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.
74
60%
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 establishes a clear and distinctive niche around multi-agent Kanban coordination with JSON storage, which is its strongest aspect. However, it lacks an explicit 'Use when...' clause, relies on some promotional language ('Perfect for building AI agent command centers'), and could be more specific about the concrete operations it supports.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to coordinate multiple AI agents, manage a Kanban task board, or set up agent team workflows with task assignment and polling.'
Replace the promotional phrase 'Perfect for building AI agent command centers' with concrete actions like 'create/assign/complete tasks, check agent heartbeats, query board status'.
Include natural trigger terms users might say, such as 'task management', 'agent orchestration', 'assign tasks to agents', or 'track agent work'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (AI agent teams, Kanban task board) and some actions (assigning work, executing tasks, heartbeat polling), but the actions are described at a high level rather than listing specific concrete operations like 'create tasks', 'update task status', 'query board state'. | 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' hints at when but is vague and promotional rather than explicit. | 2 / 3 |
Trigger Term Quality | Includes some relevant terms like 'Kanban', 'task board', 'multi-agent', 'Team Lead', 'Worker Agents', but misses common user-facing terms like 'task management', 'workflow orchestration', 'agent coordination', 'JSON task file'. The phrase 'AI agent command centers' is more marketing than a natural trigger term. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of Kanban task board, local JSON storage, multi-agent workflows with Team Lead/Worker Agent roles, and heartbeat polling creates a very distinct niche that is unlikely to conflict with other skills. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is highly actionable with executable curl commands throughout and a clear task lifecycle workflow. However, it is significantly over-verbose — the same API endpoints are documented 3-4 times across different sections, the agent config example is unnecessarily large, and the entire document could be cut by 40-50% without losing information. The monolithic structure would benefit from splitting the API reference and detailed operations into separate files.
Suggestions
Reduce redundancy by removing duplicate API documentation — keep the API reference table and the example workflow, but consolidate the Team Lead Operations and Worker Agent Operations sections into brief references to the table.
Trim the agent config example to 2-3 agents instead of 6; Claude can extrapolate the pattern.
Split the API reference table and detailed operation examples into a separate REFERENCE.md file, keeping only the quick start and task lifecycle in the main SKILL.md.
Remove the 'Recommended Agent Team Structure' table since it duplicates information already in the config example.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~300+ lines. It includes a full agent config example with 6 agents when 2 would suffice, repeats API endpoints in multiple sections (heartbeat, team lead operations, worker operations, API reference table, and example workflow), and includes a recommended team structure table that's redundant with the config example. Much of this could be cut in half. | 1 / 3 |
Actionability | Every operation has fully executable curl commands with proper headers and JSON payloads. The quick start provides a complete clone-install-run sequence, and the example workflow shows a concrete end-to-end multi-agent interaction with real commands. | 3 / 3 |
Workflow Clarity | The task lifecycle is clearly diagrammed (backlog → todo → in_progress → review → done) with explicit transitions. The heartbeat steps are sequenced 1-5, the example workflow shows a complete 5-step flow with Lead and Worker coordination, and the review/approval step serves as a validation checkpoint before marking done. | 3 / 3 |
Progressive Disclosure | The content is a monolithic wall of text with everything inline — the full API reference table, all agent operations, configuration details, and examples could be split into separate reference files. There are no references to external docs beyond the GitHub link, and the API reference table duplicates information already shown in the curl examples above it. | 2 / 3 |
Total | 9 / 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
868a866
- 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.