cancel
Cancel any active OMC mode (autopilot, ralph, ultrawork, ultraqa, swarm, ultrapilot, pipeline, team)
73
67%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/cancel/SKILL.mdQuality
Discovery
72%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description effectively communicates a specific cancellation action with excellent trigger term coverage through the enumerated mode names. Its main weakness is the lack of an explicit 'Use when...' clause, which would help Claude understand the selection criteria more clearly. The description is concise and distinctive but could benefit from briefly explaining what OMC modes are for users unfamiliar with the terminology.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to stop, exit, or cancel any running automation mode.'
Consider adding common synonyms users might say like 'stop', 'exit', 'quit', or 'end' to improve trigger coverage
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names a specific action ('Cancel') and lists multiple mode names, but doesn't explain what cancellation entails or what these modes are. The action is singular rather than multiple concrete capabilities. | 2 / 3 |
Completeness | Clearly states WHAT it does (cancel active OMC modes) but lacks an explicit 'Use when...' clause. The when is implied by the action but not explicitly stated as guidance for Claude's selection. | 2 / 3 |
Trigger Term Quality | Includes excellent natural trigger terms users would say: 'cancel', 'active', and all the specific mode names (autopilot, ralph, ultrawork, ultraqa, swarm, ultrapilot, pipeline, team). Users asking to stop or cancel these modes would naturally use these exact terms. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific mode names that are unlikely to appear in other contexts. The combination of 'cancel' with these unique mode identifiers creates a clear, non-conflicting niche. | 3 / 3 |
Total | 10 / 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.
This skill excels at actionability and workflow clarity with concrete commands, explicit validation steps, and well-defined dependency ordering for complex multi-mode cancellation. However, it suffers from severe verbosity—the content could be reduced by 60-70% without losing essential information. The exhaustive inline listings and repetitive explanations of session-aware state contracts waste significant token budget.
Suggestions
Move the 25+ item legacy compatibility file list to a separate LEGACY-FILES.md reference document
Condense the session-aware state contract explanation—it's repeated in sections 2, 3A, 3B, and Implementation Notes
Extract the detailed Team two-pass cancellation protocol to a TEAM-CANCEL.md file, keeping only a summary in the main skill
Remove redundant explanations like 'The cancel skill runs as follows' which restates what was already covered in Implementation Steps
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~350 lines with extensive repetition of state management concepts, exhaustive file path listings, and detailed implementation steps that could be dramatically condensed. The legacy compatibility list alone is 25+ items that could be a reference link. | 1 / 3 |
Actionability | Provides concrete, executable bash commands, specific file paths, exact MCP tool calls (state_read, state_clear, state_list_active), and copy-paste ready code snippets for argument parsing and cleanup operations. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflows with explicit validation checkpoints, dependency ordering (autopilot → ralph → ultrawork), two-pass team cancellation protocol with timeouts, and clear feedback loops for error recovery including orphan detection. | 3 / 3 |
Progressive Disclosure | Content is reasonably structured with clear sections, but everything is inline in one massive file. The legacy compatibility list, MCP worker cleanup details, and team protocol specifics could be split into reference files. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- Yeachan-Heo/oh-my-claudecode
- Commit
48ffaac
- 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.