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

E10 Rjf Drd

ASecurity

Use when compile or audit a Requirements Justification File against the ECSS-E-ST-10C Annex O Document Requirements Definition: validate each requirement's derivation basis, confirm a parent-derived requirement names its parent and that a top-level requirement rests on a standard or mission need instead, detect a rationale that merely restates the requirement it is meant to justify, confirm each rationale is attributed, and decide whether every requirement is justified. Trigger: ecss, e-st-10...

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 e10-rjf-drd --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of E10 Rjf Drd?

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

Security grade badge for E10 Rjf Drd
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ashfordeou-e10-rjf-drd/badge)](https://www.skillsdirectory.com/skills/ashfordeou-e10-rjf-drd)

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

Download with Pro
Files
SKILL.md
---
name: e10-rjf-drd
description: "Use when compile or audit a Requirements Justification File against the ECSS-E-ST-10C Annex O Document Requirements Definition: validate each requirement's derivation basis, confirm a parent-derived requirement names its parent and that a top-level requirement rests on a standard or mission need instead, detect a rationale that merely restates the requirement it is meant to justify, confirm each rationale is attributed, and decide whether every requirement is justified. Trigger: ecss, e-st-10-system-scope, requirements-justification-file, rjf, annex-o-drd, derivation-basis, requirement-rationale, attribution."
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-system-scope, requirements-justification-file, annex-o-drd, derivation-basis, requirement-rationale]
  version: 0.1.0
  author: Aero Agent Skills
---

# ECSS System Engineering — Requirements Justification File DRD (space-systems/ecss/e10-rjf-drd)

Use when the task is to compile or audit the Requirements Justification
File of ECSS-E-ST-10C Annex O -- the record of *why* each requirement
reads as it does, so that a later reviewer can re-derive the choice
rather than inherit it.

## Domain quick reference

- Every requirement carries three things: a derivation basis (a parent
  requirement, an analysis, an applicable standard, heritage, or a
  stated mission need), a rationale in its own words, and an attributed
  author.
- The basis and the requirement's level must agree. A requirement
  derived from a parent must name that parent. A top-level requirement
  cannot derive from one -- there is nothing above it -- so a
  parent-derived top-level row hides an unjustified requirement behind
  a trace that cannot exist.
- A top-level requirement rests on something external: an applicable
  standard or a stated mission need. Heritage is not enough at the
  apex, because "we did it this way before" explains a choice inside a
  design, not the existence of a system-level requirement.
- A parent recorded alongside a non-parent basis is fine -- an analysis
  that refined an inherited requirement legitimately has both -- so
  that combination is not a finding.
- The characteristic failure of this file is not a blank field: it is a
  rationale that restates the requirement. Every column is populated,
  nothing is explained, and a presence check passes it. A rationale
  identical to the requirement, or wholly contained in its wording,
  justifies nothing.
- Attribution matters because the file exists to be questioned later. A
  rationale nobody signed cannot be taken up with anyone.
- The file is complete only when no requirement carries a finding.

## Workflow

1. Confirm requirement identifiers are present and unique.
2. Validate each requirement's derivation basis against the recognized
   set.
3. Check the rationale: present, long enough to carry an argument, and
   not a restatement of the requirement itself. A missing rationale
   short-circuits the rest -- there is nothing to inspect.
4. Check the basis against the requirement's level: parent basis needs
   a named parent, a top-level requirement needs an external basis.
5. Confirm each rationale is attributed to an author.
6. Aggregate; a requirement is justified only when it carries no
   finding, and the file is complete only when all are.

## Pitfalls

- Grading the file on field completeness. A restating rationale fills
  every field and explains nothing, which is precisely how an RJF
  decays into a formality.
- Accepting a top-level requirement derived from a parent. The trace
  points at something that does not exist, and the requirement is
  effectively unjustified.
- Treating heritage as a sufficient basis at system level. It explains
  a design choice, not why the requirement is there at all.
- Flagging a requirement that records a parent alongside an analysis
  basis. Refining an inherited requirement legitimately has both, and
  flagging it trains reviewers to ignore findings.
- Reporting a missing rationale and a too-short rationale as two
  findings on the same row; absence is one defect, checked first.
- Leaving a rationale unattributed on the grounds that the team wrote
  it. The file's purpose is to let a later reviewer ask someone.

## Behavior contract (gate 3)

The basis validation, restatement detection, rationale, basis/level
agreement and attribution logic is exercised by the gate 3 contract
test: scripts/test_e10_rjf_drd.py against scripts/e10_rjf_drd_logic.py
(stdlib unittest, offline). Run:
python3 scripts/test_e10_rjf_drd.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 →