cancel

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

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

65%

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, executable commands and a clear dependency-ordered workflow, but it suffers from internal repetition, missing verification feedback loops around destructive cleanup, and a lack of progressive disclosure for a 370+ line skill.

Suggestions

Add explicit post-clear verification checkpoints for destructive operations (e.g., re-read state after state_clear and retry/escalate on failure) to lift workflow clarity.

Move the long bash fallback and the legacy compatibility file list into a separate reference file (e.g., references/fallback.md) and link to it from the body to improve progressive disclosure.

De-duplicate the dependency-order mode list and the Team-handling steps, which currently appear in both the overview and the Implementation Steps sections.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient operational detail (no padding with concepts Claude already knows), but it repeats material — the dependency-ordered mode list appears in both 'Auto-Detection' and 'Implementation Steps', and Team handling is described twice — and the inline bash fallback with an embedded Python heredoc is heavy, so it could be tightened.	2 / 3
Actionability	The body provides fully executable, copy-paste-ready guidance: a concrete ToolSearch query, a worked-out bash fallback with real state paths, specific state_clear/state_read calls with parameters, and tmux kill-session commands, with placeholders like MODE and {team_name} explicitly flagged.	3 / 3
Workflow Clarity	A clear dependency-ordered cancellation sequence and per-mode subsections are present, but destructive operations (rm -rf .omc/state/team-bridge/, tmux kill-session, state clearing) lack explicit post-clear verification or feedback loops, which the rubric caps at 2 for destructive/batch workflows.	2 / 3
Progressive Disclosure	The body is well-organized into sections and tables rather than an unstructured wall, but at ~374 lines it keeps long inline content (the bash fallback, the legacy compatibility file list, the team two-pass protocol) that should be split into reference files, and no bundle references exist to provide one-level-deep navigation.	2 / 3
	Total	9 / 12 Passed

Description

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 is concise and distinctive within its OMC niche, clearly stating what it does, but it omits explicit 'Use when...' trigger guidance and natural term variations like 'stop'. It is solid but lacks the trigger completeness needed for a top score.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when the user says cancel, stop, or wants to exit an active OMC mode like autopilot or ralph.'

Include common natural variations ('stop', 'stopomc', 'exit mode') in the description so trigger-term coverage reaches users' actual phrasing.

Optionally mention the graceful-vs-force distinction at a high level to give the description a second concrete action beyond 'cancel'.

Dimension	Reasoning	Score
Specificity	The phrase 'Cancel any active OMC mode' names the domain and one concrete action applied to an enumerated mode list (autopilot, ralph, ultrawork, ...), but it lists only a single action type rather than multiple distinct concrete actions. It is more specific than a vague anchor like 'Helps with documents', but falls short of listing multiple concrete actions.	2 / 3
Completeness	The description clearly answers 'what' (cancel any active OMC mode) but contains no 'Use when...' clause or equivalent explicit trigger guidance, which the rubric caps at 2 for completeness.	2 / 3
Trigger Term Quality	'cancel' is a natural keyword a user would say, and the mode names are relevant to the domain, but common variations such as 'stop' (which the body uses via 'stopomc') are absent from the description itself, leaving coverage incomplete.	2 / 3
Distinctiveness Conflict Risk	The phrase 'Cancel any active OMC mode' with a specific enumerated OMC-mode list carves out a clear, OMC-scoped niche with distinct triggers that is unlikely to fire for unrelated skills.	3 / 3
	Total	9 / 12 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
Commit: 6c59219

Reviewed: about 7 hours 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.