idea-lineage

Trace one idea's evolution through the brain: first mention, best articulation, related concepts, reversals, contradictions, abandoned branches, and the current live version. Use for single-idea conceptual lineage, not broad concept-map synthesis or structured entity metrics.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

81%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.

A well-structured, highly actionable instruction skill with an unambiguous phased workflow, concrete output contract, and explicit error handling. Its main weakness is redundancy: boundary statements against concept-synthesis and find_trajectory are repeated across five to six sections, and the tool inventory is stated twice.

Suggestions

Consolidate the concept-synthesis and find_trajectory boundary statements, currently spread across 'What this solves', 'What this is not', 'Contract', Phase 5, 'Anti-Patterns', and 'Related Skills', into a single boundary section and reference it from the phases.

Drop the 'Tools Used' section, which duplicates the frontmatter tools list, or fold each tool's one-line purpose into the phase step where it is first invoked.

Trim the four-paragraph 'What this solves' motivation down to one sentence plus the canonical example prompts, which already convey the use cases.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence and avoids explaining known concepts, but the concept-synthesis boundary is restated six times ('What this solves', 'What this is not', 'Contract', Phase 5, 'Anti-Patterns', 'Related Skills') and the find_trajectory disclaimer appears five times, plus a 'Tools Used' section that duplicates the frontmatter tool list. This matches 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than the minor-trims anchor at 4.	3 / 5
Actionability	Every phase names exact tools to run ('Search for exact phrase variants with `search`', 'Takes via `takes_search`'), the output template is copy-paste ready with citation slots, and error handling is concrete ('`get_page` returns `page_not_found` for a concept stub: resolve the slug by title search'). For an instruction-only skill this is fully executable guidance covering the common cases.	5 / 5
Workflow Clarity	Five clearly sequenced phases with explicit checkpoints: an ambiguity halt ('If multiple distinct ideas share the same phrase, ask the user to choose'), gap labeling ('When a bucket has no evidence, write "No clear evidence found"'), a proportionality guard in Phase 4, and error-recovery paths in 'When it fails'. The skill is read-only (mutating: false), so the destructive/batch validation cap does not apply.	5 / 5
Progressive Disclosure	Sections are clearly organized with well-signaled one-level-deep cross-references at the top ('see [conventions/quality.md](../conventions/quality.md)'), and no bundle files exist to split further. However, all content lives inline in a 200+ line body and sibling-skill references like 'skills/concept-synthesis/SKILL.md' are relative paths that do not resolve from this skill's location, leaving minor organization gaps short of the 'easy navigation, appropriately split' anchor.	4 / 5
	Total	17 / 20 Passed

Description

92%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: concrete deliverables, explicit use-for guidance with negative boundaries against neighboring skills, and third-person voice. The only gap is that a few natural user phrasings live in the triggers list rather than the description text itself.

Dimension	Reasoning	Score
Specificity	The description enumerates seven concrete deliverables — 'first mention, best articulation, related concepts, reversals, contradictions, abandoned branches, and the current live version' — in third person ('Trace'), matching the 'multiple specific concrete actions; comprehensive coverage' anchor. It is not 4 because the action list leaves no minor coverage gaps.	5 / 5
Completeness	Both parts are explicit: the 'what' is the enumerated lineage buckets, and the 'when' is 'Use for single-idea conceptual lineage, not broad concept-map synthesis or structured entity metrics' — concrete trigger guidance with negative boundaries, exactly matching the 'clearly and explicitly answers both what AND when' anchor.	5 / 5
Trigger Term Quality	Natural terms like 'evolution', 'lineage', 'first mention', and 'current live version' are present, but common user phrasings such as 'where did this idea come from' and 'how has my thinking changed' appear only in the triggers list, not the description itself. This fits 'good keyword coverage; a few natural terms missing' rather than the comprehensive synonym coverage of the 5 anchor.	4 / 5
Distinctiveness Conflict Risk	The description carves out a clear niche and actively disambiguates from the two adjacent capabilities ('not broad concept-map synthesis or structured entity metrics'), giving minimal conflict risk — the 5 anchor's 'clear niche with distinct triggers'.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 3 suspicious	Warning

	Total	14 / 16 Passed

Repository: garrytan/gbrain
Path: skills/idea-lineage/SKILL.md
Commit: 6622a11

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.