knowledge-consolidation

Build frameworks from scattered insights across all braindumps and notes

Quality

62%

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

71%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 body is a well-structured, actionable consolidation workflow with concrete paths, a real referenced bundle file, and strong verification/feedback loops for its batch-destructive operations. Its main weakness is verbosity from restated and motivational sections that could be trimmed without losing clarity.

Suggestions

Remove or merge the 'Analysis Techniques Reference' section with the earlier 'Pattern Recognition' section to eliminate duplicated content.

Cut the 'Philosophy' and 'Common Use Cases' sections, which add motivational/restatement padding without actionable guidance Claude does not already infer from the workflow.

Add an explicit validate/verify step within step 5 (report generation) to match the checkpoint density of the Loop Engineering section.

Dimension	Reasoning	Score
Conciseness	The core workflow is efficient with concrete paths and commands, but sections like 'Analysis Techniques Reference', 'Common Use Cases', and 'Philosophy' restate earlier content or add motivational padding that could be trimmed.	3 / 5
Actionability	Concrete save paths, an exact `date` command, a YAML frontmatter block, and named template references in references/templates.md give mostly executable guidance, with only minor gaps (e.g. no explicit dedup command).	4 / 5
Workflow Clarity	The 7-step sequence is clear and the destructive/batch operation includes explicit verification (traceability, coverage, dedup, completeness critic, termination conditions) so the batch cap does not apply; a couple of steps still have implicit rather than explicit checkpoints, keeping it just below 5.	4 / 5
Progressive Disclosure	The body is an overview that points to a single one-level-deep reference (references/templates.md, referenced 5 times by name), which was verified to exist and contain the templates; content is appropriately split with clear navigation.	5 / 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 gives a clear single action and a specific domain but lacks an explicit trigger/"Use when" clause, capping completeness and limiting trigger term coverage. It is reasonably distinct but reads as a one-liner rather than a full what-plus-when statement.

Suggestions

Add an explicit 'Use when...' clause naming the natural trigger phrases a user would say, e.g. 'Use when the user wants to consolidate knowledge, build frameworks, or synthesize insights from accumulated braindumps and notes.'

Expand the action list beyond 'Build frameworks' to mention the concrete sub-actions the skill performs (scan braindumps, detect patterns, synthesize frameworks, generate a consolidation report, mark sources consolidated).

Include common synonyms and file/path markers users actually mention (e.g. 'braindumps', 'daily briefs', 'check-ins', 'knowledge base maintenance') to broaden trigger term coverage.

Dimension	Reasoning	Score
Specificity	"Build frameworks from scattered insights across all braindumps and notes" names one concrete action (build frameworks) and the input domain (braindumps/notes), matching the 1-2 concrete actions anchor without comprehensive coverage.	3 / 5
Completeness	It has a clear "what" (build frameworks from scattered insights) but no "Use when..." clause, so per the missing-trigger-guidance rule completeness is capped at 3.	3 / 5
Trigger Term Quality	Keywords like "frameworks", "scattered insights", and "braindumps" are relevant but the description omits the natural trigger phrases ("consolidate knowledge", "synthesize insights") that appear only in the body, leaving common variations missing.	3 / 5
Distinctiveness Conflict Risk	The braindump/notes consolidation niche is fairly specific and unlikely to conflict with most skills, though the word "frameworks" is somewhat broad, placing it mostly distinct with minor overlap risk.	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: huytieu/COG-second-brain
Path: .claude/skills/knowledge-consolidation/SKILL.md
Commit: cb4644d

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.