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 Design General

ASecurity

Use when conduct and document a product's design against its allocated Technical Requirements Specification under ECSS-E-ST-10C clause 5.4.1.1: confirm every allocated requirement is covered by at least one design definition item, confirm every design item traces back to a known requirement, and confirm every design decision records the alternatives considered, the option selected and the rationale for selecting it, then decide whether the product's design is complete for the assessment. Trig...

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

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-design-general --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of E10 Design General?

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

Security grade badge for E10 Design General
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ashfordeou-e10-design-general/badge)](https://www.skillsdirectory.com/skills/ashfordeou-e10-design-general)

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

Download with Pro
Files
SKILL.md
---
name: e10-design-general
description: "Use when conduct and document a product's design against its allocated Technical Requirements Specification under ECSS-E-ST-10C clause 5.4.1.1: confirm every allocated requirement is covered by at least one design definition item, confirm every design item traces back to a known requirement, and confirm every design decision records the alternatives considered, the option selected and the rationale for selecting it, then decide whether the product's design is complete for the assessment. Trigger: ecss, e-st-10-system-scope, design-definition, design-decision, technical-requirements-specification, requirement-coverage, design-traceability, design-rationale."
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, design-definition, design-decision, requirement-coverage, design-traceability, design-rationale]
  version: 0.1.0
  author: Aero Agent Skills
---

# ECSS System Engineering — General Design Conduct (space-systems/ecss/e10-design-general)

Use when the task is to conduct a product's design so that it meets
its allocated Technical Requirements Specification under ECSS-E-ST-10C
clause 5.4.1.1, and to show that both the design definition and the
design decisions taken along the way are documented per product.

## Domain quick reference

- Coverage runs in two directions and each direction catches a
  different defect. Requirement-to-design coverage finds an allocated
  requirement that no design item implements. Design-to-requirement
  traceability finds a design item that implements nothing in the
  specification -- unrequested design work. Neither check substitutes
  for the other.
- A design item that references a requirement identifier outside the
  product's known set is a third, separate defect: not untraced, but
  traced to something that is not in this product's specification.
- A design decision is closed only when an alternative has been
  selected *and* a rationale is on record. A selection without a
  reason leaves the decision open, because the record exists to let a
  later reviewer re-derive the choice, not merely to name it.
- Every decision must carry at least one requirement identifier. A
  decision no requirement drove cannot be re-assessed when the
  specification changes, so it is flagged as untraceable independently
  of whether it is closed.
- Even a decision with one viable option records that option as its
  sole alternative -- the record is the evidence that the option space
  was examined, and an empty alternative list is an input error.
- Assessment is per product. Programme-wide requirement, design item
  and decision lists are filtered to the product under review before
  any check runs, so a requirement covered on a sibling product does
  not count as covered here.
- The design is complete only when all three finding categories are
  empty; strength in one never offsets a gap in another.

## Workflow

1. Filter the programme requirement, design item and design decision
   lists down to the product under assessment.
2. For each allocated requirement, confirm at least one design item
   references it; record an uncovered requirement otherwise.
3. For each design item, confirm it references at least one
   requirement, and that every identifier it references is in the
   product's known requirement set.
4. For each design decision, confirm it names the alternatives
   considered, records the selected alternative and its rationale, and
   traces to at least one requirement.
5. Aggregate the uncovered-requirement, unallocated-design-item and
   decision findings; the design is complete only when all are empty.

## Pitfalls

- Checking requirement coverage alone and calling the design
  traceable. That leaves design work no requirement asked for entirely
  invisible, which is the growth path for unqualified scope.
- Accepting a design item whose requirement reference is a typo. The
  item looks traced; only cross-checking each identifier against the
  product's known requirement set reveals it points nowhere.
- Closing a design decision on the strength of a selected alternative
  with no rationale recorded. The choice cannot be re-derived at the
  next review, so the decision is still open.
- Recording a decision with no alternatives because only one option
  was ever viable. The sole option is itself the alternative list, and
  its absence removes the evidence that the space was examined.
- Assessing against the programme-wide requirement list instead of the
  product's allocation, which reports requirements belonging to other
  products as uncovered and hides the ones that matter.

## Behavior contract (gate 3)

The decision-status, decision-violation, requirement-coverage,
design-item traceability and per-product aggregation logic is exercised
by the gate 3 contract test: scripts/test_e10_design_general.py against
scripts/e10_design_general_logic.py (stdlib unittest, offline). Run:
python3 scripts/test_e10_design_general.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 →