unstuck

Break through stagnation with lateral thinking personas — single or multi-persona debate

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.claude-plugin/skills/unstuck/SKILL.md

Quality

Content

77%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a clear, well-validated workflow, but it is a long monolithic document that could be tightened and could split its runtime-dispatch detail into a one-level-deep reference file.

Suggestions

Move the runtime-dispatch detail (Shape A/B and the inline-dispatch-block mechanics) into a separate reference file referenced one level deep from SKILL.md to improve progressive disclosure.

Trim the base64-alphabet and 'bot review' rationale and consolidate repeated 'fail loud, don't substitute' statements to reduce token cost.

Drop precise source line-number citations (e.g., 'evaluation_handlers.py:1324, 1333') that will rot and add little actionable value for the agent.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and task-relevant, but it is padded with internal line-number citations and over-explanation (e.g., the base64-alphabet rationale and repeated 'bot review' emphasis) that could be tightened without losing clarity.	2 / 3
Actionability	It gives the exact MCP tool name, tool-discovery query, per-mode arguments, dispatch-block format and extraction procedure, per-runtime Task/delegation patterns, and a copy-paste synthesis template — fully executable guidance.	3 / 3
Workflow Clarity	The four-step process (parse args → gather context → call MCP → branch on response) is clearly sequenced with explicit validation gates (proceed only when both context fields are populated) and error-recovery fallbacks for each response shape.	3 / 3
Progressive Disclosure	It is a single ~270-line file with no bundle/reference files, and the detailed runtime-dispatch mechanics (Shape A/B, inline dispatch block) that could be split out are all inline, so structure is present but content that should be separate is not.	2 / 3
	Total	10 / 12 Passed

Description

57%Weight 40%Scale 1-3

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 names its mechanism, but it lacks an explicit 'Use when' clause and the most natural user trigger ('I'm stuck'), which keeps specificity, trigger quality, and completeness at the mid level.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when the user says they are stuck, want to think sideways, or needs a multi-perspective reframing of a problem').

Surface the natural trigger phrase 'I'm stuck' / 'stuck' inside the description rather than only in the body.

Replace the outcome phrasing 'Break through stagnation' with a concrete action verb (e.g., 'Reframes stuck problems via lateral thinking personas') to lift specificity.

Dimension	Reasoning	Score
Specificity	Names the domain ('lateral thinking personas') and two modes ('single or multi-persona debate'), but 'Break through stagnation' describes an outcome rather than listing multiple concrete actions, so it is not comprehensive.	2 / 3
Completeness	It states what the skill does but has no explicit 'Use when...' trigger clause, so per the rubric the 'when' is only implied and completeness is capped at 2.	2 / 3
Trigger Term Quality	'stagnation' and 'lateral thinking' are somewhat natural, but the most common user phrase ('I'm stuck') appears only in the body, not the description, so common variations are missing.	2 / 3
Distinctiveness Conflict Risk	'lateral thinking personas — single or multi-persona debate' carves a clear niche with distinct triggers and is unlikely to fire for the wrong skill.	3 / 3
	Total	9 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Q00/ouroboros
Path: .claude-plugin/skills/unstuck/SKILL.md
Commit: f09fa36

Reviewed: 7 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.