CtrlK
BlogDocsLog inGet started
Tessl Logo

worktrunk

Guidance for Worktrunk (the `wt` CLI) — git worktree management, hooks, and config. Load when working out which worktree a `wt` command will act on, or reaching for the global `-C <path>` to target one; editing .config/wt.toml or ~/.config/worktrunk/config.toml; adding, modifying, or debugging hooks (post-merge, post-start, pre-commit, pre-merge, post-switch, etc.); configuring commit message generation or command aliases; or troubleshooting wt behavior. Also answers general worktrunk/wt questions.

73

Quality

90%

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 worktrunk in max-sixty/worktrunk

SKILL.md
Quality
Evals
Security

Quality

Content

88%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, actionable body that assumes Claude's competence and gives executable guidance with clear workflows and validation. Its main weakness is that the in-skill references point to a reference/ bundle that is not actually present.

Suggestions

Ship the referenced reference/*.md bundle files (config.md, hook.md, switch.md, extending.md, llm-commits.md, tips-patterns.md, shell-integration.md, troubleshooting.md, step.md) so the in-skill navigation links resolve to real content.

Trim a few explanatory parenthetical asides (e.g. 'which marker still rejects, since it keys state by branch name') to tighten conciseness without losing the wt-specific guidance.

Verify each reference/ path cited in the 'Common tasks reference' section exists with the named anchor (e.g. extending.md#aliases, step.md#wt-step-for-each) so deep links are not broken.

DimensionReasoningScore

Conciseness

Dense, competence-assuming prose with no tutorial padding about git/worktrees; mostly efficient, though a few explanatory asides (e.g. the marker branch-keying note) could be trimmed.

4 / 5

Actionability

Provides concrete, copy-paste-ready commands and examples across the common cases — wt config/switch/step commands, TOML hook pipelines, and tmux/Zellij/parallel-sub-agent spawn patterns.

5 / 5

Workflow Clarity

Multi-step workflows are explicitly sequenced with validation checkpoints (detect-tools→propose→approve→dry-run verify; derive-commands→verify-they-run→test-hooks), and the hook-approval escalation gives a clear feedback loop for a destructive/security-sensitive operation.

5 / 5

Progressive Disclosure

References to reference/*.md files are well-signaled, one level deep, and organized via a documentation listing and a task-to-reference map, but the referenced reference/ bundle directory is absent on disk, so the navigation points to missing files.

4 / 5

Total

18

/

20

Passed

Description

92%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, third-person description that clearly states the tool's purpose and enumerates concrete 'Load when...' trigger scenarios. It is specific, comprehensive, and unlikely to be confused with other skills.

DimensionReasoningScore

Specificity

Names the domain (git worktree management, hooks, config) and lists multiple concrete actions — targeting worktrees, editing config files, adding/debugging hooks, configuring commit message generation and aliases, troubleshooting — covering the tool's surface comprehensively.

5 / 5

Completeness

Explicitly answers both 'what' (worktree management, hooks, config) and 'when' via a concrete 'Load when...' clause enumerating specific trigger scenarios.

5 / 5

Trigger Term Quality

Strong natural-term coverage ('git worktree', 'hooks', 'config', 'commit message generation', 'command aliases', 'troubleshooting wt behavior') with the wt/worktrunk synonym, though a few natural phrasings and synonyms are not exhaustively enumerated.

4 / 5

Distinctiveness Conflict Risk

Clearly scoped to the Worktrunk/wt CLI with distinct triggers (wt commands, specific config paths, named hook events), giving it a clear niche with minimal overlap risk.

5 / 5

Total

19

/

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
max-sixty/worktrunk
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.