openclaw-mission-control
Coordinate AI agent teams via a Kanban task board with local JSON storage. Enables multi-agent workflows with a Team Lead assigning work and Worker Agents executing tasks via heartbeat polling. Perfect for building AI agent command centers.
67
49%
Does it follow best practices?
Impact
99%
3.41xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./data/skills-md/0xindiebruh/openclaw-mission-control-skill/openclaw-mission-control/SKILL.mdQuality
Discovery
57%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description identifies a clear and distinctive niche (multi-agent Kanban coordination with JSON storage) but suffers from incomplete trigger guidance and some marketing fluff ('Perfect for building AI agent command centers'). It would benefit from an explicit 'Use when...' clause and more concrete action verbs describing specific operations the skill performs.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to coordinate multiple AI agents, manage a task board, assign work to agents, or track agent task progress.'
Replace the marketing phrase 'Perfect for building AI agent command centers' with concrete actions like 'create tasks, assign agents, update task status, poll for task completion, and query board state.'
Include natural trigger terms users might say, such as 'task management', 'assign tasks', 'agent workflow', 'track tasks', or 'task queue'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (AI agent teams, Kanban task board) and some actions (assigning work, executing tasks, heartbeat polling), but mixes in vague marketing language like 'AI agent command centers' and doesn't list concrete operations (e.g., create task, update status, query board). | 2 / 3 |
Completeness | The 'what' is partially covered (Kanban task board with JSON storage, multi-agent workflows), but there is no explicit 'Use when...' clause or equivalent trigger guidance. The phrase 'Perfect for building AI agent command centers' is marketing fluff rather than actionable trigger guidance. | 2 / 3 |
Trigger Term Quality | Includes some relevant terms like 'Kanban', 'task board', 'multi-agent', 'JSON storage', 'Team Lead', 'Worker Agents', but these are fairly specialized. Missing common user phrases like 'task management', 'assign tasks', 'track progress', or 'agent coordination'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of Kanban task board, multi-agent workflows, heartbeat polling, and local JSON storage creates a very specific niche that is unlikely to conflict with other skills. This is a clearly distinct domain. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill excels at actionability with fully executable curl commands and concrete setup steps, but suffers significantly from verbosity and lack of progressive disclosure. The same API endpoints are documented 3-4 times across different sections, and the entire content could be reduced by 50%+ by eliminating redundancy and splitting detailed references into separate files. Missing validation/error-handling checkpoints weaken the workflow clarity for what is a complex multi-agent setup.
Suggestions
Eliminate redundant API documentation: keep the API reference table and the example workflow, but remove the separate 'Team Lead Operations' and 'Worker Agent Operations' sections that duplicate the same curl commands.
Split into multiple files: move the API reference table to API.md, the full agent config example to CONFIG.md, and the heartbeat template to HEARTBEAT_TEMPLATE.md, with brief references from the main skill.
Add validation checkpoints: after 'npm run dev' verify the server is running (e.g., curl health check), after seed verify agents were created (curl /api/agents), and note expected error responses for common failures.
Trim the agent config example to 2 agents (lead + one worker) instead of 6 — Claude can extrapolate the pattern.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~300+ lines. It repeats API endpoints multiple times (heartbeat section, team lead operations, worker agent operations, API reference table, and example workflow all show the same curl commands). The agent config example is unnecessarily long with 6 agents when 2 would suffice. The recommended team structure table duplicates information already in the config example. | 1 / 3 |
Actionability | Every operation has fully executable curl commands with proper headers, JSON bodies, and endpoint URLs. The setup instructions include concrete bash commands for installation, directory creation, and seeding. Code examples are copy-paste ready. | 3 / 3 |
Workflow Clarity | The task lifecycle diagram is clear and the example workflow shows a good end-to-end sequence. However, there are no validation checkpoints — no guidance on what to do if the server fails to start, if seed fails, if a task pick returns an error, or how to verify the system is working correctly before proceeding. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no references to external files despite being well over 300 lines. The API reference table, full config examples, agent team structure, and detailed heartbeat setup could all be split into separate referenced files. No bundle files exist to support progressive disclosure. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- NeverSight/skills_feed
- Commit
d00f12f
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.