concept-synthesis

Deduplicate and synthesize raw concept stubs into a tiered intellectual map (T1 Canon to T4 Riff), tracing idea evolution across sources over time. Transforms thousands of raw concept pages into a curated intellectual fingerprint. Includes a reversible curation cull pass (Phase 5) with hard keep/delete/merge verdicts, substance gates, grounding labels, cluster budgets, and merge-with-backlinks salience promotion.

Quality

74%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/concept-synthesis/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.

A well-structured, highly actionable skill body with strong validation safeguards for its destructive cull workflow. Its main weakness is redundancy — several rules are restated three times — which hurts token efficiency without adding clarity.

Suggestions

De-duplicate the rules restated across Phase 5, Anti-Patterns, and Quality Gates (e.g. distinctness guard, merge reversibility, no-hardcoded-cutoff); state each once and reference it.

Provide the LLM synthesis prompt and a concrete Jaccard/substring dedup snippet so Phase 1 and Phase 3 are as executable as the merge mechanics.

Consider extracting the long Phase 5 cull rubric into a references/ file referenced one level deep, keeping SKILL.md as an overview.

Dimension	Reasoning	Score
Conciseness	Mostly valuable but noticeably redundant: the distinctness guard ('hard veto, not advisory'), merge reversibility, and the 'don't hardcode a numeric similarity cutoff' rule are each restated across the Phase 5 detail, Anti-Patterns, and Quality Gates sections and could be tightened.	3 / 5
Actionability	Provides concrete executable commands (gbrain query/search/put/delete/restore/history/revert) and full markdown output templates with frontmatter, plus a concrete 6-axis scoring table; minor gaps are the described-but-unimplemented Jaccard/substring dedup and LLM synthesis prompts given as outlines rather than verbatim.	4 / 5
Workflow Clarity	A destructive/batch skill with explicit validation and feedback loops: the merge-quality gate rejects incomplete merges and flags for manual review, the distinctness guard requires affirmative LLM confirmation, test-before-bulk mandates a 3-5 cluster spot-check, and quality-gate + anti-pattern checklists plus undo paths round out error recovery.	5 / 5
Progressive Disclosure	No bundle files exist, but the body is well-organized with clear section headers and its external conventions are one-level-deep references clearly signaled via blockquote 'Convention:' callouts; the large inline Phase 5 cull rubric is well-subsectioned, leaving only minor organization gaps.	4 / 5
	Total	16 / 20 Passed

Description

75%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 specific, action-rich, distinctive description in correct third-person voice, but it omits any explicit 'when to use this' guidance, which caps its completeness. Adding a 'Use when…' clause tied to the frontmatter triggers would lift the weakest dimension.

Suggestions

Add an explicit 'Use when…' clause naming natural user phrasings (e.g. 'Use when the user asks to synthesize, deduplicate, or curate their concepts, or build their intellectual map').

Soften internal jargon in the description ('salience promotion', 'T1 Canon to T4 Riff') or pair it with plain-language synonyms to broaden natural trigger coverage.

Trim the dense 'Phase 5' parenthetical, which references internal structure rather than user-facing capability.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Deduplicate and synthesize', 'tiered intellectual map (T1 Canon to T4 Riff)', 'tracing idea evolution', 'curation cull pass (Phase 5) with hard keep/delete/merge verdicts, substance gates, grounding labels, cluster budgets, and merge-with-backlinks' — in third-person voice with comprehensive coverage.	5 / 5
Completeness	The 'what' is clearly and comprehensively stated, but there is no 'Use when…' clause or equivalent explicit trigger guidance, so per the judging guideline completeness is capped at 3.	3 / 5
Trigger Term Quality	Good natural keywords ('synthesize', 'deduplicate', 'concept stubs', 'intellectual map', 'idea evolution', 'curation cull') but misses common synonyms and leans on internal jargon ('T1 Canon', 'T4 Riff', 'salience promotion'), falling short of the comprehensive synonym coverage anchor.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (concept synthesis / intellectual mapping / reversible curation culling) with distinctive terminology, making it unlikely to trigger for the wrong skill.	5 / 5
	Total	17 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (514 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 5 missing, 5 suspicious	Warning

	Total	13 / 16 Passed

Repository: garrytan/gbrain
Path: skills/concept-synthesis/SKILL.md
Commit: 43597b1

Reviewed: 1 day 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.