knowledge-consolidation

Build frameworks from scattered insights across all braindumps and notes

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.

The skill is well-structured and unusually self-aware about its loop/verification design, but it is far too long: hundreds of lines of repetitive template scaffolding and concept restatement sit inline rather than in bundle files. It mixes strong workflow thinking with verbosity that hurts token efficiency.

Suggestions

Move the four full markdown templates (consolidated framework, new framework, pattern, timeline, report) into files under references/ and link to them one level deep, leaving only field summaries in SKILL.md.

Cut redundant restatement: the Analysis Techniques Reference and Pattern Detection Methods duplicate the Process Flow sections — keep one and reference the other.

Add a validate-before-confirm checkpoint in step 6 (Cleanup/Archival) so destructive moves to 00-inbox/archive/ are checked before the completion message is shown.

Dimension	Reasoning	Score
Conciseness	The body is ~870 lines dominated by four large, near-identical template blocks and repeated restatement of analysis methods and success metrics, well past what Claude needs; it explains organizing concepts Claude already knows.	1 / 3
Actionability	It provides concrete file paths, frontmatter schemas, and one real executable command (`date '+%Y-%m-%d %H:%M'`), but most 'steps' are template placeholders rather than executable instructions, so guidance is concrete but incomplete.	2 / 3
Workflow Clarity	The seven-step process is clearly sequenced and the Loop Engineering section adds explicit verification (traceability, coverage, dedup) and termination conditions, but batch/destructive archival lacks a validate-before-confirm checkpoint, capping it at 2.	2 / 3
Progressive Disclosure	Sections are well organized, but the four full-length markdown templates live inline in SKILL.md rather than in referenced bundle files; no references/ or scripts/ directory exists, so large template content that should be separate is inlined.	2 / 3
	Total	7 / 12 Passed

Description

52%

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 names the domain and a single core action but stops short of enumerating concrete capabilities and omits any explicit 'Use when...' trigger. Trigger terms lean on internal vocabulary rather than natural user phrasing.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user asks to consolidate notes, synthesize braindumps into frameworks, or periodically review accumulated insights.'

Replace internal jargon ('braindumps', 'COG') with natural trigger terms users would actually say ('notes', 'insights', 'build frameworks', 'synthesize knowledge').

List concrete actions (e.g. 'scan notes, detect recurring patterns, build and update framework documents') to reach a level-3 specificity anchor.

Dimension	Reasoning	Score
Specificity	Names the domain ('knowledge consolidation') and core action ('build frameworks') but does not list multiple concrete actions like the level-3 anchor ('extract', 'fill', 'merge'); 'scattered insights' is the only named verb set.	2 / 3
Completeness	It states what the skill does but has no 'Use when...' clause or explicit trigger, so the 'when' half is missing, which caps completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	The phrase 'build frameworks' and 'scattered insights' are technical/internal vocabulary a user is unlikely to say naturally; it lacks plain natural keywords users would actually utter.	1 / 3
Distinctiveness Conflict Risk	'Knowledge consolidation' / 'frameworks from insights' carves a niche but the language overlaps with generic note-synthesis or summarization skills, so it could still be mistaken for adjacent skills.	2 / 3
	Total	7 / 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
Commit: 5e9851c

Reviewed: 14 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.