CtrlK
BlogDocsLog inGet started
Tessl Logo

git-safe-ops

Encodes safe git operation rules — no force-push to main, always branch, always review before merge.

67

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

93%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 a lean, highly actionable rule set with strong validation gates via escalation and failure-mode handling, suffering only from the absence of a single canonical linear workflow sequence.

DimensionReasoningScore

Conciseness

The body is lean and rule-focused with no padding of concepts Claude already knows; every section states concrete rules and commands, and explanatory clauses are actionable justifications rather than filler.

5 / 5

Actionability

Provides fully concrete, copy-paste-ready commands throughout (git push --force, --force-with-lease, git diff --staged, git tag -a vX.Y.Z, git log --oneline origin/branch..HEAD) plus a concrete commit-message format, covering the common destructive cases.

5 / 5

Workflow Clarity

Escalation Rules and Failure Modes supply explicit validation gates and feedback loops for destructive/batch operations (so the destructive-ops cap does not apply), but there is no single canonical linear workflow sequence, leaving a minor gap.

4 / 5

Progressive Disclosure

Well-organized into clearly labeled sections (Purpose, Invocation, Core Safety Rules, Escalation, Inputs, Outputs, Failure Modes, References, Companion Skills) with one-level external links and cross-skill navigation; no bundle splitting is needed for a skill this size.

5 / 5

Total

19

/

20

Passed

Description

70%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 specific, third-person, and well-differentiated, but it omits an explicit 'Use when...' trigger clause, which caps completeness at 3.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when running any git command, especially force-pushes, merges, or commits to protected branches.'

Include common synonyms such as 'pull request'/'PR' and 'git push' to broaden trigger-term coverage.

Consider listing 1-2 more concrete rules (e.g. credential hygiene, release tagging) to push specificity toward comprehensive.

DimensionReasoningScore

Specificity

Names the git domain and lists several concrete rules ('no force-push to main, always branch, always review before merge'), but coverage is not comprehensive enough for a 5.

4 / 5

Completeness

It clearly states what the skill does ('Encodes safe git operation rules') but provides no explicit 'Use when...' trigger clause, so per the cap, 'when' is only weakly implied.

3 / 5

Trigger Term Quality

Includes natural terms users say (force-push, main, branch, merge, review) but misses common synonyms like 'pull request'/'PR' or 'git push', keeping it just below comprehensive.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear, narrow niche (git safety gating) with distinct triggers that are unlikely to fire for unrelated skills.

5 / 5

Total

16

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
pvnkmnk/AgenticSelfHostSkills
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.