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 Verification Report

ASecurity

Use when compile or audit the Verification Report against the ECSS-E-ST-10-02 clause 5.3.2.5 and Annex F Document Requirements Definition: confirm every verification event cites the underlying report holding its evidence, reconcile the executed methods against the methods the verification control document planned in both directions, detect an event whose claimed status contradicts the verdict of the report it cites, and roll the events up to a status for each requirement. Trigger: ecss, e-st-...

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 e1002-verification-report --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of E1002 Verification Report?

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

Security grade badge for E1002 Verification Report
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ashfordeou-e1002-verification-report/badge)](https://www.skillsdirectory.com/skills/ashfordeou-e1002-verification-report)

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

Download with Pro
Files
SKILL.md
---
name: e1002-verification-report
description: "Use when compile or audit the Verification Report against the ECSS-E-ST-10-02 clause 5.3.2.5 and Annex F Document Requirements Definition: confirm every verification event cites the underlying report holding its evidence, reconcile the executed methods against the methods the verification control document planned in both directions, detect an event whose claimed status contradicts the verdict of the report it cites, and roll the events up to a status for each requirement. Trigger: ecss, e-st-10-02c, verification-report, vrpt, annex-f-drd, method-agreement, evidence-linkage, status-rollup."
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, verification-report, vrpt, annex-f-drd, method-agreement, status-rollup]
  version: 0.1.0
  author: Aero Agent Skills
---

# ECSS Verification — Verification Report DRD (space-systems/ecss/e1002-verification-report)

Use when the task is to compile or audit the Verification Report (VRPT)
of ECSS-E-ST-10-02 clause 5.3.2.5 and Annex F -- the summary layer that
states, per requirement, what was done and where the evidence lives.

## Domain quick reference

- The VRPT is a roll-up, so its integrity is a question about agreement
  with its sources, not about its own internal tidiness. A summary that
  disagrees with the reports beneath it is worse than no summary: it
  carries authority the evidence does not support.
- The central check is status against source. An event claiming
  "passed" while the test report it cites failed is the defect that
  makes a summary dangerous, and no per-event view can see it.
- The check runs one way only. Claiming passed over a failed source is a
  contradiction; claiming failed over a failed source is consistent
  reporting and must not be flagged.
- Method agreement is checked in both directions against the
  verification control document. A planned method with no event was not
  carried out; an executed method nobody planned was not agreed. Both
  are findings, and each is reported against its method.
- Every event cites the report holding its evidence. An entry with
  nothing beneath it summarizes nothing, and the citation is what lets
  the source check run at all.
- An event citing a report absent from the source index is left to the
  evidence check rather than reported twice -- one missing link, one
  finding.
- Requirement status is severity ordered: any failed event fails it, any
  event not executed leaves it open, only an all-passed set verifies it.
- A requirement with no event at all raises rather than reporting
  verified by default. Nothing was done, and an empty roll-up must never
  read as success.

## Workflow

1. Confirm requirement entries are present and uniquely identified.
2. For each event, confirm a supporting report reference is cited.
3. Reconcile executed methods against planned methods in both
   directions.
4. For each event whose cited report is in the source index, confirm
   its claimed status does not overstate the source verdict.
5. Roll the events up to a requirement status under the severity
   ordering.
6. The VRPT is complete only when nothing is open or failed and the
   summary agrees with every source.

## Pitfalls

- Auditing the VRPT on its own. Every internal consistency check can
  pass while the summary contradicts the reports it stands on.
- Flagging an event that reports a failure over a failed source. It is
  doing exactly what it should, and flagging it teaches reviewers to
  ignore the check that matters.
- Comparing executed methods against planned only one way, so a method
  quietly added outside the plan never surfaces.
- Accepting a narrative citation ("see test campaign") in place of a
  report reference, which breaks the link the source check needs.
- Reporting a requirement with no verification event as verified
  because nothing failed. An empty set must raise, not pass.
- Double-reporting an event whose reference is both missing and
  unresolvable as two separate defects.

## Behavior contract (gate 3)

The evidence-linkage, two-way method agreement, status-versus-source
and severity-ordered roll-up logic is exercised by the gate 3 contract
test: scripts/test_e1002_verification_report.py against
scripts/e1002_verification_report_logic.py (stdlib unittest, offline).
Run:
python3 scripts/test_e1002_verification_report.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 →