Skip to content

bestdeejay-design/agent-skills / skills/dewey

Document classifier — assigns L1-L6 taxonomy level to each document, enforces required docs per level, detects missing required documents. Use when: "classify docs", "document classification", "missing docs", "required documents", "document taxonomy", "dewey".

Dewey — Classifier

Assigns taxonomy level (L1-L6) to each document, enforces required documents per project level.

Document Hierarchy (L1–L6)

LevelTypeExamples
L1Contractscontracts/openapi/*.yaml, contracts/asyncapi/*.yaml
L2Product Canondocs/VISION.md, docs/PRD.md, docs/ROADMAP.md, docs/FEATURES.md
L3Engineering Canondocs/ARCHITECTURE.md, docs/ADR/, docs/SAGA/, docs/TEST_CASES.md
L4Deriveddocs/REFERENCE.md, docs/DEV_GUIDE.md, docs/STATUS.md
L5ArtifactsGenerated files (API docs, changelogs, diagrams)
L6AuxiliaryREADME.md, CONTRIBUTING.md, LICENSE, templates

What it does

  • Classifies every document by type and level
  • Determines project maturity level (L1-L3 based on required docs present)
  • Validates required documents exist for detected level

Usage

# Via Chronos orchestrator
chronos --path . --preset standard

# Direct invocation
python -m chronos.agents.dewey --path .

Output Format

[warning] missing: Required L2 document missing — docs/ROADMAP.md
[info] classified: docs/ARCHITECTURE.md → L3 Engineering Canon
[info] project_level: L2 (Product Canon) — 3/4 required docs present

Required Documents per Level

LevelRequired
L1At least 1 contract file (OpenAPI/AsyncAPI/JSON Schema)
L2VISION.md, PRD.md, ROADMAP.md
L3ARCHITECTURE.md, ADR/ directory

Triggers

  • classify docs / document classification
  • missing docs / required documents
  • document taxonomy / doc hierarchy
  • dewey

Integration

Loaded by Chronos as part of standard and full presets.

Boundaries

  • Do not use for duplicate detection, links, or orphan statistics; use censor or veles.

Procedure and output contract

Classify by normalized repository-relative path, report the matched rule, and show the detected maturity level before checking required documents. Required-document findings are warnings until the project declares a stricter policy. Unknown files must be reported as unknown rather than forced into a taxonomy level.

Verification

A useful report includes every document's classification, the rule or pattern that matched it, required documents considered, and a deterministic summary. Review false positives for custom repository layouts before creating files.

rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 470kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 197kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 197kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 197kUpdated Claude CodeCodexVerifiedInstall