CtrlK
BlogDocsLog inGet started
Tessl Logo

using-git-worktrees

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback

69

Quality

84%

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

The canonical home for this skill is using-git-worktrees in obra/superpowers

SKILL.md
Quality
Evals
Security

Quality

Content

85%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 strong, actionable, well-sequenced workflow with explicit validation and feedback loops, and is appropriately structured for a single-file skill. The main improvement lever is reducing redundancy between the Red Flags, Common Mistakes, and Quick Reference sections.

Suggestions

Consolidate the overlapping Red Flags and Common Mistakes sections to remove restated guidance and save tokens.

Replace the Step 3 slash-list ('npm test / cargo test / pytest / go test') with a language-detected command table matching the Step 2 style for fully copy-paste-ready verification.

Consider trimming the Quick Reference table since its rows duplicate inline guidance already present in the steps.

DimensionReasoningScore

Conciseness

The body is mostly lean with minimal padding, though the 'Red Flags' section largely restates 'Common Mistakes' and the Quick Reference table repeats inline guidance, adding some redundancy. Not a 5 due to that repetition, not a 3 because the prose is generally efficient and assumes Claude's competence.

4 / 5

Actionability

Provides concrete executable commands throughout ('git rev-parse --git-dir', 'git worktree add "$path" -b "$BRANCH_NAME"', 'git check-ignore -q .worktrees', npm/cargo/pip/go setup). The Step 3 'npm test / cargo test / pytest / go test' slash-list is slightly less copy-paste-ready, a minor gap keeping it from a 5.

4 / 5

Workflow Clarity

Clear Step 0→3 sequence with explicit validation checkpoints: submodule guard before concluding isolation, 'git check-ignore' before creating project-local worktrees, baseline test verification, and 'If tests fail: Report failures, ask whether to proceed' feedback loop. Fully meets the top anchor including error-recovery loops.

5 / 5

Progressive Disclosure

A self-contained skill with no external bundle files and no need for them; it is well-organized into Overview, numbered Steps, Quick Reference, Common Mistakes, and Red Flags sections. Per the simple-skill scoring note, well-organized single-file content with no external-reference need scores 5.

5 / 5

Total

18

/

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 well-crafted, explicitly covering both what the skill does and when to use it with concrete, natural trigger phrases. Minor gains are possible by adding synonyms (feature branch, sandbox) and slightly broadening the action coverage.

Suggestions

Add natural synonyms like 'feature branch', 'sandbox', or 'parallel work' to broaden trigger-term coverage.

Mention cleanup/teardown or branch lifecycle to push specificity toward comprehensive coverage.

Tighten the description so the mechanism ('native tools or git worktree fallback') reads as a capability rather than an implementation detail.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'ensures an isolated workspace exists', 'via native tools or git worktree fallback' — with only minor coverage gaps (e.g., no mention of cleanup or branch management). It is not a 5 because the action set is not fully comprehensive, and not a 3 because more than 1-2 actions are named.

4 / 5

Completeness

Explicitly answers both 'what' ('ensures an isolated workspace exists via native tools or git worktree fallback') and 'when' ('Use when starting feature work that needs isolation... or before executing implementation plans') with concrete trigger phrases. Clearly meets the top anchor.

5 / 5

Trigger Term Quality

Includes natural user phrases like 'starting feature work', 'before executing implementation plans', and 'needs isolation from current workspace', but misses common synonyms such as 'feature branch', 'sandbox', or 'parallel work'. Good coverage but a few natural terms are absent, so not a 5.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche (workspace isolation for feature work) with distinct triggers like 'git worktree fallback' and 'native tools', but has minor overlap risk with general git or environment-setup skills. Not a 5 due to that residual overlap, not a 3 because the niche is clearly stated.

4 / 5

Total

17

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
rpamis/comet
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.