CtrlK
BlogDocsLog inGet started
Tessl Logo

cancel-ralph

Cancel an active Ralph Loop. Use when the user wants to stop, cancel, or abort a running ralph loop.

68

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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.

Lean, fully executable, and well-organized for a simple single-purpose skill. The one substantive gap is the missing validation around the destructive rm -rf, which both risks unreportable failures and runs before the iteration value is confirmed usable.

Suggestions

Add a pre-deletion validation step: verify the iteration value was successfully parsed from the scratchpad (e.g., grep the 'iteration:' field and fail gracefully if absent) before running rm -rf.

Narrow the destructive scope or verify it after: rm -rf .cursor/ralph removes the entire directory including the scratchpad being reported from — confirm the directory no longer exists after removal, and note explicitly that the iteration must be captured before deletion.

Include a safety check that the working directory is the project root (or that .cursor/ralph is a relative path) so the rm -rf cannot target an unexpected location.

DimensionReasoningScore

Conciseness

The ~20-line body explains nothing Claude already knows and pads nothing; every section (Trigger, Workflow, Output) carries its weight with exact paths, commands, and report strings.

5 / 5

Actionability

Fully executable guidance: a specific state path (.cursor/ralph/scratchpad.md), a named field to read (iteration:), a copy-paste command (rm -rf .cursor/ralph), and verbatim user-facing messages.

5 / 5

Workflow Clarity

The sequence and if/else branch are clear, but the destructive rm -rf runs with no validation checkpoint — no check that the iteration parsed before deleting, no confirmation before wiping the directory, and no post-removal verification — so the destructive-operation cap applies.

3 / 5

Progressive Disclosure

Under 50 lines, no external references needed, and well-organized into clearly labeled sections; per the simple-skill guidance this earns full marks on section organization alone.

5 / 5

Total

18

/

20

Passed

Description

78%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.

A strong description with explicit what-and-when structure and natural trigger synonyms. Its only real limitation is thinness of the 'what' — a single action with no elaboration of scope.

DimensionReasoningScore

Specificity

Names the domain ('active Ralph Loop') and one concrete action ('Cancel'), but lists only that single action rather than several specific capabilities, matching the 1-2-concrete-actions anchor.

3 / 5

Completeness

Explicitly answers both 'what' ('Cancel an active Ralph Loop') and 'when' ('Use when the user wants to stop, cancel, or abort a running ralph loop') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes three natural synonyms ('stop, cancel, or abort') plus the domain noun 'ralph loop', giving good keyword coverage, though common variations like 'end', 'kill', or 'quit' are missing.

4 / 5

Distinctiveness Conflict Risk

'Ralph loop' is a distinct niche, but the generic verbs stop/cancel/abort applied to 'a running loop' create minor overlap risk with generic loop- or task-management skills.

4 / 5

Total

16

/

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
cursor/plugins
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.