Tessl • The management layer for AI agent skills

Blog Docs Log inGet started

SkillPublic

worktree

Load to create, list, remove, push, or repair a git worktree.

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/worktree/SKILL.md

Quality

Content

78%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 dense, contract-style body that provides real commands, exit codes, and validation gates for destructive flows, and splits detail cleanly across two existing one-level reference files and script --help output. Its weaknesses are extreme prose compression that occasionally obscures the operating sequence and the lack of a single worked example invocation.

Dimension	Reasoning	Score
Conciseness	The body explains no known git concepts and aggressively defers detail ("Every command's contract is its `--help`"). It is not 5 because a few passages (the squash-merge paragraph, the removal proof rules) repeat ideas or are compressed to the point of needing rereads, so minor trimming would help.	4 / 5
Actionability	Concrete executable commands are present (`git -C <worktree> ls-files -- '.agents/'`, the `git rev-parse --path-format=absolute --git-common-dir` pointer command), with specific exit codes (75, 76, 1, 2) and real flags (`--targets-only`, `--apply`). Not 5: no worked example invocation (e.g. `worktree create <ID> --base main`) and full flag detail is deferred to --help.	4 / 5
Workflow Clarity	Recovery workflows are clearly sequenced with explicit validation gates: the manual-removal proof checklist ("Failed or unread proof stops recovery"), the preview-then-`--apply` pattern for destructive pruning, and the deterministic two-case `.agents` routing. The destructive-operation cap at 3 does not apply since validation is present; the score is 4 rather than 5 because the primary create/push sequences are delegated to --help instead of stated inline.	4 / 5
Progressive Disclosure	The body is an overview with a command table, and details are appropriately split into two one-level-deep reference files that exist in the bundle and are clearly signaled inline ([references/hooks.md](references/hooks.md), [references/session-guard.md](references/session-guard.md)), with scripts' --help as the terminal detail layer. Both reference files point back to SKILL.md/--help rather than chaining further, and section headers make navigation easy.	5 / 5
	Total	17 / 20 Passed

Description

70%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 concise, specific, and distinctive description that names five concrete worktree operations. Its main weakness is the absence of any explicit 'Use when...' trigger clause, leaving the invocation timing only implied, and natural synonyms such as 'delete' or 'prune' are missing.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user mentions worktrees, git worktree, or wants parallel branches or isolated checkouts."

Include natural synonyms users would say, such as "delete a worktree", "prune worktrees", or the plural "worktrees".

If the token budget allows, mention one or two of the uncovered capabilities (e.g. cleaning up merged worktrees, restacking) so the description reflects the full command surface.

Dimension	Reasoning	Score
Specificity	"create, list, remove, push, or repair a git worktree" names the domain plus five concrete verbs, matching the 'several specific actions; minor gaps in coverage' anchor. It is not 5 because the skill also supports restack, cleanup, merged, and check, so coverage is not comprehensive.	4 / 5
Completeness	The 'what' is clear (five concrete worktree operations), but there is no "Use when..." clause or equivalent explicit trigger guidance; the 'when' is only weakly implied through the verb list, which caps completeness at 3 per the rubric guideline. Not 4, which requires an explicit if imperfect 'when' clause.	3 / 5
Trigger Term Quality	"git worktree" plus natural action verbs (create, remove, list, push, repair) give good keyword coverage users would naturally say. Falls short of 5 because common synonyms like "delete", "prune", "set up", or "isolated checkout" are absent.	4 / 5
Distinctiveness Conflict Risk	"git worktree" is a clear niche and every verb is scoped to worktrees ("push... a git worktree"), giving distinct triggers with minimal conflict risk — a direct match to the anchor-5 example's pattern.	5 / 5
	Total	16 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: vanillagreencom/kendex
Path: .agents/skills/worktree/SKILL.md
Revision: 32d7bc7

Reviewed: 13 hours ago

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.

worktree

Table of Contents

Is this your skill?