update-cog

Check for and apply upstream COG framework updates (skills, docs, scripts) without touching personal content

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

87%

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

The content is highly actionable, concise, and well-structured, with its only meaningful gap being the absence of an explicit post-apply validation feedback loop for the destructive file-replacement step.

Suggestions

Add an explicit validation checkpoint after step 6 (e.g. re-read COG-VERSION or diff to confirm files changed as expected) before suggesting the commit, so the destructive flow has a validate-fix-retry loop.

Consider a brief 'rollback' note for how to undo a bad update, reinforcing the safety framing the skill already emphasizes.

Dimension	Reasoning	Score
Conciseness	The body is lean and action-oriented, assuming Claude's competence (no exposition of git concepts) with every section earning its place; minor redundancy does not rise to verbosity.	3 / 3
Actionability	It provides fully executable bash commands, a concrete framework-file list, and copy-paste-ready options ('Keep yours', 'Use upstream', 'Backup + update'), giving exact actionable guidance.	3 / 3
Workflow Clarity	A clear 7-step sequence exists with detection of customizations as a checkpoint, but the destructive git-checkout overwrite step lacks an explicit validate-then-fix feedback loop, which caps destructive/batch workflows at 2.	2 / 3
Progressive Disclosure	It is a single, well-organized SKILL.md with clear section navigation and no nested external references, fitting the well-organized-single-file pattern that earns a 3.	3 / 3
	Total	11 / 12 Passed

Description

67%

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 specific and well-scoped but is missing an explicit trigger clause, so it answers 'what' strongly while leaving 'when to use it' only implied.

Suggestions

Add an explicit 'Use when...' clause listing natural triggers such as 'update COG', 'check for COG updates', or 'get the latest COG version' to raise completeness and trigger_term_quality.

Include a couple of common phrasings users would actually say (e.g. 'COG version', 'new COG skills') so trigger matching is more robust.

Dimension	Reasoning	Score
Specificity	Names concrete actions ('Check for and apply') and enumerates specific update targets '(skills, docs, scripts)' alongside a clear protective constraint, matching the 'multiple specific concrete actions' anchor.	3 / 3
Completeness	It clearly answers 'what' (check and apply upstream framework updates without touching personal content) but lacks any explicit 'Use when...' trigger clause, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Domain terms like 'COG framework updates' are relevant, but the description omits the natural trigger phrasings users would say (e.g. 'update COG', 'check for updates') that appear only in the body, so coverage of natural terms is partial.	2 / 3
Distinctiveness Conflict Risk	The narrow COG-framework niche plus the 'without touching personal content' qualifier make it clearly distinguishable and unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 12 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
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.