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
  • 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.

Back to skills

Fable Parity

ASecurity

Opus 4.8을 Fable 5의 절차·성능으로 운용하는 강제형 워크플로우. spec→analyze→design→implement→verify→done 단계를 훅과 상태머신으로 강제한다. 트리거: "fable parity", "파리티 모드", "분석-설계-구현 절차로", 새 기능·리팩터링 등 비자명한 개발 작업 시작 시.

19 stars
0 votes
0 copies
1 views
Added 8/30/2026
ai-agentsbashapi

Works with

claude codeapi

Security Analysis

A100/100

Scanned 8/30/2026

Install to Claude Code

$npx -y skills add claude-code-expert/example --skill fable-parity --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Fable Parity?

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

Security grade badge for Fable Parity
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/claude-code-expert-fable-parity/badge)](https://www.skillsdirectory.com/skills/claude-code-expert-fable-parity)

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

Download with Pro
Files
SKILL.md
---
name: fable-parity
description: >
  Opus 4.8을 Fable 5의 절차·성능으로 운용하는 강제형 워크플로우.
  spec→analyze→design→implement→verify→done 단계를 훅과 상태머신으로 강제한다.
  트리거: "fable parity", "파리티 모드", "분석-설계-구현 절차로", 새 기능·리팩터링 등
  비자명한 개발 작업 시작 시.
---

# fable-parity — Fable 5 패리티 워크플로우

이 스킬은 지침이 아니라 **강제 장치**다. 프롬프트만으로는 절차 이탈을 막을 수 없으므로
세 겹으로 강제한다:

1. **상태머신** (`scripts/phase.sh`) — 산출물 파일 없으면 단계 전환 자체가 실패 (exit 1)
2. **PreToolUse 훅** — implement 단계 전 코드 Edit/Write를 도구 수준에서 차단 (exit 2)
3. **Stop 훅** — 검증 증거(`verify.md`) 없이 턴 종료 시도를 차단

훅 설치는 `install.sh` (아래 §설치). 훅이 없어도 phase.sh 단독으로 상태머신은 동작한다.

## 실행 절차 (스킬 발동 시 이 순서를 따른다)

```bash
bash .claude/skills/fable-parity/scripts/phase.sh start
```

| 단계 | 할 일 | 산출물 (전환 전제조건) | 전환 명령 |
|---|---|---|---|
| spec | 목표·제약·완료 기준 작성, 사용자 확인 | `.claude/fable-parity/spec.md` | `phase.sh set analyze` |
| analyze | 병렬 탐색 서브에이전트로 영향 범위 맵 작성 | `.claude/fable-parity/analysis.md` | `phase.sh set design` |
| design | 접근법 2–3개 비교 → 변경 목록·리스크·완료 기준 매핑 | `.claude/fable-parity/design.md` + **사용자 승인** | `phase.sh set implement --user-approved` |
| implement | 변경 목록 순서대로 구현, 항목마다 빌드·린트 | — | `phase.sh set verify` |
| verify | 테스트 + 실제 실행, fresh-context 리뷰 에이전트 | `.claude/fable-parity/verify.md` (명령+출력 증거, PASS 포함) | `phase.sh set done` |
| done | 교훈 1건 = 1파일 기록 | — | 완료 |

규칙:
- `--user-approved`는 사용자가 design.md를 실제로 승인했을 때만 넘긴다. 임의로 넘기지 마라.
- 각 산출물 형식과 프롬프트 문구(위임 트리거, 커버리지 검증, no-tidying)는 [reference.md](reference.md) §4–§6 참조.
- 사소한 수정(오타, 한 줄 픽스)은 이 워크플로우 대상이 아니다 — `phase.sh off` 상태로 그냥 진행.

## 모델 설정 (성능 패리티)

- Claude Code: `/model opus` (effort 기본 xhigh 유지)
- API 직접 호출: `thinking={"type":"adaptive"}` **필수 명시**(생략 = 꺼짐), `output_config={"effort":"xhigh"}`,
  `max_tokens` ≥ 64K + 스트리밍. 상세는 [reference.md](reference.md) §2.

## 설치 (다른 프로젝트에 적용)

```bash
bash skills/fable-parity/install.sh /path/to/target-project
```

- 스킬을 대상 프로젝트 `.claude/skills/fable-parity/` 에 복사
- 훅 4개(SessionStart, UserPromptSubmit, PreToolUse, Stop)를 `.claude/settings.json` 에 병합 (백업 생성)

해제: `phase.sh off` (게이트만) / settings.json에서 훅 제거 (전체).

Attribution

claude-code-expertclaude-code-expert
View sourceMore from claude-code-expert →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

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

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

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".

1066601 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', ...

686011 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.

651 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 →