CtrlK
BlogDocsLog inGet started
Tessl Logo

cancel

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

64

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./plugins/oh-my-codex/skills/cancel/SKILL.md

The canonical home for this skill is cancel in Yeachan-Heo/oh-my-codex

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 an exemplary lean operational procedure: validation-first argument handling, explicit dependency-ordered cancellation steps, concrete state-API commands with JSON examples, and a defined evidence report. The only meaningful gap is the absence of a re-verify/retry loop after cleanup and the vague pointer for `--force` cleanup details.

DimensionReasoningScore

Conciseness

The body is dense and imperative with zero padding — e.g. "Reject `--all`, unknown flags, repeated flags, and mixed flags before mutation" and "Clear standalone modes only after proving they are not linked" — explaining nothing Claude already knows and making every token earn its place.

5 / 5

Actionability

Concrete executable commands appear throughout (`omx state list-active --json`, `omx state clear --input '{"mode":...}' --json`, `omx team shutdown <team>`), with minor gaps: the `--force` path delegates to unspecified "documented native-stop cleanup" without naming where that documentation lives.

4 / 5

Workflow Clarity

The sequence is dependency-ordered with explicit validation gates (reject invalid flags before mutation, confirm session/root before cleanup, prove standalone modes are not linked, confirm post-conditions, report rollback failures). It falls short of 5 only because there is no fix-and-retry feedback loop after a failed clear or rollback.

4 / 5

Progressive Disclosure

At ~40 lines with clean, well-organized sections, the body keeps only overview-level content inline and clearly signals its two one-level-deep references (`AGENTS.md#durable-runtime-invariants-canonical-ssot` and `docs/contracts/ralph-cancel-contract.md`); no bundle files exist, so nothing is inlined that belongs elsewhere.

5 / 5

Total

18

/

20

Passed

Description

65%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 distinctive and uses precise domain terminology with an exhaustive enumeration of target modes, but it states only a single action and entirely lacks a "Use when..." trigger clause. Adding explicit trigger guidance and a few natural synonyms (stop, abort) would lift it substantially.

Suggestions

Add a "Use when..." clause, e.g. "Use when an OMX mode is active and the user says cancel, stop, abort, or exit, or invokes /cancel, cancelomc, or stopomc."

Mention the cleanup action the skill actually performs, e.g. "Cancel any active OMX mode (...) and perform its documented cleanup, preserving resumable state where defined" — this adds a second concrete capability.

Include natural synonyms ("stop", "abort", "exit", "kill") alongside "Cancel" so the description matches the varied phrasings users actually say.

DimensionReasoningScore

Specificity

"Cancel any active OMX mode" names one concrete action and comprehensively enumerates the nine target modes, but only a single action verb is given with no mention of the cleanup or stop semantics the body performs — matching the anchor for 1-2 concrete actions without full coverage of what the skill does.

3 / 5

Completeness

The "what" is clear (cancel an active OMX mode), but there is no "Use when..." clause or equivalent; the "when" is only weakly implied by the word "active", which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

The mode names (autopilot, ralph, ultrawork, ecomode, ultraqa, swarm, ultrapilot, pipeline, team) are exactly the terms a user would naturally say to invoke this skill, but common synonyms such as "stop", "abort", "exit", or "kill" are missing.

4 / 5

Distinctiveness Conflict Risk

It occupies a clear niche (OMX modes) with distinct named triggers enumerated explicitly, so the risk of it firing for the wrong skill is minimal; it is clearly distinguishable from generic cancel/stop skills.

5 / 5

Total

15

/

20

Passed

Validation

100%

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
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.