unstuck

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

Quality

63%

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 ./skills/unstuck/SKILL.md

Quality

Content

73%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 a well-sequenced, highly actionable operational guide with strong validation checkpoints and feedback loops, undermined only by repeated rationale and some over-explanation that could be tightened.

Suggestions

Consolidate the routing-contract / separator-collision rationale, which is currently restated three times across Step 3, Step 4, and 'When MCP is unavailable'.

Add one literal copy-paste MCP invocation example showing the full argument object for both solo and debate modes.

Trim the base64-alphabet explanation; Claude already knows base64 cannot emit '-->', so a one-line note suffices.

Dimension	Reasoning	Score
Conciseness	The body is dense and operational but restates the routing-contract/separator-collision rationale multiple times and explains the base64 alphabet, so it is mostly efficient yet could be tightened, fitting anchor 3.	3 / 5
Actionability	Provides concrete arg-parsing tables, exact MCP tool and parameter names, file:line references, the exact sentinel format, and per-runtime dispatch commands, but describes the MCP call structurally rather than as a copy-paste invocation, matching anchor 4.	4 / 5
Workflow Clarity	Clear four-step sequence with explicit validation gates (both context fields required before proceeding, invalid-args rejection, MCP-unavailable halt) and a conditional Round-2 feedback loop, matching anchor 5.	5 / 5
Progressive Disclosure	Single self-contained file with no bundle directories, but well-organized through headers and tables that provide clear navigation; minor inline material (runtime-dispatch prose, RFC footer) could be split out, fitting anchor 4.	4 / 5
	Total	16 / 20 Passed

Description

53%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 conveys a clear, distinctive what but omits explicit when/trigger guidance, which caps completeness. Trigger-term coverage is thin relative to the natural phrases users would actually say.

Suggestions

Add an explicit 'Use when...' clause with concrete trigger phrases (e.g., 'Use when you are stuck, need to reframe a problem, or want a multi-persona debate').

Expand trigger terms to include natural user phrases like 'I'm stuck', 'think sideways', or 'reframe the problem', not just 'stagnation' and 'lateral thinking'.

Optionally list 2-3 concrete actions (reframe solo, run a parallel debate, synthesize options) to lift specificity from anchor 3 toward 4.

Dimension	Reasoning	Score
Specificity	Names the domain ('lateral thinking personas') and two modes ('single or multi-persona debate'), but lists only 1-2 concrete actions and is not comprehensive, matching anchor 3.	3 / 5
Completeness	Provides a clear 'what' (break stagnation with lateral thinking personas, single or multi-persona debate) but no 'Use when...' clause, capping completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Contains 'stagnation' and 'lateral thinking' but is missing common natural variations and synonyms a user would say, so it sits at anchor 3 rather than the broader coverage of anchor 4.	3 / 5
Distinctiveness Conflict Risk	The 'lateral thinking personas / debate' niche is mostly distinct with only minor overlap risk against other brainstorming-style skills, fitting anchor 4 better than the fully distinct anchor 5.	4 / 5
	Total	13 / 20 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: skills/unstuck/SKILL.md
Commit: 80333ae

Reviewed: 3 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.