| name | ai-collab-protocols |
| description | Surface in-task AI collaboration protocols one tactic at a time. Use when the user refers to entities by colloquial labels, asks how to structure a Claude workflow, or describes a multi-step workflow without durable URLs. |
| disable-model-invocation | true |
Spot the protocol gap, name the better tactic, point at the durable handle. Small surgical interventions, not a lecture.
Core protocols
URL-as-entity-reference
If the user says "the PR Bob mentioned", "that bug from last week", or "the function we discussed", stop and ask for the URL or the symbol path. Why: names are ambiguous in long-context sessions and unrecoverable across sessions. A stable URL (GitHub PR comment permalink, MCP resource URI like @github:pr/owner/repo/123#comment-456, file:line reference) survives compaction and enables exact match. The chat that prompted this skill explicitly named this as the highest-signal collaboration tip.
Durable PR-comment threads as session memory
Long-running PR comment threads outlive any single session and form the persistence layer for multi-session work. Prefer leaving a comment on the PR over a chat-only handoff. Why: the next session (yours, a colleague's, or a future agent's) can resume from the thread without replaying context. Chat is ephemeral; PR comments are addressable.
Fit the protocol
When a project has an AGENTS.md, CLAUDE.md, or .clinerules, read it before acting. When the project has none and the work is non-trivial, propose authoring one. Defer to init for AGENTS.md authoring rather than re-doing it here. Why: project-level rule files are the cross-tool agent-config convention; fighting them creates drift across sessions.
Anti-patterns to flag
- Screenshot-only context: loses URL grounding, copy-paste, and search. Pair every screenshot with the URL or text export.
- Token-usage / LOC framing as a quality proxy: quantity is not capability. The chat that prompted this skill explicitly rejects this framing; surface the rejection if the user reaches for it.
Optional 2026 research extensions (verification status)
Earlier candidate extensions, second-pass verified. Usage details belong in a dedicated reference, not here:
- ✅ Tool Search Tool (verified, Anthropic official). Source:
https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-search-tool.
- ❌ REVERSE_PROMPT.md / TASKLOG.md bidirectional pattern (unverified). No primary-source documentation found. Do not cite as 2026 standard.
- ⚠️ Structured-output filtering / summarization (partial; different API names). Concepts exist in the Messages API but not under the names originally claimed. Refer to the official Messages API reference before citing.
Modality differentiation
| Skill | When |
|---|
ai-collab-protocols | In-task tactic surfacing: user describes an AI workflow informally |
contexts | Pre-implementation context sweep: gather files / patterns / tooling for a feature |
qa | Bug capture: user reports something broken in plain language |
init | AGENTS.md authoring: onboarding a repository, capturing hard-to-rediscover conventions |
Posture
Surface one tactic at a time. Name the protocol. Show the better handle in concrete form (the actual URL, the actual file path, the actual symbol name).
