cancel-ralph

Codex-compatible cancel command for Ralph loop state, preserving the original command name.

Quality

68%

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 ./bundled/skills/cancel-ralph/SKILL.md

Quality

Content

87%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 concise, actionable, and well-structured for a simple single-purpose skill, with a verified bundle script. Its only weakness is workflow clarity: the destructive cancellation lacks an explicit validation or confirmation checkpoint, which the rubric caps at 3.

Suggestions

Add an explicit validation/confirmation step before removal (e.g., confirm the active state file exists and print its iteration before deleting it).

Include a short feedback loop (check state -> remove -> re-verify removal succeeded) to satisfy the destructive-operation feedback-loop requirement.

Optionally surface a dry-run or no-op confirmation when no state exists to make the safety boundary explicit.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-sectioned with no padding or explanation of concepts Claude already knows; every line (script path, usage, behavior) earns its place, matching the lean-and-efficient anchor.	5 / 5
Actionability	Provides a fully executable, copy-paste-ready PowerShell invocation resolving the script path from $CODEX_HOME, and the referenced scripts/cancel-ralph.ps1 bundle exists, matching the fully-executable anchor.	5 / 5
Workflow Clarity	Behavior is listed (no-state vs active-state outcomes) but this destructive operation (removing loop state) has no explicit validation/confirmation checkpoint before removal, which the rubric caps at 3 for destructive skills missing feedback loops.	3 / 5
Progressive Disclosure	Under 50 lines, single-purpose, with a real bundled script correctly referenced via a well-organized set of sections and no nested references, qualifying for the simple-skill 5 under the scoring notes.	5 / 5
	Total	18 / 20 Passed

Description

48%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 to a niche domain and mostly distinct from other skills, but it states only a minimal action and omits any explicit "Use when" trigger guidance, capping completeness. Adding a concrete trigger clause and a second action detail would lift specificity and completeness.

Suggestions

Add an explicit "Use when..." trigger clause (e.g., "Use when canceling an active Ralph compat loop") to satisfy the completeness requirement.

Name a second concrete action or outcome (e.g., "removes the local compat loop state and reports the current iteration") to raise specificity above 2.

Include natural user-facing synonyms such as "stop", "abort", or "ralph-loop" to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ("cancel command for Ralph loop state") but offers only one minimal action with no concrete detail on what cancellation entails, matching the anchor for naming the domain with minimal/generic actions rather than the 1-2 concrete actions needed for a 3.	2 / 5
Completeness	Provides a clear "what" (cancel command for Ralph loop state) but no explicit "Use when..." trigger guidance, which the rubric caps at 3 for missing trigger clauses.	3 / 5
Trigger Term Quality	Includes relevant keywords like "cancel command" and "Ralph loop state" but lacks common natural variations or synonyms a user might actually say, fitting the anchor for some relevant keywords missing common variations.	3 / 5
Distinctiveness Conflict Risk	The "Ralph loop state" niche is specific and mostly distinct with only minor overlap risk against closely related loop-management skills, matching the mostly-distinct anchor.	4 / 5
	Total	12 / 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: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/cancel-ralph/SKILL.md
Commit: d5ae560

Reviewed: 1 day 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.