Standardizes project directory structures and agent instructions for consistent AI agent performance.

Install

mkdir -p .claude/skills/context-map && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/12367" && unzip -o skill.zip -d .claude/skills/context-map && rm skill.zip

Installs to .claude/skills/context-map

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Scaffold and audit agent-first repository structures using the Context_Map standard.
84 chars · catalog descriptionno explicit “when” trigger
Beginner

Key capabilities

  • Scaffold Context_Map directory structure
  • Create agent entry-point files
  • Generate documentation indexes and plan templates
  • Set up quality tracking documents
  • Audit existing projects against Context_Map standard

How it works

The skill either creates missing directories and files according to the Context_Map standard or audits an existing project against that standard, generating a compliance report.

Inputs & outputs

You give it
Project repository for scaffolding or auditing
You get back
Scaffolded directories and files, or a compliance report with score and remediation suggestions

When to use context-map

  • Scaffolding new agent projects
  • Auditing project directory structures
  • Standardizing AI documentation

About this skill

Context Map

Scaffold and audit agent-first repository structures using the Context_Map standard.

This skill provides two subcommands for managing the Context_Map directory layout, documentation routing, and quality standards in any project repository.

Subcommands

/context-map scaffold

Scaffolds the full Context_Map directory structure into the current project. Creates all required directories, agent entry-point files, documentation indexes, plan templates, and quality tracking documents.

Usage:

/context-map scaffold

What it creates:

  • Root agent entry points: AGENTS.md, CLAUDE.md, CODEX.md, .cursorrules, .github/copilot-instructions.md
  • Documentation directory: docs/ with _INDEX.md and subdirectories for architecture, golden-rules, quality, workflows, agent-guide, and session
  • Plans directory: plans/ with _INDEX.md, _TEMPLATE.md, active/, completed/
  • Guide directory: guide/ with README.md and 8 educational chapters
  • Scripts directory: scripts/ with validation scripts (check-structure.sh, check-doc-freshness.sh, check-agent-files.sh, check-doc-links.sh)
  • Quality files: docs/quality/QUALITY_SCORECARD.md and docs/quality/TECH_DEBT_REGISTER.md
  • Claude skill definitions: .claude/ directory with skill configurations
  • Additional agent configs: .codex/setup.sh, .cursor/rules/global.mdc

See references/directory-spec.md for the complete directory specification including which entries are required vs optional and the purpose of each file.

Instructions for Claude:

  1. Read references/directory-spec.md to load the full directory tree.
  2. Check which directories and files already exist in the project.
  3. Create only the missing directories and files. Never overwrite existing content.
  4. For each created file, insert the appropriate boilerplate from the spec.
  5. Set freshness dates on all new documentation files to today's date.
  6. After scaffolding, run a quick audit to confirm completeness.
  7. Report what was created and what already existed.

/context-map audit

Audits an existing project against the Context_Map standard and produces a compliance report with a score and remediation suggestions.

Usage:

/context-map audit

What it checks:

  • Structure compliance -- Verifies all required directories and files exist.
  • Agent routing -- Confirms each agent entry point (AGENTS.md, CLAUDE.md, CODEX.md, .cursorrules, copilot-instructions.md) routes to docs/ rather than duplicating content inline.
  • Documentation freshness -- Checks that every doc has a freshness date and that no document is older than 30 days.
  • Quality tracking -- Validates that QUALITY_SCORECARD.md and TECH_DEBT_REGISTER.md exist and contain scored entries.
  • Plan hygiene -- Confirms plan templates, indexes, and status fields are present.
  • Session continuity -- Checks that SESSION_HANDOFF.md exists and has been updated within the current working window.

See references/checklist.md for the full list of audit criteria. See references/remediation.md for step-by-step fixes for common failures.

Instructions for Claude:

  1. Read references/checklist.md to load all audit criteria.
  2. Walk the project directory tree, checking each criterion.
  3. For each check, record pass or fail with a brief reason.
  4. Calculate an overall score: (passed checks / total checks) as a percentage.
  5. For every failed check, look up the matching remediation in references/remediation.md.
  6. Present results as a markdown report with three sections:
    • Score summary -- overall percentage and letter grade (A >= 90, B >= 75, C >= 60, F < 60)
    • Detailed results -- each check with its pass/fail status
    • Remediation plan -- ordered list of fixes, highest impact first
  7. If the score is A-grade, congratulate the user. Otherwise, offer to auto-fix any issues that can be resolved non-destructively.

Notes

  • Scaffold is non-destructive. It never overwrites existing files.
  • Audit is read-only. It never modifies the project.
  • Both subcommands work in any repository, not just ones created from the Context_Map template.
  • When in doubt, prefer creating thin routing files that point to docs/ over embedding documentation directly in agent entry points.

When not to use it

  • When not managing agent-first repository structures
  • When not needing to scaffold or audit against the Context_Map standard
  • When needing to overwrite existing files during scaffolding

Limitations

  • Scaffolding is non-destructive and never overwrites existing files
  • Auditing is read-only and never modifies the project
  • Requires `references/directory-spec.md` for scaffolding details

How it compares

This automates the setup and verification of a specific agent-first repository structure, unlike manual project initialization or ad-hoc audits.

Compared to similar skills

context-map side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
context-map (this skill)05moNo flagsBeginner
project-planner329moReviewIntermediate
spec-kit-workflow118moNo flagsIntermediate
specification-architect139moReviewAdvanced

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

project-planner

adrianpuiu

Comprehensive project planning and documentation generator for software projects. Creates structured requirements documents, system design documents, and task breakdown plans with implementation tracking. Use when starting a new project, defining specifications, creating technical designs, or breaking down complex systems into implementable tasks. Supports user story format, acceptance criteria, component design, API specifications, and hierarchical task decomposition with requirement traceability.

32115

spec-kit-workflow

jmanhype

Guides specification-driven development workflow. Automatically invoked when discussing new features, specifications, technical planning, or implementation tasks. Ensures proper workflow phases (specify → clarify → plan → checklist → tasks → analyze → implement).

11111

specification-architect

adrianpuiu

A rigorous, traceability-first system that generates five interconnected architectural documents (blueprint.md, requirements.md, design.md, tasks.md, and validation.md) with complete requirements-to-implementation traceability. Use this skill when users need to architect systems, create technical specifications, or develop structured project documentation with guaranteed traceability.

1388

architecture

davila7

Architectural decision-making framework. Requirements analysis, trade-off evaluation, ADR documentation. Use when making architecture decisions or analyzing system design.

1244

context-driven-development

wshobson

Use this skill when working with Conductor's context-driven development methodology, managing project context artifacts, or understanding the relationship between product.md, tech-stack.md, and workflow.md files.

744

planning-agent

parcadei

Planning agent that creates implementation plans and handoffs from conversation context

531

Search skills

Search the agent skills registry