Skill Detail — Security skill for Claude Code
Shared model-rubric detail + plan-doc update pattern for gate-a~e, audit, doc-cleanup.
How to install Skill Detail
Installs to ~/.claude/skills/park-jongbeom-patrick-work-harness-skill_detail/SKILL.md
mkdir -p ~/.claude/skills/park-jongbeom-patrick-work-harness-skill_detail && curl -fsSL https://raw.githubusercontent.com/park-jongbeom/patrick-work-harness/HEAD/skills/SKILL_DETAIL.md -o ~/.claude/skills/park-jongbeom-patrick-work-harness-skill_detail/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Skill Detail does
name: SKILL_DETAIL description: "Shared model-rubric detail + plan-doc update pattern for gate-a~e, audit, doc-cleanup. Load on demand (not auto-loaded). Reference via Read when R-13 guard, Effort/Thinking rule, or tier-aware plan-doc update wording is needed."
Skill Common Model Rubric Detail
**Load-on-demand** — this file is NOT auto-loaded. Load it explicitly via `Read` when the R-13 cost-justification guard, Effort/Thinking rule, PROC-MODEL-RUBRIC rationale, or the tier-aware p
Alternatives in Security
- 02 Cross Reference Audit — Cross-Reference Audit 1.1k ★
- Comm — by CommE2E - Serves as a development reference for E2E-encrypted messaging applications with code organization 325 ★
- Senior Engineering Partner — A stack-agnostic Claude Code skill: strict code reviewer, pair programmer, debugger, and mentor (Python/Bash/A 148 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Claude Clean Context
Keep Claude Code's always-loaded context lean: deterministic memory guard-rail distiller + skills audit. Never
Consistency Check
Audit a doc bundle for cross-reference integrity, count drift, pronoun ambiguity, audience assumptions, and ot
Token Optimizer Skill
Token cost optimization skill for Claude Code — model routing (Opus/Sonnet/Haiku), extended thinking tuning, p
Gaia Audit
Audit memory, wiki, and auto-loaded files for duplication, conflicting instructions, and stale content. The de
Repo Doctor
Audit a repo's agent docs — AGENTS.md/CLAUDE.md topology, always-loaded token cost, CodeMap freshness and line
Onsite Audit
Run on-demand onsite SEO health audit using DataForSEO Lighthouse + on_page_instant_pages. Audits the homepage
Related Agents
Review Workflow Context Budget
Reviews workflow machinery for context-window budget on three axes: always-loaded surface, load-on-demand disc
Manual Rule Liveness Prober
Probes a manifest manual rule for liveness via with/without-rule fresh-subagent dispatch, capturing a RED→GREE
Daily Copilot
The everyday work partner. Use for prioritization, thinking out loud, "remember this", "challenge this", "what