Tessl • The management layer for AI agent skills

A dense, well-structured routing skill: it assumes Claude's competence, routes every task to a concrete subcommand with exit codes and validation gates, and splits detail correctly into two reference files and bundled script help text. The main weakness is that core workflows (create, push, restack) read as compressed contract prose rather than sequenced steps, and the basic create invocation is absent from the body.

Dimension	Reasoning	Score
Conciseness	The body never explains concepts Claude already knows (no git-worktree primer, no library background) and every sentence carries tool-specific contracts, paths, exit codes, or routing rules. Repeated "--help" pointers are navigational rather than padding.	5 / 5
Actionability	The body gives the executable launcher path, a command table, exact exit codes (75, 76, 1, 2), and copy-paste diagnostics such as "git -C <worktree> ls-files -- '.agents/'" and the "git rev-parse --path-format=absolute --git-common-dir" pointer. Held below 5 because the basic "create <ID> [<branch>]" invocation lives only in the frontmatter argument-hint, not the body, and several common flows defer entirely to "--help".	4 / 5
Workflow Clarity	The destructive/batch operations do have validation gates ("cleanup" previews by default and deletes only under "--apply"; removal recovery requires an explicit proof checklist where "Failed or unread proof stops recovery"; "fix-links" non-zero exits name unrestored paths), so the cap at 3 does not apply. However, the mainline create/push/restack flows are described as dense contract prose rather than clearly sequenced steps, leaving minor sequencing gaps.	4 / 5
Progressive Disclosure	SKILL.md is a genuine overview: both [references/hooks.md](references/hooks.md) and [references/session-guard.md](references/session-guard.md) are real one-level-deep files, each introduced with a descriptive lead-in, and the bulk of per-command detail is routed to the bundled scripts' "--help". Verified against the actual bundle structure; no inlined content belongs in separate files.	5 / 5
	Total	18 / 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, distinctive description with concrete verbs, but it omits any "when to use" trigger clause and under-represents the skill's full command surface. Adding a "Use when..." sentence would lift completeness; naming a few more capabilities (restack, cleanup, fix-links) would close coverage gaps.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to create, remove, list, or push a git worktree, or to repair a broken worktree or its symlinks."

Mention additional capabilities the skill supports (restack, cleanup of merged worktrees, fix-links symlink repair, merged-PR lookup) so the description matches the body's command table.

Optionally include a natural synonym such as "isolated working copy" so users who don't say "worktree" still trigger the skill.

Dimension	Reasoning	Score
Specificity	"create, list, remove, push, or repair a git worktree" names the domain plus five concrete actions, but the skill also implements restack, cleanup, merged, and fix-links, leaving minor coverage gaps.	4 / 5
Completeness	The "what" is clear (create, list, remove, push, repair a git worktree) but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	"git worktree" with the natural verbs "create", "remove", "push", "repair" covers the phrases a user would say, but common synonyms like "working copy" or "delete" are absent.	4 / 5
Distinctiveness Conflict Risk	"git worktree" is a clear niche with distinct, specific triggers (create/remove/push/repair a worktree); minimal overlap risk with other skills.	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: 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?