cancel

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

Quality

60%

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 ./plugins/oh-my-codex/skills/cancel/SKILL.md

Quality

Content

50%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 actionable with concrete executable bash for each mode and validation-aware destructive-operation handling, but it suffers from verbosity, duplicated sections, and structural inconsistencies that hurt conciseness and workflow clarity. Progressive disclosure is limited because most detailed material is inlined in a single large file.

Suggestions

Merge or remove the duplicated "Normative Ralph post-conditions" sections and fix the broken list numbering (1, 2, 4) and the orphaned "3B" subsection heading.

Move the per-mode bash implementations and the dense normative/scope-safety contract text into separate referenced files (e.g., references/mode-cancellation.md, references/scope-safety-contract.md) and keep SKILL.md as an overview with one-level-deep links.

Resolve the contradiction between the rm-based code blocks (which silently remove ralph-state.json) and the "MUST not silently removed / current_phase='cancelled'" post-condition by aligning the code with the stated terminalization requirement.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose, including two near-duplicate "Normative Ralph post-conditions (MUST)" sections (lines 45-56 and 70-77) and dense legalistic scope-safety prose (e.g., the NODE_EXTRA_CA_CERTS exemption paragraph) that could be trimmed.	2 / 5
Actionability	Provides concrete, executable bash blocks per mode with real jq commands, file paths, and tmux commands, plus a step-by-step team shutdown sequence; minor gaps remain in some standalone cases.	4 / 5
Workflow Clarity	Sequences and validation checkpoints (fail-before-mutation, fail-closed, revalidation) are present, but broken list numbering (1, 2, 4), a "3B" subsection with no 3A, duplicated Ralph sections, and a contradiction between the rm-based code blocks and the "MUST not silently removed" post-condition weaken clarity.	3 / 5
Progressive Disclosure	Section headers and tables provide some structure, but at ~340 lines the simple-skill exception does not apply and per-mode bash implementations plus normative contract text are inlined rather than split into referenced files; the one external reference (docs/contracts/ralph-cancel-contract.md) is signaled but not a bundle file.	3 / 5
	Total	12 / 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 specific and distinct, clearly naming the action and the OMX modes it targets, but it omits an explicit "Use when..." trigger clause, which limits its completeness. Trigger keyword coverage is good though missing a few natural synonyms.

Suggestions

Add a "Use when..." clause naming the situations that should trigger this skill (e.g., "Use when the user wants to stop or exit an active OMX mode").

Include common synonyms such as "stop" or "exit" alongside "cancel" to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	States the concrete action "Cancel any active OMX mode" and enumerates 9 named mode targets (autopilot, ralph, ultrawork, ecomode, ultraqa, swarm, ultrapilot, pipeline, team), giving several specific targets though it is essentially one action applied to a list.	4 / 5
Completeness	The "what" is clear (cancel any active OMX mode), but there is no "Use when..." clause or equivalent explicit trigger guidance, so completeness is capped at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	The named modes (autopilot, ralph, ultrawork, etc.) are natural terms a user would say, giving good keyword coverage, but common synonyms like "stop" or "exit" are absent.	4 / 5
Distinctiveness Conflict Risk	A clear niche (cancelling OMX modes) with distinctly named triggers and minimal overlap risk with other skills.	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: plugins/oh-my-codex/skills/cancel/SKILL.md
Commit: e94437f

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.