CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cli-commands

Use when adding or modifying CLI command (`but` commands) under `crates/but/src`.

Quality

72%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/cli-commands/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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, concrete walkthrough that teaches the repo's command-implementation pattern through a fully worked `commit3` example, with virtually no filler or explanation of concepts Claude already knows. Its main weaknesses are repetitive restatement of the resolve/run split and elided function bodies in the skeleton. Overall it is an efficient, highly actionable skill guide.

DimensionReasoningScore

Conciseness

The body is dense with repo-specific conventions (CliIdArg vs String, IntermediateChannel vs OutputChannel, ERROR_EXAMPLES, theme newtypes, bad_input) and assumes Claude already knows Rust and clap rather than explaining them. The resolve/run division of labor is restated across several overlapping notes ("resolve returns CliResult because...", "run returns anyhow::Result because...", "run() loads current repository state...", "A non-CLI caller such as the TUI..."), which is minor over-explanation that could be trimmed, so it does not reach 'every token earns its place'.

4 / 5

Actionability

It provides concrete, near-copy-paste Rust code for each phase — the full `Platform` args struct, the `Subcommands` registration, the match arm, and the commit/resolve/run skeleton with `CliOutput` impls — plus specific types and helpers to use. Minor gaps remain: the `resolve` and `run` bodies are elided with `// ...` and the match arm includes uncommented context like `InitCtxOptions`, so it is mostly rather than fully executable.

4 / 5

Workflow Clarity

The implementation sequence is clear and correctly ordered — Arguments, Handling the command, Implementing the command, More examples — with each step carrying concrete code and conventions. There is no explicit verification checkpoint for the implementer (e.g., building the command or checking `--help` output), which is a minor validation gap rather than an absent sequence.

4 / 5

Progressive Disclosure

The single file is well-organized into four clearly headed sections, and the 'More examples' section points to four real source files in the repo as one-level-deep, clearly signaled references. At ~245 lines with no bundle files, some of the extended 'Things to note' material could live in a reference file, which keeps it below the clear-overview-with-well-signaled-references anchor.

4 / 5

Total

16

/

20

Passed

Description

56%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 has a clear, well-scoped trigger and good natural keywords for someone working in this codebase, with minimal conflict risk. Its main weakness is that it omits any statement of what the skill provides, leaving the 'what' half of the equation entirely implicit. Adding a capability clause before the 'Use when' clause would materially improve it.

Suggestions

Add a 'what' clause stating the skill's content, e.g., "Provides the standard structure for implementing `but` CLI commands: argument types, dispatch wiring, and the resolve/run split. Use when adding or modifying CLI commands under `crates/but/src`."

List the concrete phases the skill covers (defining args in `args/`, adding the match arm in `lib.rs`, implementing resolve/run) to raise specificity beyond the two generic verbs 'adding or modifying'.

Include a couple of natural trigger variations such as "subcommand" or "CLI argument" so users phrasing the request differently still match.

DimensionReasoningScore

Specificity

The description names its domain ("CLI command (`but` commands) under `crates/but/src`") and exactly two actions ("adding or modifying"), which matches the anchor for 1-2 concrete actions without comprehensive coverage. It never states what the skill actually provides (e.g., argument structuring, dispatch wiring, resolve/run conventions), so it does not reach 'several specific actions'.

3 / 5

Completeness

The description is entirely a 'when' clause ("Use when adding or modifying CLI command...") with no 'what' — nothing states what the skill does or contains. This matches the anchor 'only when is present without what'; it cannot score 3, which requires a clear 'what'.

2 / 5

Trigger Term Quality

It includes the natural phrasings a contributor would use — "adding or modifying", "CLI command", "but commands", plus the concrete path `crates/but/src` — giving good keyword coverage. A few natural variants are missing (e.g., "subcommand", "command-line argument"), keeping it below comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

The trigger is scoped to a clear niche — `but` commands specifically located under `crates/but/src` — so it is unlikely to fire for unrelated skills. The combination of tool name and path gives it distinct triggers with minimal conflict risk.

5 / 5

Total

14

/

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

gitbutlerapp/gitbutler

Path

.agents/skills/cli-commands/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.