idea-refine

Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on "ideate", "refine this idea", or "stress-test my plan".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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

A well-structured, highly actionable ideation skill with clear phased sequencing and a verification checklist. Its two weaknesses are token redundancy across overlapping summary/anti-pattern/red-flag sections and three broken references to bundle files that do not exist.

Suggestions

Either add the missing referenced files (frameworks.md, refinement-criteria.md, examples.md) or remove the 'Read ... in this skill directory' lines — currently the body points to three files absent from the bundle, which breaks progressive-disclosure navigation.

Consolidate the redundant sections: the 'How It Works'/'Usage'/'Output' summary at the top restates the 'Detailed Instructions'/'Process' detail, and 'Anti-patterns to Avoid' overlaps 'Red Flags' — merge these to tighten the body.

Trim the Philosophy aphorisms ('Show people the future...', 'The parts you can't see...') and the Tone section, which read as flavor rather than actionable guidance.

Dimension	Reasoning	Score
Conciseness	The body is mostly substantive guidance without explaining basic concepts, but it carries real redundancy: the top 'How It Works'/'Usage'/'Output' sections restate the 'Detailed Instructions'/'Process' content, the 'Anti-patterns to Avoid' and 'Red Flags' sections overlap heavily, and the Philosophy aphorisms plus Tone section are flavor that could be tightened.	2 / 3
Actionability	Guidance is concrete and copy-paste ready: "Ask 3-5 sharpening questions", seven named ideation lenses, three named evaluation criteria, and a complete markdown output template with exact section structure — for an instruction-only skill this is specific, actionable guidance.	3 / 3
Workflow Clarity	Three phases are explicitly sequenced with a checkpoint ("Do NOT proceed until you understand who this is for and what success looks like"), a feedback transition ("After the user reacts to Phase 1... shift to convergent mode"), and a closing Verification checklist, matching clear sequencing with explicit checkpoints.	3 / 3
Progressive Disclosure	References are one-level-deep and clearly signaled ("Read frameworks.md", "Read refinement-criteria.md", "Read examples.md in this skill directory"), but none of these files exist in the bundle — only scripts/idea-refine.sh is present — so the signaled navigation leads nowhere, falling short of the 'easy navigation' anchor.	2 / 3
	Total	10 / 12 Passed

Description

92%

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: third-person voice, concrete actions, explicit 'Use when' guidance, and natural trigger phrases covering both what and when. Its only weakness is moderate overlap risk with generic planning/strategy skills on the broader triggers.

Dimension	Reasoning	Score
Specificity	"Refines raw ideas into sharp, actionable concepts" and the embedded actions (stress-test assumptions, expand options, converge) name multiple concrete operations in the ideation domain, matching the anchor for listing several specific actions rather than the score-2 'names domain and some actions'.	3 / 3
Completeness	It states what the skill does ("Refines raw ideas...") and explicitly when to use it ("Use when an idea is still vague... or when you want to expand options before converging on one"), so both 'what' and 'when' are clearly answered with explicit triggers.	3 / 3
Trigger Term Quality	"Triggers on 'ideate', 'refine this idea', or 'stress-test my plan'" are natural phrases a user would actually say, giving good coverage of common variations rather than the sparse score-2 set.	3 / 3
Distinctiveness Conflict Risk	The ideation niche is reasonably distinct, but triggers like "stress-test my plan" and "refine this idea" could plausibly fire for general planning or strategy skills, so it could still overlap with similar skills rather than sitting in an unambiguous niche.	2 / 3
	Total	11 / 12 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: addyosmani/agent-skills
Commit: 70b7506

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.