update-cog
Check for and apply upstream COG framework updates (skills, docs, scripts) without touching personal content
58
67%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/update-cog/SKILL.mdQuality
Discovery
57%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 reasonably specific to a clear niche (COG framework upstream updates) and distinguishes itself well from other potential skills. Its main weaknesses are the lack of an explicit 'Use when...' clause and limited trigger term coverage for how users might naturally request this functionality.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to sync, update, or pull upstream changes to the COG framework.'
Include natural trigger term variations such as 'sync', 'pull updates', 'upgrade framework', 'check for new versions' to improve discoverability.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (COG framework updates) and some actions (check for, apply updates), and specifies scope (skills, docs, scripts) while noting a constraint (without touching personal content). However, it doesn't list multiple distinct concrete actions beyond 'check' and 'apply'. | 2 / 3 |
Completeness | The 'what' is reasonably clear (check for and apply upstream COG framework updates). However, there is no explicit 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 2. | 2 / 3 |
Trigger Term Quality | Includes some relevant terms like 'upstream', 'COG framework', 'updates', 'skills', 'docs', 'scripts', but these are fairly niche/technical. A user might say 'update framework' or 'sync upstream' but the description doesn't cover common variations of how users might phrase this need. | 2 / 3 |
Distinctiveness Conflict Risk | This is a very specific niche — upstream COG framework updates — with the additional constraint of not touching personal content. It is unlikely to conflict with other skills given its narrow, well-defined scope. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill with excellent actionability and workflow clarity. The 7-step process is logically sequenced with concrete git commands at every step, and the customization detection checkpoint (Step 5) properly handles the destructive operation of file replacement. Minor improvements could be made in conciseness by trimming some explanatory notes and in progressive disclosure by potentially extracting the framework file list to a reference.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary explanation (e.g., 'never contain user content' comments, explaining what content folders are). The alternative shell script section adds useful but somewhat redundant information. Some tightening is possible. | 2 / 3 |
Actionability | Every step includes concrete, executable bash commands that are copy-paste ready. The git commands are specific and complete, covering remote setup, fetching, diffing, and surgical file checkout. The framework file list is explicit and comprehensive. | 3 / 3 |
Workflow Clarity | The 7-step process is clearly sequenced with logical progression from version check through verification. Step 5 provides an explicit validation checkpoint before destructive operations (detecting customizations and offering backup options), and Step 7 includes a verification and summary phase. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and numbered steps, but everything is inline in a single file. The framework file list and alternative shell script section could potentially be referenced externally. However, no bundle files exist, so there's no opportunity to evaluate cross-file navigation. For a skill of this length (~80 lines of substantive content), it's borderline acceptable as a single file. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- huytieu/COG-second-brain
- Commit
034af4c
- Reviewed
Table of Contents
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.