diegosouzapw/awesome-omni-skill / skills/ai-agents/agent-protocol
agent-protocol
VerifiedHuman and agent coordination protocol for repos using .agentprotocol. Use to manage TODO intake, open and archived work items, and plan/build docs with deterministic indexes.
Agent Protocol
Coordinate work in repos that use .agentprotocol/. Keep work items self-contained and minimize follow-up questions.
Always load first
- Read
.agentprotocol/README.mdat the start of any session. - If
.agentprotocol/is missing, offer to initialize withbun ./skills/agent-protocol/scripts/init.ts.
Core structure
.agentprotocol/README.md: protocol contract and Active Work Index..agentprotocol/TODO.md: intake queue..agentprotocol/open/<ID>-<slug>/: active work items..agentprotocol/archive/<ID>-<slug>/: completed or cancelled items (moved as a whole).
Workflow
- Intake work in
.agentprotocol/TODO.md. - Create a work item with
create.ts(build-only by default; add--planfor plan + build). - Write or refine
plan.mdif needed; keep it flexible (PRDs, user stories, specs). - Execute from
build.mdwith tasks, verification, and append-only log. - Archive by moving the whole directory to
.agentprotocol/archive/.
Work selection
- If the user names a path or ID, use it.
- If not, suggest up to 3 candidates from the Active Work Index and TODO. The user chooses.
- Never auto-select.
plan.md
- Optional design surface. May include PRDs, user stories, acceptance criteria, constraints, and invariants.
- Frontmatter:
id,title,status,created_at,updated_at, optionalrefs. statusvalues:draft | ready | done | cancelled.readymeans Open Questions is empty (or risks explicitly accepted).
build.md
- Execution surface with tasks, verification, and append-only log.
- May exist without a plan (ad-hoc).
- Frontmatter:
id,status,created_at,updated_at, optionalplan_id. statusvalues:todo | in_progress | blocked | done | cancelled.- If
build/exists, include a Build File Index table listing allbuild/*.md(sorted by path). build/*.mdfiles are plain markdown by default (no required frontmatter).
Active Work Index
.agentprotocol/README.mdcontains a markdown table of all open work item directories.- Update with
bun ./skills/agent-protocol/scripts/reindex.ts(deterministic; avoids manual edits). - Use
--nextto include next-action extraction when desired.
IDs and timestamps
IDis Crockford base32 encoding of UUIDv7 bytes.- Uppercase, fixed 26 chars, left-padded with
0. - Alphabet:
0123456789ABCDEFGHJKMNPQRSTVWXYZ. - No zero padding in body identifiers (use
US-1, notUS-001). created_at/updated_atuse RFC3339 with timezone (recommend UTCZ).
Archiving
- When a work item is
done | cancelled, move the entire directory fromopen/toarchive/. - Remove the row from the Active Work Index.
Migration
- For old
context/repos, followreferences/migration.md.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 466k | Updated | Claude CodeCodex | Verified | Install |
| 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: 196k | Updated | Claude CodeCodex | Verified | Install |
| 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: 196k | Updated | Claude CodeCodex | Unverified | Install |
| 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: 196k | Updated | Claude CodeCodex | Verified | Install |