CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

66

Quality

83%

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

81%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.

A well-structured operational skill: executable commands throughout, an explicit sequenced workflow with validation and error-recovery paths, and a decision table that makes edge cases unambiguous. Remaining polish is minor — tighten two redundant explanation spots, define the placeholder variables in the worktree-add block, and consider splitting the reference tables into a bundled file.

DimensionReasoningScore

Conciseness

The body is lean: it assumes git competence, skips worktree concept explanations, and lets runnable commands carry the instruction. Minor over-explanation remains — "Why critical: Prevents accidentally committing worktree contents to repository" restates the preceding MUST directive, and the rationalizations table is borderline padding — so it is efficient with minor trim opportunities rather than fully lean.

4 / 5

Actionability

Nearly everything is executable: rev-parse detection commands, a submodule guard, check-ignore verification, `git worktree add`, and a concrete setup matrix. The one gap is `path="$LOCATION/$BRANCH_NAME"`, which references undefined variables, so that block is not copy-paste ready — keeping it at 'mostly executable with minor gaps' rather than fully executable.

4 / 5

Workflow Clarity

The sequence is explicit (Step 0 detect → Step 1a/1b create → Step 2 setup → Step 3 baseline) with validation checkpoints (submodule guard, MUST check-ignore, clean-baseline tests) and error-recovery loops (sandbox fallback, report-failures-and-ask on test failure), plus a quick-reference table mapping every situation to an action. This matches the top anchor: clear sequence, explicit validation, feedback loops for error recovery.

5 / 5

Progressive Disclosure

No bundle files exist, and the body is well-organized with clear section headers, a decision table, and a quick-reference index. At ~165 lines everything is inline; the Quick Reference and Common Rationalizations tables are candidates for a separate reference file, leaving it at 'good structure; most content appropriately placed' rather than a textbook clear-overview-with-references layout.

4 / 5

Total

17

/

20

Passed

Description

78%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.

A strong description with an explicit when-clause and a clear, mechanism-specific what. Its main gaps are thin action coverage (one composite action) and a few missing natural trigger synonyms. Third-person phrasing is maintained throughout.

Suggestions

Enumerate 2-3 more concrete capabilities in the what-clause, e.g. 'detects existing worktree/submodule isolation, verifies the worktree directory is git-ignored, and runs baseline tests' to raise specificity.

Add natural trigger synonyms users would say, such as 'worktree', 'work tree', 'parallel branch', or 'isolated environment', to broaden trigger-term coverage.

Clarify the trigger boundary with plan-execution skills — e.g. 'Use when starting feature work or executing implementation plans that require an isolated workspace' — to reduce co-trigger risk.

DimensionReasoningScore

Specificity

The description names the domain (workspace isolation) and one composite action — "ensures an isolated workspace exists via native tools or git worktree fallback" — but omits the skill's other concrete behaviors (detecting existing isolation, verifying ignore status, baseline testing). It lists 1-2 concrete actions rather than several, matching the anchor for 'names domain and 1-2 concrete actions, but not comprehensive'.

3 / 5

Completeness

It explicitly answers both questions: "Use when starting feature work that needs isolation... or before executing implementation plans" is a concrete when-clause, and "ensures an isolated workspace exists via native tools or git worktree fallback" is a clear what. Both are explicit with concrete trigger phrases, matching the top anchor rather than the 'when could be more explicit' anchor below it.

5 / 5

Trigger Term Quality

Natural trigger phrases are present — "starting feature work", "needs isolation", "before executing implementation plans", "git worktree" — and a user would plausibly say these. A few natural terms are missing, such as "worktree" as a standalone trigger, "parallel branch", or "isolated environment", so it falls just short of comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

The worktree-isolation niche is mostly distinct with its own triggers, but "before executing implementation plans" overlaps with plan-execution skills and could co-trigger. Minor overlap risk with closely related skills matches this anchor; the clear niche keeps it above the 'could still overlap' level.

4 / 5

Total

16

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

obra/superpowers

Path

skills/using-git-worktrees/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.