Tessl • The management layer for AI agent skills

Blog Docs Log inGet started

SkillPublic

update-cog

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

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/update-cog/SKILL.md

Quality

Content

82%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: fully executable git commands at every step, a clear numbered workflow with pre-flight customization checks and post-update verification, and lean prose with almost no padding. Remaining gains are small — trim the redundant Purpose/Important Notes overlap and add brief failure-path handling for fetch or checkout errors.

Dimension	Reasoning	Score
Conciseness	The body is lean and command-driven — git snippets, a terse framework-file list, and short bullets with no explanation of concepts Claude already knows (no git tutorials, no explanation of what a remote is). Minor trimming is possible: the 'Purpose' section restates the description and 'Important Notes' repeats points already made inline ('No merge conflicts possible' duplicates the checkout comment), so it sits just below the level-5 'every token earns its place' anchor.	4 / 5
Actionability	Every step is copy-paste-ready executable commands: 'git remote add cog-upstream https://github.com/huytieu/COG-second-brain.git', 'git fetch cog-upstream main --quiet', 'git show cog-upstream/main:COG-VERSION', 'git checkout cog-upstream/main -- <file>', plus complete cog-update.sh usage flags. This fully matches the level-5 anchor: executable commands covering the common cases.	5 / 5
Workflow Clarity	A clear 7-step sequence (version check → remote setup → fetch → compare → customization detection → apply → verify/summarize) with explicit pre-flight checkpoints (step 5 diffs each file and warns with keep/overwrite/backup options) and post-update verification (step 7), so the destructive/batch cap at 3 does not apply. Minor gaps keep it at 4: no handling for a failed fetch/missing upstream file and no re-check that the checkout actually changed the version.	4 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent) and the single-file structure is appropriate for this single-procedure skill; sections are clearly headed and navigable in one level with no nested references. It is not a sub-50-line skill (~100 lines), and parts like the framework file list could live in a reference file, leaving it just below the level-5 anchor.	4 / 5
	Total	17 / 20 Passed

Description

65%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 concise, third-person description with a clear 'what' and strong distinctiveness, but it lacks any 'when to use' trigger guidance and names only two concrete actions. Adding an explicit 'Use when...' clause and one or two more concrete actions (e.g., compare versions, review changes) would lift it substantially.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to update COG, check for COG updates, get the latest COG version, or asks about their COG version.'

Name one or two more concrete actions to improve specificity, e.g. 'compare local and upstream versions, review changed framework files, and selectively apply approved updates.'

Include common user phrasings/synonyms such as 'get latest', 'sync', or 'upgrade COG' to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	"Check for and apply upstream COG framework updates (skills, docs, scripts) without touching personal content" names the domain and exactly two concrete actions (check, apply) with an enumerated scope, matching the 'names domain and 1-2 concrete actions' anchor. It does not list several specific actions (no version comparison, diff review, or selective update language), so the level-4 anchor is not met.	3 / 5
Completeness	The 'what' is clearly stated (check for and apply upstream COG framework updates), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. The 'when' must be inferred from the topic rather than read from the description.	3 / 5
Trigger Term Quality	Natural terms a user would say are present: "check for", "apply", "updates", "upstream", "COG framework", "personal content". A few common variations are missing (e.g., "get latest version", "sync", "upgrade"), placing it at good-but-not-comprehensive coverage rather than the level-5 anchor.	4 / 5
Distinctiveness Conflict Risk	The description occupies a clear niche: upstream updates for the named COG framework with an explicit personal-content exclusion. Phrases like "upstream COG framework updates" and "without touching personal content" are highly unlikely to trigger for the wrong skill, matching the level-5 anchor.	5 / 5
	Total	15 / 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/update-cog/SKILL.md
Revision: 144c7a3

Reviewed: 1 month ago

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.

update-cog

Table of Contents

Is this your skill?