CtrlK
BlogDocsLog inGet started
Tessl Logo

cardputer-buddy

Iterate on the Cardputer-Adv MicroPython app bundle (Claude Buddy, Snake, Hello) after the device is already provisioned via m5-onboard. Use when the user wants to add a new app, push a single changed .py without re-flashing, watch device serial logs, or run a one-shot REPL command. Trigger on "add an app", "push to the cardputer", "tail the device", "run on the device", or follow-up work after /maker-setup.

76

Quality

93%

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

87%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 tight, highly actionable skill body with executable commands and clean section structure; its one weakness is that the add/push workflows lack explicit validation checkpoints and error-recovery loops.

Suggestions

Add an explicit verification step after pushing, e.g. run tail_serial.py and confirm the new app appears in the launcher menu, with a 'fix and re-push' note on failure.

For the 'Adding an app' flow, number the steps (crib → edit → push → verify on boot) so the sequence and checkpoint are unambiguous.

Note a recovery path when a pushed file errors on boot (watch tail_serial, revert or re-edit, re-push) to close the missing feedback loop.

DimensionReasoningScore

Conciseness

Lean and efficient — assumes Claude's competence (no MicroPython primer), uses terse prose and direct executable commands; every line earns its place. Not the 4 anchor because there is no over-explanation to trim.

5 / 5

Actionability

Fully executable, copy-paste-ready commands with real paths and flags (install_apps.py --src buddy, push.py --files, tail_serial.py, repl_run.py --script), plus concrete port examples covering the common cases.

5 / 5

Workflow Clarity

Sequences are present (crib from example → push; push/tail/REPL commands) but validation checkpoints are only implicit ('it appears on next boot') with no explicit verify step or error-recovery feedback loop. Not 4 because checkpoints are missing rather than merely gapped; not 2 because the steps are clearly defined.

3 / 5

Progressive Disclosure

A sub-50-line skill with well-organized sections (Device layout, Adding an app, Dev loop tooling) and no nested or buried references; the simple-skill exception applies, and no bundle files exist to require deeper structuring.

5 / 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.

A strong, well-targeted description that states concrete capabilities, gives explicit 'Use when' and 'Trigger on' guidance, and occupies a distinct niche. Third-person voice is maintained throughout.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'add a new app', 'push a single changed .py without re-flashing', 'watch device serial logs', 'run a one-shot REPL command' — with comprehensive coverage of the bundle's dev loop.

5 / 5

Completeness

Explicitly answers both 'what' (iterate on the Cardputer-Adv MicroPython app bundle after m5-onboard provisioning) and 'when' (a 'Use when...' clause plus an explicit 'Trigger on' list with concrete phrases).

5 / 5

Trigger Term Quality

Provides natural trigger phrases a user would say ('add an app', 'push to the cardputer', 'tail the device', 'run on the device', 'follow-up work after /maker-setup') alongside action synonyms, giving comprehensive coverage.

5 / 5

Distinctiveness Conflict Risk

A clear, narrow niche (Cardputer-Adv MicroPython bundle, post-m5-onboard) with device-specific triggers yields minimal overlap with other skills.

5 / 5

Total

20

/

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
anthropics/claude-plugins-official
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.