CtrlK
BlogDocsLog inGet started
Tessl Logo

using-git-worktrees

Use this whenever you need to create an isolated workspace.

45

Quality

56%

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 ./.agency/plugins/nori/skills/using-git-worktrees/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

70%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 operational document: an explicit, well-validated workflow with concrete commands, feedback loops, and recovery procedures. Its weaknesses are redundancy — the same rules appear in the required steps, the Maintaining Working Directory section, Common Mistakes, and two Red Flags sections — and a monolithic single-file layout with no reference files for secondary material.

Suggestions

Consolidate the duplicated rule content: merge the two 'Red Flags' sections and fold 'Common Mistakes' into them, since both restate the required steps' rules (gitignore verification, test baseline, ask-on-failure).

Replace the deprecated 'TodoWrite' instruction in the <required> block with the current task-list tool name, and define $BRANCH_NAME/$path with a concrete example line so every snippet is copy-paste ready.

Move 'Common Mistakes', 'Red Flags', and 'Example Workflow' into a single reference file (e.g. references/troubleshooting.md) linked from the body, keeping SKILL.md as a lean workflow overview.

DimensionReasoningScore

Conciseness

Most of the body is lean executable command blocks, but there is genuine padding: the working-directory rule from step 7 is restated as an entire 'Maintaining Working Directory' section, 'Red Flags' appears as both a subsection and a top-level section with overlapping bullets, and 'Common Mistakes' largely repeats those same rules. This fits 'Mostly efficient but includes some unnecessary explanation or could be tightened' — the duplication is real but interleaved with efficient command content, so it does not drop to 'several unnecessary explanations or padded sections'.

3 / 5

Actionability

Nearly all guidance is executable: concrete git/grep/npm/cargo commands, an auto-detect setup script, a report template, and verify commands (pwd, git branch). Minor gaps keep it below 5: '$BRANCH_NAME' and '$path' are placeholders never defined in a runnable line, and the multi-language setup snippet is presented as one block without a wrapping loop or explanation of how to run it per-project.

4 / 5

Workflow Clarity

The 7-step sequence is explicit with validation checkpoints throughout: .gitignore verification before worktree creation, an explicit baseline test run, a feedback loop ('If tests fail: Report failures, ask whether to proceed or investigate'), recovery steps for accidentally exiting the worktree, and a report format. This matches the top anchor 'Clear sequence with explicit validation steps; feedback loops for error recovery'.

5 / 5

Progressive Disclosure

There are no bundle files at all — the skill is a ~180-line single document with section headers but no external references, and secondary material ('Common Mistakes', 'Red Flags', 'Example Workflow') that would naturally live in a reference file is inlined. This fits 'Some structure but could be better organized; content that should be separate is inline'; it is not a 2 because headers provide genuine navigability and nothing is buried or nested.

3 / 5

Total

15

/

20

Passed

Description

25%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 provides an explicit trigger clause but almost nothing else: it never mentions git worktrees or any concrete capability, and it omits every natural trigger term a user would say when needing this skill. It functions as a bare 'when' with a vague object, which both limits discoverability and invites conflicts with other environment-setup skills.

Suggestions

State the concrete 'what' up front, e.g. 'Creates an isolated git worktree with its own branch, verifies .gitignore, auto-detects and runs project setup, and establishes a clean test baseline.'

Add natural trigger terms users would say: 'worktree', 'git worktree', 'work tree', 'parallel branch', 'isolated copy of the repo'.

Use third-person voice consistent with the trigger clause (e.g. 'Creates... Use when the user asks for a worktree or an isolated copy of the repository') rather than the bare imperative 'Use this'.

DimensionReasoningScore

Specificity

The description names only one generic action, "create an isolated workspace", with no concrete capabilities (git worktree creation, project setup, dependency install, test baseline verification). This matches the anchor 'Names the domain but actions are minimal or generic' — it does not even name the git worktree domain, but the single stated action keeps it above a score of 1, which requires entirely vague language with no actions at all.

2 / 5

Completeness

A 'when' clause is present ("Use this whenever you need to create an isolated workspace"), but the 'what' is vague — the skill's actual capabilities (creating git worktrees, verifying .gitignore, auto-detecting project setup, running baseline tests) are never stated. This matches anchor 2 ('Has a vague what...') rather than anchor 3, which requires a clear 'what' but missing 'when' — here the situation is inverted.

2 / 5

Trigger Term Quality

Only one keyword phrase ("isolated workspace") appears; the natural terms a user would actually say — "worktree", "git worktree", "work tree", "parallel branch", "separate working directory" — are all missing. It sits between anchor 1 (no natural keywords) and anchor 3 (some relevant keywords with missing variations); one generic phrase is closer to 'one or two generic keywords; missing the natural phrases users say'.

2 / 5

Distinctiveness Conflict Risk

"Create an isolated workspace" is generic enough to collide with sandbox setup, containerization, virtualenv, and general environment-setup skills. It does not score 3 because the absence of any git/worktree-specific term leaves high overlap risk with many related skills, matching 'Very broad; high overlap risk with many similar skills'.

2 / 5

Total

8

/

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
microsoft/FluidFramework
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.