CtrlK
BlogDocsLog inGet started
Tessl Logo

git-workflow

Squad branching model: dev-first workflow with insiders preview channel

56

Quality

65%

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 ./.copilot/skills/git-workflow/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

80%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is lean, highly actionable, and well-sequenced with concrete commands throughout. Its main gaps are missing explicit validation checkpoints before destructive operations and no use of progressive disclosure to split the longer sections into reference files.

Suggestions

Add explicit validation checkpoints before destructive cleanup, e.g. verify the PR is merged and CI is green before running 'git push origin --delete' or 'git worktree remove'.

Split the substantial Worktrees and Multi-Repo sections into one-level-deep reference files (e.g. WORKTREES.md, MULTI-REPO.md) with signaled links from the main workflow overview.

Add a brief verify/retry feedback loop for the publish steps (e.g. confirm the --tag preview publish succeeded) to strengthen workflow clarity.

DimensionReasoningScore

Conciseness

The body is command-dense with tables and code blocks, assumes git competence without explaining basics, and its rare rationale prose (e.g. merge=union reasoning) earns its place rather than padding.

3 / 3

Actionability

It provides fully executable git/gh commands with concrete examples (e.g. 'git worktree add ../squad-195 -b squad/195-fix-stamp-bug origin/dev') and clearly marked placeholders, making guidance copy-paste ready.

3 / 3

Workflow Clarity

Steps are clearly numbered and sequenced with preconditions, but destructive cleanup operations (remote branch deletion, worktree removal) lack explicit verify/validate checkpoints or feedback loops, capping the score at 2.

2 / 3

Progressive Disclosure

Content is well-organized into clear sections (avoiding a wall of text) but lives in a single ~200-line file with no external references, and substantial sections (Worktrees, Multi-Repo) remain inline that could be split into reference files.

2 / 3

Total

10

/

12

Passed

Description

50%Weight 40%Scale 1-3

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 names a specific team workflow domain but is a noun phrase with no enumerated actions and no 'Use when...' trigger guidance. It is specific and distinguishable yet incomplete on when-to-use signaling.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when creating issue branches, opening PRs against dev, or managing parallel work with worktrees.'

Lead with concrete verbs/actions ('Branch from dev, open draft PRs, manage worktrees') instead of a pure noun phrase so capabilities are explicit.

Include common natural keywords users would say ('git', 'PR', 'pull request', 'feature branch') alongside the team-internal terms.

DimensionReasoningScore

Specificity

Names a specific domain ('Squad branching model', 'dev-first workflow', 'insiders preview channel') but lists no concrete verb-actions, so it is specific rather than vague yet not comprehensive enough for a 3.

2 / 3

Completeness

It states the WHAT (the branching model/workflow) but provides no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 2 per the rubric.

2 / 3

Trigger Term Quality

Contains relevant developer keywords ('branching', 'dev', 'workflow', 'preview channel') but they are team-internal ('Squad', 'insiders') and miss common natural variations such as 'git', 'PR', or 'pull request'.

2 / 3

Distinctiveness Conflict Risk

The niche is specific (Squad's dev-first + insiders model) but the absence of explicit trigger boundaries leaves some overlap risk with a generic git-branching skill.

2 / 3

Total

8

/

12

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
microsoft/waza
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.