CtrlK
BlogDocsLog inGet started
Tessl Logo

setup-osn

Use when setting up or repairing a development environment for this repository on a machine — Bun at the pinned version, the GitHub CLI and its auth, SSH commit signing and the recommended git config, workspace dependencies, lefthook hooks and the portless dev proxy — and verifying it with the type-check, lint and format gates. Also the place to start when bun, gh, turbo or a hook is missing or the wrong version.

75

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

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 strong, highly operational skill body: concrete commands with per-step validation, thoughtful handling of environments where steps cannot run, and a clear reporting contract. The only weaknesses are mild — a couple of dense passages that could be tightened, and all content living in SKILL.md rather than split across reference files.

Suggestions

Split the environment-dependent detail (e.g., Step 8's portless proxy setup and Step 5's SSH signing walkthrough) into a reference file under references/ and keep a one-line pointer plus the gate-relevant command in SKILL.md.

Break the Step 7 bare-root paragraph into short labeled items (what it writes, what it never touches, what to tell the user) so the safety-relevant behavior is scannable rather than buried in a run-on sentence.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence — it never explains what Homebrew, SSH signing, or a linter is, and every section carries operational instructions rather than padding. It falls just short of the level-5 anchor because a few passages (the Step 7 bare-root paragraph and the portless CA aside) are dense run-ons that could be tightened without losing information.

4 / 5

Actionability

Nearly everything is copy-paste executable: `curl -fsSL https://bun.sh/install | bash -s "bun-v$(cat .bun-version)"`, the git-config table with per-setting check and apply commands, `bash scripts/setup.sh`, and the portless commands — and edge cases (no sudo, no network, non-macOS) each get concrete fallback commands. This matches the level-5 anchor; the `… true` ellipsis in the apply column is trivially resolved from the check column and does not create a real gap.

5 / 5

Workflow Clarity

Nine sequenced steps each embed verification (re-run `bun --version`, the three `gh` checks, `git config --global --list` confirmation, the three gates), with explicit failure handling ("If a gate fails, paste the shortest decisive lines into the table and keep going") and a mandatory final report. Clear sequence with explicit validation and error-recovery guidance matches the level-5 anchor.

5 / 5

Progressive Disclosure

No bundle files exist, and the body (~110 lines) keeps everything inline in SKILL.md; however it is well-sectioned and defers detail to real repo files one level deep ("Read `lefthook.yml` for what the hooks do", `scripts/setup.sh`, `wiki/conventions/devloop-urls.md`) instead of duplicating them. This fits the level-4 anchor (good structure, references clear, minor organization gaps); level 5 would require content appropriately split across files.

4 / 5

Total

18

/

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.

An excellent description: it states concrete capabilities, gives explicit and varied 'use when' triggers including failure states, uses appropriate voice, and is tightly scoped to this repository's environment. It is distinguishable from generic setup skills and free of fluff.

DimensionReasoningScore

Specificity

The description enumerates concrete, specific capabilities — "Bun at the pinned version, the GitHub CLI and its auth, SSH commit signing and the recommended git config, workspace dependencies, lefthook hooks and the portless dev proxy — and verifying it with the type-check, lint and format gates" — with comprehensive coverage of the skill's scope. It matches the level-5 anchor (multiple specific concrete actions) and exceeds level 4, which allows minor coverage gaps.

5 / 5

Completeness

It opens with an explicit "Use when setting up or repairing a development environment..." clause and adds a second explicit trigger ("Also the place to start when bun, gh, turbo or a hook is missing or the wrong version"), so both what and when are answered concretely. This matches the level-5 anchor; level 4 would require the 'when' to be less explicit or specific.

5 / 5

Trigger Term Quality

It covers natural trigger phrasing users would actually say — "setting up or repairing a development environment" plus tool-name triggers "bun, gh, turbo or a hook is missing or the wrong version", including failure-state variations. Coverage is comprehensive including synonyms (set up / repair, missing / wrong version), fitting the level-5 anchor rather than level 4's "a few natural terms missing".

5 / 5

Distinctiveness Conflict Risk

It carves a clear niche — this repository's dev environment with named tools (bun, gh, turbo, lefthook, portless) — so it is unlikely to trigger for unrelated skills. Minimal conflict risk matches the level-5 anchor; level 4 would require minor overlap with closely related skills, which the tool-specific naming avoids.

5 / 5

Total

20

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 4 missing

Warning

Total

15

/

16

Passed

Repository
englishstreetventures/osn
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.