
- Outputs arrive with two independent properties: whether the item was
  delivered at all, and whether it is mature enough to be reviewed. A
  draft delivered on time is still not reviewable, so delivery and
  maturity are counted separately and a mandatory item that is either
  absent or immature blocks the phase.
- Observations carry a severity and a disposition, and the two do
  different jobs. Severity says how much the finding matters; the
  disposition says what the board did with it. An observation rejected
  without a rationale is an undocumented disposition, whatever its
  severity.
- Open observations of major severity are the hard gate. Minor
  observations and comments left open become actions and let the phase
  close with actions, which is a different verdict from closed and has
  to be reported as such.
- Readiness is a fraction of the mandatory output set, and a fraction
  that lands exactly on its threshold has met it. Comparing a computed
  division strictly against a declared threshold fails reviews that are
  precisely on target.

## Workflow

1. Fold the review identifier and the phase onto recognised names and
   report a review that does not close the phase it is being held for.
2. Resolve the board: a chair with a named side, and the participants.
   Refuse a board with no chair, and report a chair that is not on the
   customer side as a finding rather than an input error.
3. Resolve the mandatory and optional output list. Refuse a repeated
   item identifier, and record delivery and maturity separately for
   each item.
4. Report every mandatory item that is undelivered or immature, and
   compute the readiness fraction over the mandatory set only.
5. Fold every observation onto a severity and a disposition. Report an
   observation rejected with no rationale, and keep the open ones
   grouped by severity.
6. Compare the readiness fraction against the declared threshold,
   absorbing representation error, and never widen the threshold.
7. Decide the verdict: repeated if a major observation is open or a
   mandatory output is missing or immature, closed with actions if
   anything lesser is outstanding, closed otherwise.

## Pitfalls

- Treating delivery as readiness. An item can be handed over on the due
  date and still be a skeleton; the review needs the content, so the
  maturity flag is the one the verdict depends on.
- Letting the supplier chair the board. The review exists so that the
  customer accepts the phase outputs, and a supplier-chaired board
  quietly converts acceptance into self-certification.
- Rolling a major observation into the action list to protect the
  schedule. Actions are the mechanism for the lesser findings; a major
  one moved there closes a phase on an unresolved defect and the record
  shows a clean review.
- Counting optional outputs in the readiness fraction. The figure then
  improves by adding nice-to-have items and gets worse by dropping
  them, which is exactly backwards.
- Comparing readiness against its threshold with a strict inequality. A
  three-in-four division landing on a 0.75 threshold can sit a unit in
  the last place below it and repeat a phase that was ready.

## Behavior contract (gate 3)

The review-to-phase match, board chair check, output delivery and
maturity accounting, observation severity and disposition folding,
readiness comparison and closure verdict are exercised by the gate 3
contract test: scripts/test_e2040_device_phase_review_conduct.py
against scripts/e2040_device_phase_review_conduct_logic.py (stdlib
unittest, offline). Run:
python3 scripts/test_e2040_device_phase_review_conduct.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 →