원클릭으로 Manus에서 모든 스킬 실행

review-context

스타1

포크0

업데이트2026년 3월 1일 21:10

Use when reviewing the health and completeness of a project's context infrastructure, when the user says "review context", "context health", "how complete is my context", or periodically during maintenance. Provides infrastructure inventory, coverage analysis, and quality assessment.

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

Manus에서 실행

출처

pwarnock

pwarnock/codified-context

GitHub 저장소 열기 Creator 저장소 보기

다운로드

Manus에서 실행

관련 직업SOC

SOC 직업 분류 기준

소프트웨어 품질 보증 분석가·테스터컴퓨터 및 수학직·SOC 15-1253

파일 탐색기

2 개 파일

SKILL.md

readonly

name	review-context
description	Use when reviewing the health and completeness of a project's context infrastructure, when the user says "review context", "context health", "how complete is my context", or periodically during maintenance. Provides infrastructure inventory, coverage analysis, and quality assessment.
version	1.0.0

Overview: Comprehensive review of a project's codified context infrastructure. Evaluates completeness, quality, and coverage to identify gaps and improvements.

Workflow:

Infrastructure Inventory
- Check which context files exist in .claude/context/
- Compute completeness score (constitution, trigger tables, failure modes, subsystem map, specs)
- List any missing core files
- Count spec files and their sizes
Coverage Analysis
- Compare subsystem-map.md against actual directory structure — which subsystems lack documentation?
- Check trigger-tables.md coverage — what % of source directories have routing rules?
- Evaluate failure-modes.md entries — how many categories have entries?
- Cross-reference specs/ with subsystem map — which subsystems lack specs?
Quality Assessment Using criteria from ${CLAUDE_PLUGIN_ROOT}/skills/review-context/references/coverage-criteria.md:
- Constitution: All 10 sections populated? Commands verified? Stack current?
- Trigger tables: Routes specific enough? Rationale provided?
- Failure modes: Entries have all 4 fields (symptom, cause, fix, prevention)?
- Subsystem map: Boundaries clear? Dependencies documented?
Growth Metrics (if git history available)
- Context files creation date
- Number of updates since creation
- Ratio of codebase changes to context updates
- Session count since last audit
Recommendations Report Generate prioritized recommendations:
- Critical: Missing core files, broken references
- High: Undocumented subsystems with recent activity
- Medium: Stale specs, incomplete failure modes
- Low: Cosmetic improvements, optional enrichments
Output Format Present as a structured health report with scores and actionable items.

이 저장소의 다른 Skills

같은 저장소

audit-staleness

pwarnock/codified-context

Use when checking if project context documents are stale or outdated, when the user says "audit staleness", "check context drift", "are my docs current", or when the session-start hook detected drift. Performs deep analysis of all context documents against current codebase state.

2026-03-011

bootstrap-context

pwarnock/codified-context

Use when setting up persistent context infrastructure for a project, when the user says "bootstrap context", "set up context", "initialize codified context", or when a project lacks .claude/context/ directory. Creates constitution, trigger tables, failure modes, and subsystem map.

2026-03-011

codify-knowledge

pwarnock/codified-context

Use when capturing debugging insights, repeated explanations, architecture decisions, or gotchas as durable context. Use when the user says "codify this", "write this down", "remember this", "capture knowledge", or after debugging sessions. Implements the "explained it twice, write it down" methodology.

2026-03-011

context-routing

pwarnock/codified-context

Use when deciding which agent, skill, or context document to invoke for a given file or task. Consults trigger tables to route work to the right specialist. Activated automatically when working in a project with codified context infrastructure.

2026-03-011

codification-loop

pwarnock/codified-context

Use when capturing knowledge from conversations into durable context documents. Implements the "explained it twice, write it down" methodology for AI coding agents. Use when the user says "write this down", "remember this", "codify this", or when you detect repeated explanations, debugging breakthroughs, or architecture decisions.

2026-03-011

codified-context-patterns

pwarnock/codified-context

Use when setting up or understanding the three-tier codified context framework for AI coding agents. Provides the constitution template, trigger table format, failure modes format, and subsystem map format. Use when the user says "set up context", "create a constitution", "what is codified context", or wants to manually build persistent context infrastructure.

2026-03-011

name	review-context
description	Use when reviewing the health and completeness of a project's context infrastructure, when the user says "review context", "context health", "how complete is my context", or periodically during maintenance. Provides infrastructure inventory, coverage analysis, and quality assessment.
version	1.0.0

Overview: Comprehensive review of a project's codified context infrastructure. Evaluates completeness, quality, and coverage to identify gaps and improvements.

Workflow:

Infrastructure Inventory
- Check which context files exist in .claude/context/
- Compute completeness score (constitution, trigger tables, failure modes, subsystem map, specs)
- List any missing core files
- Count spec files and their sizes
Coverage Analysis
- Compare subsystem-map.md against actual directory structure — which subsystems lack documentation?
- Check trigger-tables.md coverage — what % of source directories have routing rules?
- Evaluate failure-modes.md entries — how many categories have entries?
- Cross-reference specs/ with subsystem map — which subsystems lack specs?
Quality Assessment Using criteria from ${CLAUDE_PLUGIN_ROOT}/skills/review-context/references/coverage-criteria.md:
- Constitution: All 10 sections populated? Commands verified? Stack current?
- Trigger tables: Routes specific enough? Rationale provided?
- Failure modes: Entries have all 4 fields (symptom, cause, fix, prevention)?
- Subsystem map: Boundaries clear? Dependencies documented?
Growth Metrics (if git history available)
- Context files creation date
- Number of updates since creation
- Ratio of codebase changes to context updates
- Session count since last audit
Recommendations Report Generate prioritized recommendations:
- Critical: Missing core files, broken references
- High: Undocumented subsystems with recent activity
- Medium: Stale specs, incomplete failure modes
- Low: Cosmetic improvements, optional enrichments
Output Format Present as a structured health report with scores and actionable items.