CtrlK
BlogDocsLog inGet started
Tessl Logo

worktrail-repo-init

Bootstrap a new repo, or migrate an existing single-branch repo, onto the workspace's repo-standards doctrine (~/rules/CLAUDE.repo.md): the AGENTS.md-is-truth/CLAUDE.md-imports-it split, a dev/prd, dev/stg/prd, or main-only (trunk) branch model with matching GitHub rulesets, an OpenSpec scaffold, an auto-merge workflow, and a seeded .worktrail/policy.yaml. Trigger phrases: "onboard this repo", "apply repo standards", "initialize repo standards", "set up this repo like the rest of the fleet", "bring this repo into line with the repo standards doctrine".

69

Quality

86%

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

SKILL.md
Quality
Evals
Security

Quality

Content

73%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, project-specific operational guide: concrete commands, a clearly sequenced workflow with real validation checkpoints and user-confirmation gates around the destructive apply step, and proper deferral of branch-model detail to a real reference file. Its weaknesses are density-driven: the Best Practices section and the add-on flag paragraphs repeat caveats and could be tightened or split into reference files, and the PR-creation step could be spelled out as concretely as the others.

Suggestions

Tighten the --with-aspens and --with-gitnexus paragraphs: they both end with the same best-effort/'only reliable success signal' caveat and could share one sentence covering both flags, cutting ~10 lines from the propose step.

Move the .worktrail/policy.yaml and gitleaks bullets (and the add-on flag rationale) from Best Practices into a references/ file (e.g. references/scaffold-details.md) so SKILL.md stays a lean overview, matching how branch-model-decision.md is already handled.

Make Step 3 as concrete as Steps 2 and 4: give the actual git add/commit/gh pr create command sequence (with a suggested commit message and PR-body skeleton) instead of describing the standard workflow, and show a minimal required_status_checks hand-edit example for the ci_jobs_discovered case in Step 2.

DimensionReasoningScore

Conciseness

Almost all content is project-specific knowledge Claude cannot be assumed to have (doctrine file paths, CLI flag semantics, GitHub App credentials), so it avoids explaining known concepts — but the body is noticeably long and could be tightened: 'the only reliable success signal available' appears nearly verbatim in both the --with-aspens and --with-gitnexus bullets, 'don't default it on' is repeated in the same paragraph pair, and several multi-line parentheticals restate their justification twice. This fits anchor 3 ('mostly efficient but includes some unnecessary explanation or could be tightened') better than anchor 4, where over-explanation would be only minor.

3 / 5

Actionability

Two copy-paste-ready bash blocks ('git worktree add ../<repo>-worktrees/repo-standards -b repo-standards <current-default-branch>' / 'worktrail-repo-init propose --repo . --branch-model 2 --json'; 'git checkout <old-default-branch> && git pull' / 'worktrail-repo-init apply --repo . --json') plus concrete JSON fields to review ('written/skipped/warnings', 'ci_jobs_discovered', 'branches/default_branch/.../rulesets'). Minor gaps keep it at 4 rather than 5: Step 3's 'git add, commit, push, gh pr create' is gestured rather than given as a command, and the hand-edit of required_status_checks in Step 2 is described but never shown with an example diff.

4 / 5

Workflow Clarity

A clear four-step sequence (decide branch model → worktree + propose → commit/push/PR → apply) with explicit validation checkpoints: review the propose JSON's written/skipped/warnings and ci_jobs_discovered before committing, explicit user confirmation before the destructive apply, 'Any FAILED entry means apply exited non-zero — investigate and re-run', and a manual-follow-up checklist. This matches anchor 5 (validation steps, feedback loops, checklist) despite the destructive operations — the guideline capping destructive skills at 3 applies only when validation is missing, and it is not.

5 / 5

Progressive Disclosure

Good structure: Overview → When to Use → Instructions (4 steps) → Examples → Best Practices, with a well-signaled one-level-deep reference ('Read references/branch-model-decision.md before choosing --branch-model') that exists in the bundle and contains exactly the deferred detail, with the body keeping only 'the short version'. Not a 5 because the body still inlines ~240 lines of detail — the long --with-aspens/--with-gitnexus paragraphs and the .worktrail/policy.yaml and gitleaks bullets in Best Practices are candidates for a second reference file — which fits anchor 4's 'most content is appropriately placed; minor organization gaps'.

4 / 5

Total

16

/

20

Passed

Description

100%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 is exemplary: third-person, concrete about every deliverable, and it closes with explicit trigger phrases that make both the 'what' and the 'when' unambiguous. Its density is informational rather than padded, and its workspace-specific scope makes conflict with other skills unlikely.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'the AGENTS.md-is-truth/CLAUDE.md-imports-it split, a dev/prd, dev/stg/prd, or main-only (trunk) branch model with matching GitHub rulesets, an OpenSpec scaffold, an auto-merge workflow, and a seeded .worktrail/policy.yaml' — with comprehensive coverage of what the skill does. It is dense but every clause names a concrete deliverable, not padding; score 4 would require minor gaps in coverage, which aren't present.

5 / 5

Completeness

It explicitly answers 'what' (bootstrap or migrate a repo onto the doctrine with the enumerated artifacts) and 'when' (the explicit 'Trigger phrases:' clause). The anchor-5 example pattern — capabilities followed by concrete trigger guidance — is followed exactly; a 4 would require the 'when' to be less explicit, which it is not.

5 / 5

Trigger Term Quality

Five explicit, natural trigger phrases are provided verbatim: 'onboard this repo', 'apply repo standards', 'initialize repo standards', 'set up this repo like the rest of the fleet', 'bring this repo into line with the repo standards doctrine'. These cover synonyms and phrasings a user would actually say; anchor 5's 'comprehensive coverage of natural terms including synonyms' is matched, and anchor 4's 'a few natural terms missing' does not apply.

5 / 5

Distinctiveness Conflict Risk

It carves out a clear niche — onboarding repos under ~/projects/ onto this workspace's repo-standards doctrine (~/rules/CLAUDE.repo.md) — with trigger phrases ('onboard this repo', 'bring this repo into line with the repo standards doctrine') unlikely to collide with any general-purpose skill. Minimal conflict risk; anchor 5 fits.

5 / 5

Total

20

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 4 missing, 4 deeper-than-1-level

Warning

Total

13

/

16

Passed

Repository
behindthedash/worktrail
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.