CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

moai-ref-git-workflow

Git workflow patterns, branch strategies, conventional commits, and PR templates reference for git operations. Agent-extending skill that amplifies manager-git expertise with production-grade git workflow patterns. NOT for: code implementation, testing, architecture design, documentation content.

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/moai-ref-git-workflow/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 body is a well-structured, table-driven reference that is lean, concrete, and actionable, with explicit verification checkpoints and safety rules for destructive git operations. It is appropriately self-contained with no dangling or nested references.

DimensionReasoningScore

Conciseness

Dense tables and ASCII branch diagrams with essentially no re-explanation of concepts Claude already knows; the 'Common Rationalizations' table is mildly padded but adds practical value. Not 5 because a few rows (e.g., some rationalizations) could be trimmed; not 3 because there is no genuinely unnecessary explanation.

4 / 5

Actionability

Provides concrete executable commands ('gh pr merge --squash'), a copy-paste-ready PR template, exact branch-naming patterns, and worked commit-message examples. Not 5 because actual git commands for branch creation and merge execution are absent (patterns only); not 3 because the guidance is concrete and complete for a reference skill.

4 / 5

Workflow Clarity

As a reference skill it is organized by task area, and the Verification section gives explicit checkpoints ('show git log --oneline', 'grep for <<<<<<<') while the safety-rules table validates destructive operations ('NEVER on main/master, ask user first'). Not 5 because there are no error-recovery feedback loops; not 3 because validation checkpoints are explicitly present.

4 / 5

Progressive Disclosure

Single-file skill (~190 lines) with clean section headers, no nested references, and self-contained content; frontmatter declares progressive_disclosure token levels and no bundle files exist to point to. Not 5 because it exceeds 50 lines and sections like the PR template or rationalizations could plausibly live in reference files; not 3 because the structure is well-organized, not in need of reorganization.

4 / 5

Total

16

/

20

Passed

Description

66%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 clearly communicates what the skill covers with concrete, domain-appropriate keywords, and the NOT-for boundary aids distinctiveness. Its main weakness is that positive trigger guidance is absent from the description itself (delegated to when_to_use), capping completeness at 3.

Suggestions

Add an explicit 'Use when...' clause to the description itself (e.g., 'Use when setting branch strategy, writing conventional commit messages, creating PRs, or choosing merge vs. rebase') rather than relying solely on the separate when_to_use field.

Include common synonyms such as 'pull request', 'merge', and 'rebase' alongside 'PR templates' to broaden natural trigger coverage.

Mention merge/rebase flow selection in the description so the what-coverage matches the body's actual scope.

DimensionReasoningScore

Specificity

Lists several concrete content areas — 'branch strategies, conventional commits, and PR templates' — with minor gaps (merge/rebase flows are only in when_to_use, not the description). Not 5 because coverage is not fully comprehensive; not 3 because it names more than 1-2 concrete items.

4 / 5

Completeness

The 'what' is clear ('reference for git operations' with enumerated pattern areas) and the 'NOT for:' clause gives negative triggers, but the description itself contains no positive 'Use when...' clause — that guidance lives in a separate when_to_use field. Per the rubric guideline, a missing explicit trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

Good natural keywords users would say ('git workflow', 'branch', 'commits', 'PR'), but missing common synonyms like 'pull request', 'merge', and 'rebase'. Not 5 because synonym coverage is incomplete; not 3 because keyword coverage is solid rather than partial.

4 / 5

Distinctiveness Conflict Risk

Scoped to a clear niche (git workflow patterns amplifying 'manager-git' expertise) with explicit exclusions for code, testing, architecture, and docs. Mostly distinct with only minor overlap risk against a generic git-operations skill.

4 / 5

Total

15

/

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.

Validation — 15 / 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

modu-ai/moai-adk

Path

.claude/skills/moai-ref-git-workflow/SKILL.md

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.