cancel

Cancel any active OMC mode (autopilot, ralph, ultrawork, ultraqa, ultragoal, swarm, ultrapilot, pipeline, team)

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/cancel/SKILL.md

Quality

Content

63%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with concrete tool calls, executable fallback code, and explicit validation checkpoints for destructive state changes, but it suffers from redundant restating of the dependency cascade and is a monolithic file that under-uses progressive disclosure.

Suggestions

Consolidate the repeated autopilot→ralph→ultrawork dependency cascade into one authoritative section and reference it elsewhere instead of restating.

Move the long bash fallback, the legacy compatibility file list, and the team two-pass protocol into reference files (e.g., references/fallback.sh, references/legacy-state.md) and link to them from SKILL.md.

Reconcile the mode list between "Auto-Detection" (12 modes) and the "Implementation Steps" handlers so the workflow covers every enumerated mode consistently.

Dimension	Reasoning	Score
Conciseness	The body is substantive and free of basic-concept padding, but the autopilot→ralph→ultrawork dependency cascade and cleanup logic are restated across "What It Does", "Auto-Detection", "Implementation Steps", and "Implementation Notes", so it could be noticeably tightened.	3 / 5
Actionability	Concrete, executable guidance dominates — exact ToolSearch query, state_clear/state_read calls with arguments, and a copy-paste bash fallback — but the team two-pass protocol is pseudocode-style and the fallback's MODE placeholder must be hand-edited.	4 / 5
Workflow Clarity	Destructive state mutation is guarded by explicit validation ("If this write fails, stop immediately", "require success", report failures) and feedback loops, but inconsistent mode lists (12 modes in Auto-Detection vs. fewer handled in Implementation Steps) create minor gaps.	4 / 5
Progressive Disclosure	Section headers give reasonable structure, but this ~390-line skill is monolithic with no detail-file references; the bash fallback, legacy compatibility list, and team protocol are inlined content that could live in separate files.	3 / 5
	Total	14 / 20 Passed

Description

66%Weight 40%Scale 1-5

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 is concrete and distinct, naming a clear niche and nine specific target modes, but it omits any explicit "Use when..." trigger guidance and lacks synonyms for "cancel", which cap completeness and trigger-term quality.

Suggestions

Add a "Use when ..." clause stating when Claude should invoke this skill (e.g., when an OMC mode is active and needs to be stopped).

Include natural synonyms such as "stop" or "exit" alongside "cancel" to improve trigger-term coverage.

Mention the --force/--all reset behavior briefly so the description signals full capability scope.

Dimension	Reasoning	Score
Specificity	The single concrete action "Cancel" is applied comprehensively to nine enumerated modes (autopilot, ralph, ultrawork, ...), giving specific concrete targets, but only one verb keeps it short of the multiple-action anchor 5.	4 / 5
Completeness	The "what" is clear ("Cancel any active OMC mode (...)") but there is no "Use when..." trigger clause, so per the rubric guideline completeness is capped at 3.	3 / 5
Trigger Term Quality	"Cancel" plus the nine mode names are natural terms a user running OMC would say, but synonyms such as stop/exit/abort are absent, so coverage is good rather than comprehensive.	4 / 5
Distinctiveness Conflict Risk	The OMC-mode framing and enumerated mode list carve a clear niche with minimal conflict risk, though there is minor overlap potential with related OMC lifecycle skills (resume/stop/exit).	4 / 5
	Total	15 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Yeachan-Heo/oh-my-claudecode
Path: skills/cancel/SKILL.md
Commit: 5aa678c

Reviewed: 8 days ago

Table of Contents

Discovery Implementation Validation

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.