CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

62

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/git/skills/git-notes/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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.

The content is highly actionable with thorough, executable command examples, but it suffers from structural issues: duplicated command coverage inflates length, batch/destructive workflows lack validation checkpoints, and a referenced `references/commands.md` file is missing while its intended content is inlined.

Suggestions

Create the referenced `references/commands.md` and move the full '# Git Notes Command Reference' section into it, keeping only the Quick Reference table and Essential Patterns in SKILL.md to eliminate the dangling reference and inlined bulk.

Add validation checkpoints to batch/destructive workflows — e.g. dry-run `git notes prune -n` before pruning, or verify the SHA list with `git log --format='%H' HEAD~10..HEAD | wc -l` before bulk `git notes remove`.

De-duplicate the Quick Reference table against the Command Reference section so each command appears in detail in only one place, cutting the body length substantially.

DimensionReasoningScore

Conciseness

Mostly efficient per-section, but the body duplicates command coverage between the Quick Reference table and the full Command Reference section, and runs ~430 lines for a single subcommand — it could be tightened by not presenting the same commands twice.

3 / 5

Actionability

The body is dense with copy-paste-ready, executable git commands covering add/show/append/edit/remove/copy/prune/merge across namespaces, with concrete examples for the common cases like review tracking and test annotation.

5 / 5

Workflow Clarity

Workflow Examples are sequenced, but batch and destructive operations (e.g. `git notes remove` across `HEAD~10..HEAD`, bulk `git notes add` loops) lack validation/verification checkpoints, which caps this dimension at 3 per the rubric.

3 / 5

Progressive Disclosure

The first half is a well-structured overview (tables, patterns, mistakes, best practices), but ~350 lines of command reference are inlined in the body while line 37 points readers to `references/commands.md` — a file that does not exist in the bundle, leaving a dangling reference alongside content that should live in that file.

3 / 5

Total

14

/

20

Passed

Description

83%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.

The description is strong: it pairs a concrete 'Use when...' trigger clause with a clear statement of what the skill provides, using third-person voice and specific use cases. Its main weakness is mild redundancy between 'adding metadata to commits' and 'attaching non-invasive metadata to Git objects'.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'adding metadata to commits without changing history', 'tracking review status, test results, code quality annotations', 'supplementing commit messages post-hoc' — but 'adding metadata to commits' and 'attaching non-invasive metadata to Git objects' restate the same action, leaving minor coverage gaps rather than full breadth.

4 / 5

Completeness

It explicitly 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...') with concrete trigger phrases, mirroring the anchor-5 example structure.

5 / 5

Trigger Term Quality

Natural phrases a user would say are present ('metadata to commits', 'review status', 'test results', 'commit messages', 'git notes') with an explicit 'Use when' trigger, but it lacks synonyms/variations that would push it to comprehensive coverage.

4 / 5

Distinctiveness Conflict Risk

'git notes' is a clear, specific niche with low conflict risk, but triggers like 'tracking review status' and 'test results' create minor overlap with code-review/CI skills rather than being wholly distinct.

4 / 5

Total

17

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
NeoLabHQ/context-engineering-kit
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.