メニュー
Generate a comprehensive map of all files relevant to a task before making any changes. Use when about to implement features, fix bugs, or refactor code — maps files to modify, dependencies, tests, reference patterns, and risk assessment.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation. Produces a validated design doc, then invokes writing-plans.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
TaskLang pseudocode language for AI agent prompting. Use when writing, reviewing, or refactoring agent definitions, skill playbooks, commands, workflow pipelines, or project rules in TaskLang syntax.
Create tools on the fly — Bash scripts, Python scripts, Node.js scripts, or request MCP server/CLI installation — when the agent identifies a capability gap. Use when a task requires a tool that doesn't exist yet, or when an MCP server or CLI tool would solve the problem better than manual steps.
Before answering any question or starting any task, identify what files and context are needed for an accurate, complete response. Use when the agent needs to understand what it doesn't know yet — the meta-cognitive 'stop and think' gate.
SOC 職業分類に基づく
| name | context-map |
| description | Generate a comprehensive map of all files relevant to a task before making any changes. Use when about to implement features, fix bugs, or refactor code — maps files to modify, dependencies, tests, reference patterns, and risk assessment. |
TASKLANG TYPE SKILL
IDENTITY "Context Map — Know Before You Change"
Cartographer skill that maps the blast radius of any code change before it happens. Produces a structured map showing: files to modify, their dependencies, related tests, reference patterns to follow, and a risk assessment. This is the playbook for someone who never makes a change without understanding the full picture.
!!! Never modify code without a context map. !!! The cost of reading 20 files is nothing compared to the cost of breaking 3 you didn't know about. !!! Every dependency you miss is a bug you'll ship.
MAP workflows "workflows/scan-codebase.md" -> "Search the codebase for files related to the task" "workflows/map-dependencies.md" -> "Trace imports, exports, and cross-file relationships" "workflows/assess-risk.md" -> "Evaluate breaking changes, migrations, and configuration impacts"
KNOWLEDGE PATTERNS - "Ripple analysis — for each file to modify, trace what depends on it" - "Pattern matching — find similar implementations in the codebase to use as reference" - "Test discovery — for each source file, find its test file(s) by convention" - "Config surface — identify all config/env files that might need changes" - "API surface — identify public interfaces that consumers depend on" - "Migration detection — flag changes that require data or schema migrations"
CONVENTIONS - "Always produce a table: File | Purpose | Changes Needed" - "Dependencies table: File | Relationship (imports/exports/extends)" - "Test table: Test File | What It Covers" - "Reference patterns: File | Pattern to follow" - "Risk checklist: breaking API, migrations, config changes, side effects" - "Sort files by modification priority: core changes first, then ripple effects"
STRATEGY CAPTURE: dependency patterns, common file relationships, project-specific conventions UPDATE_FREE: references/ UPDATE_APPROVAL: SKILL.md
REQUIRE
