git-notes
Use when adding metadata to commits without changing history, tracking review status, test results, code quality annotations, or supplementing commit messages post-hoc - provides git notes commands and patterns for attaching non-invasive metadata to Git objects.
77
71%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/git/skills/git-notes/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly defines a specific niche (git notes), lists concrete use cases, and includes an explicit 'Use when' clause with natural trigger terms. The description is concise yet comprehensive, covering both what the skill does and when it should be selected, with enough specificity to avoid conflicts with general git or commit message skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: adding metadata to commits, tracking review status, test results, code quality annotations, supplementing commit messages post-hoc, and providing git notes commands and patterns. | 3 / 3 |
Completeness | Clearly answers both what ('provides git notes commands and patterns for attaching non-invasive metadata to Git objects') and when ('Use when adding metadata to commits without changing history, tracking review status, test results, code quality annotations, or supplementing commit messages post-hoc'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'git notes', 'metadata', 'commits', 'review status', 'test results', 'code quality annotations', 'commit messages'. These cover the domain well and match how users would naturally describe these tasks. | 3 / 3 |
Distinctiveness Conflict Risk | Very distinct niche — git notes is a specific, lesser-known Git feature. The description clearly differentiates from general git skills by focusing on non-invasive metadata attachment, review status tracking, and post-hoc annotations, making conflicts with other skills unlikely. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides highly actionable, executable git notes commands and patterns, which is its primary strength. However, it is severely bloated — the command reference section duplicates and expands the quick reference at great length, wasting token budget. The content should be split into a concise overview SKILL.md with references to separate detailed files, rather than inlining everything.
Suggestions
Split the detailed 'Command Reference' section into a separate file (e.g., references/commands.md) and keep only the Quick Reference table and Essential Patterns in SKILL.md.
Remove explanations of basic concepts like what notes are and how they display — Claude already knows git fundamentals. Focus on the non-obvious patterns (namespaces, rebase preservation, merge strategies).
Add validation/verification steps to bulk operations, e.g., 'Preview affected commits with --dry-run before applying notes in bulk'.
Eliminate redundant examples — e.g., 'Add note to HEAD' vs 'Add note to specific commit' are trivially different and don't need separate entries.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is extremely verbose and repetitive. The 'Quick Reference' table covers the essential commands, but then the entire 'Command Reference' section repeats and expands everything at massive length. Basic git concepts Claude already knows are explained, and many trivial variations (e.g., every flag combination for `git notes remove`) bloat the file significantly. This should be ~50 lines, not ~300+. | 1 / 3 |
Actionability | The skill provides fully executable, copy-paste ready bash commands throughout. Every pattern includes concrete examples with specific commands, flags, and realistic placeholder values. The workflow examples are complete and directly usable. | 3 / 3 |
Workflow Clarity | Individual workflows like code review tracking and sharing notes are clearly sequenced. However, there are no validation checkpoints or error recovery steps for bulk operations (which are destructive-adjacent), and the merge conflict resolution workflow is minimal. The 'Preserving Through Rebase' section is just config commands without a clear workflow sequence. | 2 / 3 |
Progressive Disclosure | The content is a monolithic wall of text with everything inlined. It references 'references/commands.md' for a complete command reference, but then includes what appears to be the entire command reference inline in the same file. There is no meaningful separation of overview from detailed reference material, and no bundle files exist to support the reference. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- NeoLabHQ/context-engineering-kit
- Commit
dedca19
- 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.