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

Special Conditions

ASecurity

Use when you must determine whether a novel or unusual transport-category design feature needs a special condition under FAR 25.17 or CS-25.17 instead of being covered by the existing airworthiness standards: classify the feature from its novelty, existing coverage, and safety significance, then draft the special condition scope with the affected subject, the issue addressed, and the proposed means of compliance (analysis, test, simulation). Produces the special-condition verdict and the scop...

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 special-conditions --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Special Conditions?

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

Security grade badge for Special Conditions
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ashfordeou-special-conditions/badge)](https://www.skillsdirectory.com/skills/ashfordeou-special-conditions)

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

Download with Pro
Files
SKILL.md
---
name: special-conditions
description: "Use when you must determine whether a novel or unusual transport-category design feature needs a special condition under FAR 25.17 or CS-25.17 instead of being covered by the existing airworthiness standards: classify the feature from its novelty, existing coverage, and safety significance, then draft the special condition scope with the affected subject, the issue addressed, and the proposed means of compliance (analysis, test, simulation). Produces the special-condition verdict and the scoped content for the certification program. Trigger: special condition, novel design feature, fly-by-wire, envelope protection, unusual technology, new technology, means of compliance, FAR 25.17, CS 25.17."
license: Apache-2.0
compliance: STANDARDS-REF
standards:
  - id: far-25
    reference-only: true
  - id: cs-25
    reference-only: true
gated: false
domain: avionics
pack: avionics
compatibility: "agentskills.io SKILL.md; any SKILL.md host (Claude Code, Hermes, OpenClaw)"
metadata:
  domain: avionics
  subdomain: far-cs25
  tags: [special-conditions, far-25, cs-25, novel-design-feature, fly-by-wire, means-of-compliance, transport-category, envelope-protection]
  version: 0.1.0
  author: Aero Agent Skills
---

# Special Conditions (avionics/far-cs25/special-conditions)

Use when the task is the special-conditions decision for a transport
airplane: whether a novel or unusual design feature is covered by the
existing FAR-25 / CS-25 airworthiness standards or needs a special
condition under 25.17, and what that special condition should contain.

## Domain quick reference

- FAR 25.17 / CS-25.17 let the certification authority issue special
  conditions when a novel or unusual design feature is not covered by
  the existing airworthiness standards.
- The special condition states additional requirements for the feature
  and the means of compliance that demonstrate them.
- Examples from certification history: fly-by-wire flight control with
  envelope protection, and novel composite wing structures.
- A special condition is scoped per feature: affected subject, the
  issue addressed, and the proposed means of compliance (analysis,
  test, simulation).
- This module reasons over categorical inputs (booleans and short
  text), so no physical quantities or unit conventions apply.

## Workflow

1. Describe the feature: name, novelty (novel), coverage by an
   existing standard (existing_standard), and safety significance
   (safety_significant).
2. Classify with classify_feature: returns the verdict and the
   category from the rule table.
3. When the verdict is special-condition-required, scope the content
   with draft_scopes: subject area, issue, means of compliance.
4. Bring the draft scope to the certification authority for agreement
   on the requirement text and the means of compliance.

## Pitfalls

- Treating every new feature as needing a special condition when an
  existing standard already covers it.
- Scoping a special condition (draft_scopes) for a feature the rule
  table classifies as covered: it raises ValueError.
- Passing numbers or strings where booleans are expected, or omitting
  a required key: the module raises ValueError.
- Confusing the special-conditions decision with the certification
  basis or the 25.1309 safety assessment (separate leaves).

## Behavior contract (gate 3)

The classification and scoping logic is exercised by the gate 3
contract test: scripts/test_special_conditions_logic.py against
scripts/special_conditions_logic.py (stdlib unittest, offline).
Run:
python3 scripts/test_special_conditions_logic.py

## Compliance

- FAR-25 is US government work (17 U.S.C. 105), quotable with
  citation; CS-25 reproduction authorised with source acknowledged
  (EASA). Paraphrase preferred 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 →