cancel

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

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

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

Quality

Content

75%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 body is a tight, well-sequenced, destructive-operation workflow with concrete commands and solid validation checkpoints. Its main gaps are conceptual mid-process steps lacking exact commands and the absence of an explicit error-recovery retry loop.

Suggestions

Give exact commands for the conceptual steps (e.g. how to "terminalize" Ralph state and "prove" a mode is not linked) so every step is executable.

Add an explicit validate-then-retry feedback loop for cleanup failures rather than only reporting them, to reach the anchor-5 workflow_clarity bar.

Collect the external references (AGENTS.md, docs/contracts/ralph-cancel-contract.md) into a short dedicated references section for clearer navigation.

Dimension	Reasoning	Score
Conciseness	The body is dense operational guidance with executable commands and no padding of concepts Claude already knows; only minor explanatory clauses like "it is the invariant authority for scope, ownership, hooks, and Team cleanup" could be trimmed, matching anchor 4 rather than the fully lean anchor 5.	4 / 5
Actionability	Concrete executable commands are provided ("omx state list-active --json", "omx state clear --input '{...}' --json", "omx team shutdown <team>"), but steps 3-5 describe behavior conceptually ("terminalize the target state", "Clear standalone modes only after proving...") without exact commands, fitting anchor 4's "minor gaps".	4 / 5
Workflow Clarity	A clearly numbered sequence with explicit validation checkpoints (reject flags before mutation, confirm target before cleanup, prove modes are not linked, confirm post-conditions) is present, so the destructive-cap does not apply; however error handling is "Report rollback or cleanup failures" rather than an explicit re-validate retry loop, matching anchor 4 over anchor 5.	4 / 5
Progressive Disclosure	The skill is under 50 lines with well-organized sections (When to use, Inputs and preconditions, Operational steps, Exit and evidence) and one-level-deep external references ("AGENTS.md#...", "docs/contracts/ralph-cancel-contract.md"); references are signaled inline rather than in a dedicated navigation section, so it sits at anchor 4 rather than the well-split anchor 5.	4 / 5
	Total	16 / 20 Passed

Description

70%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, distinct, and richly enumerates its targets, but it omits an explicit "Use when..." trigger clause, which caps its completeness. Adding a brief usage trigger would lift the weakest dimension.

Suggestions

Add an explicit "Use when..." clause, e.g. "Use when an OMX mode is active and the user wants to stop it and run its cleanup." to raise completeness.

Include natural synonyms such as "stop" or "abort" in the description so trigger term coverage reaches common user phrasings.

Dimension	Reasoning	Score
Specificity	Quotes "Cancel any active OMX mode" with a comprehensive enumeration of nine specific modes (autopilot, ralph, ultrawork, ecomode, ultraqa, swarm, ultrapilot, pipeline, team); concrete and comprehensive in targets, though only a single action verb, so it sits below the multi-action anchor 5.	4 / 5
Completeness	It gives a clear "what" ("Cancel any active OMX mode...") but has no "Use when..." clause; the "when" is only weakly implied, and the rubric caps completeness at 3 for missing explicit trigger guidance.	3 / 5
Trigger Term Quality	"Cancel" and each named mode are natural terms a user would say (e.g. "cancel autopilot"), but common synonyms like "stop"/"abort" that appear in the body are absent from the description, matching anchor 4 rather than the comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	The OMX-mode-cancellation niche with nine distinct named mode triggers is clearly distinguishable and unlikely to fire for the wrong skill, matching the clear-niche anchor 5.	5 / 5
	Total	16 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Yeachan-Heo/oh-my-codex
Path: skills/cancel/SKILL.md
Commit: 304fb3b

Reviewed: 4 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.