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

E1006 Wording

ASecurity

Use when verify requirement wording against ECSS-E-ST-10C §8.3 rules: confirm each statement uses shall (mandatory), should (recommendation), or may (permission); detect non-standard verbal forms (will, must); flag ambiguous or unverifiable terms (adequate, appropriate, user-friendly); enforce single obligation per statement; and reject embedded rationale text. Replace forbidden terms with measurable criteria and move justification to a NOTE. Trigger: ecss, e-st-10-system-scope, wording, verb...

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

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 e1006-wording --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of E1006 Wording?

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

Security grade badge for E1006 Wording
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ashfordeou-e1006-wording/badge)](https://www.skillsdirectory.com/skills/ashfordeou-e1006-wording)

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

Download with Pro
Files
SKILL.md
---
name: e1006-wording
description: "Use when verify requirement wording against ECSS-E-ST-10C §8.3 rules: confirm each statement uses shall (mandatory), should (recommendation), or may (permission); detect non-standard verbal forms (will, must); flag ambiguous or unverifiable terms (adequate, appropriate, user-friendly); enforce single obligation per statement; and reject embedded rationale text. Replace forbidden terms with measurable criteria and move justification to a NOTE. Trigger: ecss, e-st-10-system-scope, wording, verbal-form, shall, requirements-authoring, ambiguity, single-statement, verifiability."
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, wording, verbal-form, shall, requirements-authoring, ambiguity, single-statement, verifiability]
  version: 0.1.0
  author: Aero Agent Skills
---

# ECSS Requirements Authoring — Wording Rules (space-systems/ecss/e1006-wording)

Use when the task is to verify or correct the wording of system
requirements per ECSS-E-ST-10C §8.3 — selecting the right verbal form,
removing ambiguous terms, splitting compound obligations, and relocating
embedded rationale.

## Domain quick reference

- §8.3 prescribes three verbal forms: **shall** for every mandatory
  requirement, **should** for a recommendation that is not binding, and
  **may** for a permitted option. Any other form (will, must, is required
  to) is non-standard and must be replaced with the correct keyword before
  the requirement enters a baseline.
- A requirement must express exactly one obligation. If a statement
  contains more than one **shall** clause, it covers more than one
  requirement; each clause must be separated into its own standalone
  statement so that traceability, verification, and change control can be
  applied at the right granularity.
- Ambiguous and unverifiable terms are forbidden in requirement text.
  Words such as "adequate", "appropriate", "sufficient", "user-friendly",
  "maximize", "minimize", "easy", "robust", "flexible", "where
  applicable", and "etc." have no measurable criterion attached and must
  be replaced with specific, quantified limits or pass/fail conditions.
- Rationale and justification belong in a NOTE attached to the
  requirement, never in the requirement text itself. Phrases such as
  "in order to", "so that", "because", and "to enable" signal that
  rationale has been embedded and must be moved.

## Workflow

1. For each candidate requirement statement, identify the verbal form
   present: **shall**, **should**, **may**, or a non-standard form.
   If a non-standard form (will, must, is required to, are required to)
   is found, reject the statement and instruct the author to substitute
   **shall**. If no verbal form is present, the statement is not a
   requirement and must be reworded or removed.
2. Count the number of **shall** clauses in the statement. If the count
   is greater than one, split the statement at each obligation boundary
   so that each resulting statement contains exactly one **shall** clause
   and is independently traceable.
3. Scan the requirement text for ambiguous or unverifiable terms from
   the forbidden list. For each hit, flag the term and require the
   author to replace it with a specific, measurable criterion (a
   numeric limit, a test-observable condition, or a defined standard
   reference).
4. Scan the requirement text for rationale-marker phrases. For each
   hit, extract the rationale clause and move it verbatim into a NOTE
   below the requirement. The requirement text itself retains only the
   obligation.
5. After applying steps 1–4, re-check the resulting statement. A
   requirement passes wording review when: the verbal form is **shall**
   (or **should**/**may** for the appropriate type), no forbidden terms
   remain, the obligation count is one, and no rationale-marker phrase
   is present.

## Pitfalls

- Accepting "will" as equivalent to "shall" — in English-language
  technical standards "will" is a declaration of fact about what the
  system is expected to do, not an obligation imposed on it; replacing
  it with "shall" changes the normative weight.
- Leaving "and/or" in requirement text — the ambiguity (is one
  sufficient, or are both required?) makes the verification criterion
  undefined; the author must decide and write two explicit alternatives
  or a conjunction.
- Treating the absence of a forbidden term as a guarantee of
  verifiability — a requirement can be free of listed forbidden terms
  and still be unverifiable if it lacks a measurable threshold. The
  forbidden-term scan is a minimum filter, not a completeness check.
- Splitting a compound requirement and losing shared context — when a
  single statement is split into two, both new requirements must carry
  the subject noun and any qualifying conditions that were implicit in
  the original combined form.

## Behavior contract (gate 3)

The verbal-form detection, obligation-count, forbidden-term, and
rationale-marker logic is exercised by the gate 3 contract test:
scripts/test_e1006_wording.py against scripts/e1006_wording_logic.py
(stdlib unittest, offline). Run:
python3 scripts/test_e1006_wording.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 →