CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

scotty

Run and troubleshoot Bead Me Up, Scotty, the local web UI for Beads, in Docker or rootless Podman. Use when starting or stopping the Beads UI, changing compose.yaml or docker/scotty/Dockerfile, fixing "permission denied" on .beads, SCOTTY_USER, podman-docker or docker compose problems, a Scotty board that shows 0 beads, the scotty-config volume, or bumping the Scotty or bd version.

Quality

95%

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

96%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.

An excellent operational skill body: dense, executable, and validated, with destructive-operation warnings and symptom-indexed troubleshooting. The only structural critique is that everything lives in the one file at ~87 lines, slightly over what a simple no-reference skill would be.

Suggestions

Move the step-by-step 'Empty board (0 beads)' recovery walkthrough into a references/recovery.md and keep only the confirmation steps and the 'never force-push' warning in SKILL.md, keeping the main file a lean overview.

Relocate the version-bump procedure ('change compose.yaml..., then docker compose build --no-cache scotty') to a short reference so routine run/stop usage does not load it.

DimensionReasoningScore

Conciseness

Nearly every line carries repo-specific facts Claude cannot know (e.g. 'In the image node is just a symlink to bun', 'The Dockerfile creates that directory with mode 0777', 'SCOTTY_USER="$(id -u):$(id -g)" does not fix rootless Podman'). No padding or explanation of concepts Claude already knows; the one inline version number ('default 1.4.4') sits in the Versions section where version facts belong. Matches 'lean and efficient; every token earns its place'.

5 / 5

Actionability

Fully copy-paste-ready commands throughout: 'bun run scotty:up', 'SCOTTY_USER=0:0 bun run scotty:up', 'chmod -R a+rX .beads', 'mv .beads/embeddeddolt ".beads/embeddeddolt.empty-$(date +%Y%m%d-%H%M%S)"', 'bun x bd bootstrap -y', 'git ls-remote origin refs/dolt/data', plus a symptom-to-fix table. This matches the 'fully executable; specific examples cover the common cases' anchor.

5 / 5

Workflow Clarity

The 'Empty board' recovery is a numbered sequence with explicit validation checkpoints ('bun x bd stats must show a non-zero total', 'a SHA means history exists'), a fallback path for divergent histories, and a destructive-operation guard ('Never bd dolt push --force'). Quick diagnosis gives symptom-to-fix feedback loops. This matches the top anchor: clear sequence, explicit validation, error-recovery guidance.

5 / 5

Progressive Disclosure

The single file is well organized with clear section headers and tables, and there are no nested or orphaned references (no bundle files exist). However, at ~87 lines it exceeds the under-50-line simple-skill case, and some operational detail (e.g. the version-bump procedure and the full recovery walkthrough) is inlined that could live in a reference file, matching 'good structure; most content appropriately placed; minor organization gaps' rather than a clearly split overview.

4 / 5

Total

19

/

20

Passed

Description

91%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 description: third-person, concise, with an explicit 'Use when' clause packed with the exact file paths, env vars, and error strings users will actually encounter. Its only weakness is minor overlap risk from the broad 'docker compose problems' trigger and the bd-version trigger shared with the companion beads skill.

DimensionReasoningScore

Specificity

Concrete actions are 'Run and troubleshoot' plus enumerated fix scenarios ('fixing "permission denied" on .beads', 'a Scotty board that shows 0 beads', 'bumping the Scotty or bd version'), matching the 'lists several specific actions; minor gaps' anchor. Not a 5 because the action verbs themselves are only two, with the rest expressed as situations rather than capabilities, so coverage is not fully comprehensive.

4 / 5

Completeness

It explicitly answers both: what ('Run and troubleshoot Bead Me Up, Scotty, the local web UI for Beads, in Docker or rootless Podman') and when ('Use when starting or stopping the Beads UI, changing compose.yaml...') with a concrete trigger list. This matches the anchor for a clear what AND an explicit 'Use when' clause with concrete trigger phrases; a 4 would require the when to be less explicit, which it is not.

5 / 5

Trigger Term Quality

Comprehensive natural terms including exact artifacts and error strings a user would hit: 'compose.yaml or docker/scotty/Dockerfile', 'permission denied', 'SCOTTY_USER', 'podman-docker', '0 beads', 'the scotty-config volume'. These are the literal phrases that appear in real sessions, matching the anchor's 'including synonyms and file extensions' level; no common variation is missing.

5 / 5

Distinctiveness Conflict Risk

Triggers are largely unique to this niche ('SCOTTY_USER', 'scotty-config volume', 'docker/scotty/Dockerfile'), so mostly distinct with only minor overlap risk — e.g. 'docker compose problems' and 'bumping the... bd version' slightly overlap with a general Docker skill and the companion 'beads' skill. Not a 5 because of that minor overlap with closely related skills; not a 3 since the overwhelming majority of triggers could not fire any other skill.

4 / 5

Total

18

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

williamrjribeiro/bun-agentic-starter

Path

.agents/skills/scotty/SKILL.md

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.