knowledge-consolidation

Build frameworks from scattered insights across all braindumps and notes

Quality

48%

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 ./.claude/skills/knowledge-consolidation/SKILL.md

Quality

Content

47%

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

The skill excels at workflow clarity with explicit verifiers and loop-engineering termination conditions, but it is markedly verbose — repeating template structures and restating familiar concepts — and keeps hundreds of lines of template content inline instead of splitting it into reference files.

Suggestions

Move the four large template blocks into reference files (e.g. references/framework-template.md, references/consolidation-report-template.md) and replace them with one-line pointers, cutting the bulk of the inline content.

Remove or condense the "Philosophy", "Success Metrics", "Analysis Techniques Reference", and "Consolidation Guidelines" sections, which restate pattern-detection and synthesis concepts Claude already knows.

Provide at least one fully worked example (real framework name, real source links) instead of placeholder-only templates to lift actionability.

Dimension	Reasoning	Score
Conciseness	The ~870-line body is padded with sections that restate concepts Claude already knows ("Analysis Techniques Reference", "Philosophy", "Success Metrics", "Consolidation Guidelines") and repeats near-identical template structures across four large inline templates, well beyond what the task requires.	1 / 3
Actionability	It gives concrete guidance (exact scan directories, a real `date '+%Y-%m-%d %H:%M'` command, frontmatter fields, save paths), but the four template blocks are placeholder scaffolds ([framework-name], [Principle 1], [Same structure...]) rather than fully worked executable examples.	2 / 3
Workflow Clarity	The 7-step process is clearly sequenced with explicit validation checkpoints: a required pre-flight date check, a traceability/coverage/dedup verifier, a completeness critic, and layered termination (dry K=2, coverage complete, hard cap) — directly satisfying the feedback-loop requirement for batch operations.	3 / 3
Progressive Disclosure	Headers and a numbered flow provide structure, but the four large template blocks (framework, new framework, pattern, timeline, consolidation report) are inline content that should live in separate reference files; no references/scripts/assets bundle exists, and the only external pointer is to another skill.	2 / 3
	Total	8 / 12 Passed

Description

50%

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 third-person and identifies a clear domain, but it states only a single action and entirely lacks a "Use when..." trigger clause, capping completeness and distinctiveness. It reads as a what-only summary rather than a fully specified skill trigger.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user says 'consolidate knowledge', 'build frameworks', or 'synthesize insights', or for periodic knowledge-base maintenance."

List more concrete actions (e.g. extract patterns, update existing frameworks, document thinking evolution, archive superseded content) to reach multiple specific capabilities.

Include natural trigger variations users would say ("consolidate", "synthesize", "knowledge base review") to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	"Build frameworks from scattered insights across all braindumps and notes" names the domain (braindumps, notes, insights) and a core action (build frameworks), but lists only one action rather than multiple specific concrete actions, so it stops short of the score-3 anchor.	2 / 3
Completeness	It states what the skill does (build frameworks from scattered insights) but provides no explicit "Use when..." trigger guidance, so per the rubric guideline completeness is capped at 2.	2 / 3
Trigger Term Quality	Terms like "braindumps", "notes", and "frameworks" are natural for users of this system, but the description omits common phrasings users would actually say (e.g. "consolidate", "synthesize", "knowledge base"), leaving only partial coverage.	2 / 3
Distinctiveness Conflict Risk	"Braindumps and notes" gives it a recognizable niche, but "build frameworks from insights" is generic enough to overlap with other synthesis/notes skills, and the lack of explicit triggers raises conflict risk.	2 / 3
	Total	8 / 12 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
skill_md_line_count	SKILL.md is long (877 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: huytieu/COG-second-brain
Path: .claude/skills/knowledge-consolidation/SKILL.md
Commit: dfbf9e9

Reviewed: 2 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.