agent-team-kit
# Agent Team Kit — SKILL.md
What this skill does
# Agent Team Kit — SKILL.md
*A framework for self-sustaining AI agent teams.*
---
## What This Is
A complete team process kit for OpenClaw agents that enables:
- **Self-service work queues** — Agents pick up tasks without human bottlenecks
- **Clear role ownership** — Everyone knows who does what
- **Continuous discovery** — Work flows in automatically
- **Proactive operation** — The team runs itself via heartbeat
---
## Quick Start
### 1. Copy the Process Files
```bash
# From your workspace root
cp -r skills/agent-team-kit/templates/process ./process
```
This creates:
- `process/INTAKE.md` — The 5-phase work loop
- `process/ROLES.md` — Role definitions
- `process/OPPORTUNITIES.md` — Raw ideas/discoveries
- `process/BACKLOG.md` — Triaged work queue
- `process/STATUS.md` — Who's working on what
### 2. Add Heartbeat Config
Merge `templates/HEARTBEAT.md` into your existing `HEARTBEAT.md`:
```bash
cat skills/agent-team-kit/templates/HEARTBEAT.md >> HEARTBEAT.md
```
Or copy it directly if you don't have one yet.
### 3. Customize Roles
Edit `process/ROLES.md` to match your team:
- Rename roles to fit your domain
- Add/remove specialized execution roles
- Update the human lead section with your name
---
## The Intake Loop
```
DISCOVER → TRIAGE → READY → EXECUTE → FEEDBACK
↑ ↓
└──────────────────────────────────────┘
```
1. **Discover** — Find opportunities (Scout role)
2. **Triage** — Decide what's ready (Rhythm role)
3. **Ready** — Self-service queue (any agent)
4. **Execute** — Do the work (assigned agent)
5. **Feedback** — Learn and spawn new ideas (completing agent)
---
## Core Roles
| Role | Mission | Owns |
|------|---------|------|
| **Scout 🔍** | Find opportunities | `OPPORTUNITIES.md`, discovery |
| **Rhythm 🥁** | Keep work flowing | `BACKLOG.md`, triage |
| **Harmony 🤝** | Keep team healthy | Unblocking, retros |
| **[Human]** | Strategic direction | Hard calls, spawning |
**Execution roles** (spawn as needed):
- Link 🔗 — Builder
- Pixel 🎨 — Designer
- Sage 🦉 — Architect
- Echo 📢 — Voice
- Spark ✨ — Creative
---
## Key Principles
### Self-Service
If it's in Ready, any agent can pick it up. No approval needed.
### Clear Ownership
Every phase has ONE owner. No ambiguity.
### Always Log
Ideas, discoveries, completions — if you don't log it, it didn't happen.
### Spawn, Don't Solo
Main agent coordinates. Sub-agents execute. Don't do everything yourself.
---
## File Structure
```
process/
├── INTAKE.md # How the loop works (reference)
├── ROLES.md # Who does what
├── OPPORTUNITIES.md # Raw discoveries (anyone adds)
├── BACKLOG.md # Triaged work (Rhythm maintains)
└── STATUS.md # Current activity (self-updated)
HEARTBEAT.md # Proactive check triggers
```
---
## Heartbeat Integration
Add to your heartbeat checks:
```markdown
### Team Health (run hourly)
- [ ] OPPORTUNITIES.md stale? → Spawn Scout
- [ ] Ready queue empty? → Alert Rhythm
- [ ] Active work stuck >2h? → Nudge owner
- [ ] Any unresolved blockers? → Harmony
```
The heartbeat keeps the loop spinning even when the human isn't watching.
---
## Customization
### Adding a New Role
1. Define in `ROLES.md`:
- Mission (one sentence)
- Owns (what they're responsible for)
- Cadence (how often they work)
- Outputs (what they produce)
2. Update the ownership matrix
3. Add spawn criteria in `INTAKE.md` if needed
### Changing the Loop
The 5-phase loop is flexible. Adapt it:
- Add validation gates between phases
- Split EXECUTE into parallel tracks
- Add approval checkpoints (if your domain requires it)
---
## Anti-Patterns
❌ Human manually adds every task → Use triage role instead
❌ Waiting for permission to pick up work → Ready = fair game
❌ One agent does everything → Spawn specialists
❌ Ideas stay in heads → Log to OPPORTUNITIES.md
❌ Heartbeat just returns OK → Actually check the loop
---
## Metrics (Optional)
Track team health:
- **Cycle time** — OPPORTUNITIES → DONE
- **Queue depth** — Items in Ready (healthy: 5-15)
- **Stale items** — Days since last triage
- **Spawn rate** — Sub-agents created per day
---
*The system runs itself. Your job is to trust it.*
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.