dev-worktree

AI DevKit · Worktree setup and resume guidance for isolated feature work. Use when starting, resuming, switching, or verifying a feature branch/worktree for lifecycle, debugging, implementation, review, or multi-agent workflows.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

82%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 tight, executable skill body: lean imperative steps, concrete git and package-manager commands, and explicit verification and approval checkpoints. The gaps are minor — undefined heuristics (project-root detection, ecosystem detection, "clean enough"), no error-recovery guidance when a checkpoint fails, and a bootstrap command inventory that could move to a reference file.

Suggestions

Add concrete commands for the undefined steps, e.g. `git rev-parse --show-toplevel` for project-root detection and a lockfile-to-manager mapping for ecosystem detection.

Add an error-recovery branch for the verification checkpoint (e.g., what to do when `git -C .worktrees/feature-<name> branch --show-current` does not return `feature-<name>`), and define what "clean enough for the requested work" means.

Consider moving the per-ecosystem dependency-install command inventory to a references/ file, keeping SKILL.md as a shorter overview with a clearly signaled pointer.

Dimension	Reasoning	Score
Conciseness	The body is lean and imperative throughout ("Ensure `.worktrees` is listed in the project `.gitignore`; if not, add it"), and the one explanatory passage (stale built artifacts causing "errors that look like code regressions") conveys genuinely non-obvious operational knowledge. Every token earns its place, matching anchor 5 rather than anchor 4 where trimmable over-explanation would remain.	5 / 5
Actionability	Mostly executable guidance with concrete commands ("git worktree add -b feature-<name> .worktrees/feature-<name>", "git -C .worktrees/feature-<name> branch --show-current", and per-ecosystem install commands). Minor gaps keep it at anchor 4: "Determine the project root, the directory containing `.git`" and "Detect ecosystem from lockfiles, manifests, and tooling configs" lack concrete commands, and "clean enough for the requested work" is undefined.	4 / 5
Workflow Clarity	Sequences are clearly ordered with explicit checkpoints (step 9's "it must equal `feature-<name>`" verification, "wait for approval before switching"), matching anchor 4. It falls short of anchor 5 because error-recovery feedback loops are absent: nothing says what to do if the branch-verification or clean-worktree check fails.	4 / 5
Progressive Disclosure	Well-organized self-contained sections (Phase Contract, Start, Resume, Dependency Bootstrap, Output) with no buried or nested references and no inlined content that clearly belongs elsewhere. At 68 lines it exceeds the under-50-line simple-skill exemption for a score of 5, and the per-ecosystem bootstrap command inventory is a plausible candidate for a separate reference file, so anchor 4 fits best.	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 and well-enumerated "Use when" trigger clause and a clear worktree niche. Its main weaknesses are thin capability specificity (setup/resume only, no concrete operations) and a broad trailing context list that raises overlap risk with general development skills.

Suggestions

Name 2-3 concrete operations in the what-clause (e.g., "create and reuse project-local git worktrees, verify branch context, and bootstrap dependencies") to lift specificity.

Trim the broad context list "for lifecycle, debugging, implementation, review, or multi-agent workflows" to worktree-specific triggers to reduce conflict risk with general dev-workflow skills.

Add common user phrasings such as "new feature", "git worktree", or "switch branches" as trigger synonyms for fuller keyword coverage.

Dimension	Reasoning	Score
Specificity	"Worktree setup and resume guidance" names the domain plus 1-2 concrete actions (setup, resume) but stops short of listing several specific capabilities, matching the anchor for domain plus limited concrete actions. It is above level 2 because real actions are named, but below level 4 because the actions remain high-level.	3 / 5
Completeness	It explicitly answers what ("Worktree setup and resume guidance for isolated feature work") and when ("Use when starting, resuming, switching, or verifying a feature branch/worktree") with concrete trigger phrases, matching anchor 5. It is above anchor 4 because the when-clause is specific and enumerated rather than merely present.	5 / 5
Trigger Term Quality	"Use when starting, resuming, switching, or verifying a feature branch/worktree" covers natural phrasings users would say, though common variations like "new feature", "git worktree", or "switch context" are absent. Good coverage with a few missing terms fits anchor 4 rather than the comprehensive synonym coverage of anchor 5.	4 / 5
Distinctiveness Conflict Risk	The worktree/git-workspace niche is mostly distinct, but the trailing "for lifecycle, debugging, implementation, review, or multi-agent workflows" broadens it toward general dev-workflow skills with minor overlap risk. This fits anchor 4; anchor 5 would require a tight niche with no broadening triggers.	4 / 5
	Total	16 / 20 Passed

Validation

100%

Warnings & errors only

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: codeaholicguy/ai-devkit
Path: skills/dev-worktree/SKILL.md
Commit: 7ef0cd5

Reviewed: 8 days ago

Table of Contents

Discovery Implementation Validation

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.