CtrlK
BlogDocsLog inGet started
Tessl Logo

004-commands-installation

Use when you need to install the embedded project commands into command directories (.github/commands, .claude/commands, .cursor/command, .codex/commands), selecting the destination interactively and copying the embedded command definitions from project assets. This should trigger for requests such as Install embedded commands; Bootstrap .cursor/command; Bootstrap .claude/commands; Copy project commands; Install project command suite. Part of Plinth Toolkit

65

Quality

82%

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

72%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 well-structured, token-efficient overview that correctly delegates detailed steps to an existing one-level-deep reference with a matching asset bundle. Its main weakness is workflow presentation: no explicit step sequence or validation/verification checkpoint for what is a batch, potentially overwriting operation, plus the confusing 'XInclude' claim and duplicated trigger/constraint sections.

Suggestions

Replace the implicit ordering with a short numbered sequence (ask destination → create directory → copy all 14 files → report results) and add an explicit verification step (e.g., list the destination directory and diff against the source) so the batch operation is not left without a checkpoint.

Remove or correct the phrase 'defined via XInclude from assets/commands' — the commands are plain markdown files listed in the reference; the current wording is inaccurate and could mislead execution.

De-duplicate the body: drop the 'When to use this skill' section (it repeats the frontmatter description triggers) and the redundant constraint bullets so the body states each requirement once.

DimensionReasoningScore

Conciseness

The ~40-line body is lean, assumes competence, and explains nothing Claude already knows. Minor trimming is possible: the "When to use this skill" section duplicates the frontmatter description's trigger list, and the "Constraints" bullets restate the "What is covered" bullets — minor over-explanation, not a 3.

4 / 5

Actionability

The MUST constraints are concrete and testable — "copy all embedded command files from skill assets/commands/", "create the destination directory if it does not exist", four exact destination paths, and explicit ask-before-write ordering. It is not a 5 because the exact file list and copy mechanics are deferred to the reference, and the phrase "defined via XInclude from assets/commands" is an inaccurate/confusing detail (the reference lists plain markdown files, no XInclude mechanism).

4 / 5

Workflow Clarity

A sequence is discernible (ask destination → copy all commands → report overwrites) via the coverage bullets and MUST constraints, but there are no numbered steps and no validation checkpoint in the body. Per the batch-operation guideline (14 files, overwriting existing targets), missing validation caps this at 3 even though the constraint ordering implies the sequence.

3 / 5

Progressive Disclosure

The body is a clean overview (coverage, constraints, when-to-use) with a single well-signaled one-level-deep link, references/004-commands-installation.md, which exists and holds the detailed step-by-step procedure; the assets/commands/ bundle (14 files) matches the file list in that reference. Structure and navigation match the top anchor.

5 / 5

Total

16

/

20

Passed

Description

83%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: explicit 'Use when' trigger guidance with verbatim trigger phrases, concrete destination paths, and a well-defined niche. Minor gaps are missing natural synonyms for triggering requests and slight overlap risk with sibling toolkit skills.

DimensionReasoningScore

Specificity

Concrete actions are named — "install the embedded project commands into command directories (.github/commands, .claude/commands, .cursor/command, .codex/commands), selecting the destination interactively and copying the embedded command definitions from project assets" — with all four destination paths explicit. It stays at 4 rather than 5 because the skill performs essentially one core action (copying a bundle) rather than multiple distinct concrete capabilities.

4 / 5

Completeness

It explicitly answers what ("install the embedded project commands... selecting the destination interactively and copying the embedded command definitions from project assets") and when ("Use when you need to... This should trigger for requests such as...") with a list of concrete trigger phrases — matching the top anchor exactly.

5 / 5

Trigger Term Quality

Natural trigger phrases are provided verbatim: "Install embedded commands; Bootstrap .cursor/command; Bootstrap .claude/commands; Copy project commands; Install project command suite." Coverage of 'install/bootstrap/copy' phrasings is good but misses common variations users might say (e.g., 'set up commands', 'add commands', 'scaffold'), so it is not a 5.

4 / 5

Distinctiveness Conflict Risk

The "embedded project commands" scope, exact directory paths, and "Part of Plinth Toolkit" qualifier carve out a clear niche with distinct triggers. It is not a 5 because phrases like "Copy project commands" and "Install project command suite" remain generic enough to overlap with sibling installer skills in the same toolkit family.

4 / 5

Total

17

/

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
jabrena/plinth
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.