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 Definition Phase Review

ASecurity

Evaluate whether the definition phase may close and architecture work start, the gate ECSS-E-ST-20-40C clause 5.2.7 places there: check each data item the phase owes against the maturity this gate demands rather than against mere presence, stop on an open major review discrepancy, and accept a discrepancy with an action only when that action falls due before the work it is meant to protect begins. Use when a definition-phase review package is assembled or chaired, or when a gate decision is r...

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

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-definition-phase-review --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of E2040 Device Definition Phase Review?

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

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

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

Download with Pro
Files
SKILL.md
---
name: e2040-device-definition-phase-review
description: "Evaluate whether the definition phase may close and architecture work start, the gate ECSS-E-ST-20-40C clause 5.2.7 places there: check each data item the phase owes against the maturity this gate demands rather than against mere presence, stop on an open major review discrepancy, and accept a discrepancy with an action only when that action falls due before the work it is meant to protect begins. Use when a definition-phase review package is assembled or chaired, or when a gate decision is reconstructed afterwards. Trigger: ecss, e-st-20-electrical-scope, device-definition-phase-review, definition-gate-data-item-maturity, review-discrepancy-disposition, action-due-before-architecture-start, definition-gate-verdict."
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-electrical-scope, e2040-device-definition-phase-review, device-definition-phase-review, definition-gate-data-item-maturity, review-discrepancy-disposition, action-due-before-architecture-start, definition-gate-verdict]
  version: 0.1.0
  author: Aero Agent Skills
---

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

Use when the task is the gate duty of ECSS-E-ST-20-40C clause 5.2.7 --
deciding whether the definition phase is closed and architecture work on
the device may begin, from the package submitted and the discrepancies
raised against it.

## Domain quick reference

- The gate has a fixed package: the requirements specification, the
  development plan, the pre-tailoring matrix, the preliminary
  verification plan and the feasibility and risk assessment. A data item
  the phase owes and did not submit is a gate stopper, not a gap to note.
- Maturity is per item, not one bar across the package. The requirements
  specification and the tailoring matrix have to be baselined because
  the architecture is about to be built against them; a plan may still
  sit at for-review. A package counted by presence passes with drafts
  inside it.
- A data item with no revision cannot be identified later. The gate
  reviewed something; a year on nobody can say what.
- Discrepancy severity decides the disposition that is allowed. An open
  major discrepancy stops the gate. An open minor or editorial one is
  carried as an action.
- A discrepancy accepted with an action is a conditional pass only while
  the action falls due BEFORE the work it constrains starts. An action
  due after architecture work has begun protects nothing it was raised
  to protect, and an action with no due date is not an action.
- A major discrepancy simply rejected needs a recorded rationale. The
  disposition alone records a decision with no reasoning behind it.
- Closure ratios are counts over counts, so a threshold met exactly is
  met and the comparison absorbs representation error.

## Workflow

1. Fold the package onto the data items the phase owes, refusing a
   repeat or an unknown key as an input defect, and report every item
   the package does not carry.
2. Compare each submitted item against the maturity THIS gate requires
   for that item, and report an item with no revision separately.
3. Fold every discrepancy onto a severity and a disposition, refusing a
   repeated identifier.
4. Stop the gate on an open major discrepancy; carry an open minor or
   editorial one as an action.
5. For each discrepancy accepted with an action, require a due date and
   require it to fall before architecture work starts.
6. Report a rejected major discrepancy as needing a rationale.
7. Compute the closure ratio, compare it against any declared threshold
   absorbing representation error, and return the verdict: not-closed on
   any blocking finding, closed-with-actions when something is carried,
   closed otherwise.

## Pitfalls

- Counting the package by presence. Five items are on the table and two
  of them are drafts; the gate passes and the architecture is built
  against a requirements specification that is still moving.
- Applying one maturity bar to every item. It either blocks plans that
  are legitimately at for-review or lets the specification through as a
  draft, and both are wrong in the same review.
- Accepting an action with no due date, or with one after the phase it
  was meant to protect. The discrepancy is recorded as dispositioned and
  reappears, unchanged, at the next gate.
- Treating an open minor discrepancy as a stopper. It converts a
  conditional pass into a schedule hit for an editorial point.
- Comparing a closure ratio against its threshold with a strict
  inequality. A two-of-two division landing on 1.0 can sit a unit in the
  last place below it and red a gate that closed everything.

## Behavior contract (gate 3)

The package folding, per-item maturity comparison, revision check,
discrepancy folding, disposition rules, action due-date placement
against the architecture start and the closure-threshold comparison are
exercised by the gate 3 contract test:
scripts/test_e2040_device_definition_phase_review.py against
scripts/e2040_device_definition_phase_review_logic.py (stdlib unittest,
offline). Run:
python3 scripts/test_e2040_device_definition_phase_review.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 →