Agent skill
housekeeping
Repository housekeeping workflows for AGENTS/CLAUDE architecture, progressive disclosure, and migration of legacy monolithic instruction files.
Install this agent skill to your Project
npx add-skill https://github.com/bout3fiddy/agents/tree/main/skills/housekeeping
Metadata
Additional technical details for this skill
- id
- housekeeping.core
- version
- 1
- priority
- 65
- task types
-
[ "agents-architecture", "migration", "claude-architecture", "repo-housekeeping", "housekeeping" ] - load strategy
- progressive
- trigger phrases
-
[ "AGENTS.md", "CLAUDE.md", "progressive disclosure", "legacy AGENTS migration", "instruction cleanup", "context-memory organization", "housekeeping" ] - activation policy
- both
- workflow triggers
-
[ "agents_architecture_requested", "legacy_migration_requested", "docs_housekeeping_requested" ]
SKILL.md
Housekeeping (AGENTS/CLAUDE Architecture)
Use this skill when work is about organizing or modernizing AGENTS.md/CLAUDE.md context systems.
Operating rules
- Keep root
AGENTS.mdconcise: critical guardrails, task router, canonical commands, and links. - Prefer scoped instruction files in dense areas (
apps/frontend,infra,apps/agent, etc.). - Move deep or volatile details into
.agents/repo-context/*, not rootAGENTS.md. - Curate continuously: deduplicate, resolve contradictions, and remove stale guidance.
- Preserve behavior intent during migrations; change structure first, then tighten wording.
Workflow
- Assess current state (concise router vs mixed/legacy monolith).
- Select target architecture from references.
- Migrate content into scoped
AGENTS.mdfiles and deep docs. - Rewrite root
AGENTS.mdas a short router. - Add freshness metadata for volatile facts where feasible.
- Verify links/routes and remove conflicting duplicate rules.
- If work includes both AGENTS.md and CLAUDE.md, apply parity checks in the same pass.
Canonical ownership
instructions/global.md: trigger registration, precedence, escalation, and lifecycle policy.skills/housekeeping/SKILL.md: workflow sequence and reference selection for housekeeping execution.skills/housekeeping/references/*: deep guidance and operating patterns; AGENTS and CLAUDE are references.
Reference triggers (open when clearly relevant)
- AGENTS/CLAUDE architecture, progressive disclosure, or context-memory organization ->
skills/housekeeping/references/agents-architecture.md - Legacy monolithic AGENTS cleanup, contradiction pruning, or migration planning ->
skills/housekeeping/references/migration-playbook.md
References
skills/housekeeping/references/index.md- References index for this skillskills/housekeeping/references/agents-architecture.md- Target architecture, file tree, and root templateskills/housekeeping/references/migration-playbook.md- Legacy-to-modern migration workflow and checklist
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
design
Frontend design curation skill for UI critique, motion storyboarding, and DialKit tuning. Use when the user asks for interface feedback, animation sequencing, or interactive design-control setup.
planning
Planning workflows for clarifying ambiguous build requests, running spec/work-package delivery, and managing Linear lifecycle transitions.
coding
Core engineering skill for implementation, bug fixes, refactors, and technical reviews with mandatory smell guardrails and targeted domain reference routing.
skill-creator
Create, update, or install skills (including planning/specs and edits to skills/*) using our repo workflow (uv + skills-ref validation, lean SKILL.md, references/ for detail, and sync via bin/sync.sh).
edit-article
Edit and improve articles by restructuring sections, improving clarity, and tightening prose. Use when user wants to edit, revise, or improve an article draft.
handoff
Compact the current conversation into a handoff document for another agent to pick up.
Didn't find tool you were looking for?