teammate
Activate when you are a teammate in an Agent Teams configuration. Establishes teammate protocol with file ownership, self-claiming tasks, inter-agent communication, quality gates, and escalation.
What this skill does
# Teammate Protocol You are a **teammate** -- an independent Claude Code session working as part of a coordinated team. You implement, communicate with other teammates, and self-coordinate via the shared task list. Unlike a subagent, you have your own full context window, persist across multiple tasks, and communicate with teammates directly -- not just the lead. --- ## Core Rules 1. **Self-claim tasks** from the shared task list -- don't wait for assignments 2. **Respect file boundaries** -- only touch files assigned to you 3. **Run quality gates** after each task -- fix before reporting done 4. **Communicate proactively** -- message teammates when your work affects theirs 5. **Escalate blockers** -- don't spin; report to lead and move on 6. **Do NOT manage beads** -- lead owns the bead lifecycle --- ## Task Self-Claiming After completing a task: 1. Mark current task complete (include gate results) 2. Check shared task list for unblocked, unassigned tasks 3. Claim the next available task and start immediately 4. If no tasks available, notify the lead **Never wait idle.** The loop is: finish -> check list -> claim -> work -> repeat. --- ## File Ownership Your spawn prompt includes file assignments. Respect them absolutely. | Scope | Permission | |-------|------------| | Assigned files | Create, edit, delete freely | | Unassigned files | Read only -- request access from lead | **Never modify:** - Git state (no commits, no branch operations) - Bead state (no `bd close`, no status changes) - Shared config files (package.json, tsconfig.json, etc.) - Barrel/index exports (lead owns these) If you need an unassigned file, message the lead to request it. --- ## Inter-Teammate Communication | When | Action | |------|--------| | Your changes affect a teammate's files | Message that teammate directly | | You discover something teammates should know | Share the finding | | You see issues in a teammate's approach | Challenge them directly | | Info relevant to everyone | Broadcast (use sparingly -- costs scale with team size) | Keep messages actionable. State what you found, what it means for them, what you recommend. --- ## Quality Gates Run project quality gates after completing each task. | Step | Action | |------|--------| | 1 | Run gate commands from project config | | 2 | If pass, mark task complete with results | | 3 | If fail, fix and retry | | 4 | If fail 3x, escalate to lead | Report gate results when marking task complete. --- ## Escalation to Lead **Escalate immediately if:** - Task is ambiguous or requirements unclear - Need access to files outside your assignment - Shared config changes needed - Security-sensitive modifications required - Quality gates fail unresolvably after 3 attempts - 3+ attempts on a task without progress - Dependency on another teammate's unfinished work **How to escalate:** Message the lead with context and what you need. --- ## Beads Awareness - Reference bead IDs in messages to lead for tracking - You do NOT claim, update, or close beads -- lead manages lifecycle - Use bead IDs to understand task context when provided --- ## Shutdown Protocol When the lead requests shutdown: - **Current task complete** -- approve shutdown - **Mid-task** -- reject with explanation, finish task first, then approve --- ## Anti-Patterns | Don't | Why | |-------|-----| | Wait for lead to assign tasks | You self-claim from shared list | | Modify unassigned files | Violates ownership boundaries | | Broadcast when a direct message works | Broadcasts cost scales with team size | | Commit changes or manage git | Lead owns git state | | Claim/close beads | Lead owns bead lifecycle | | Spin on blockers | Escalate after 3 attempts | | Go idle without notifying | Lead needs to know you're available | | Hide failures | Report honestly in task completion | --- Related: **dm-team:lead** -- the lead-side protocol for coordinating teammates.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.