CtrlK
BlogDocsLog inGet started
Tessl Logo

acme-cli-custom-commands

How to author custom commands for the acme-cli CLI using the co-generated SDK.

62

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 ./seed/cli/cli-multi-spec/no-custom-config/.agents/skills/custom-commands/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

87%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is lean, concrete, and well-organized with executable code and a useful regeneration-safety table. The main gap is workflow clarity: the step sequence lacks explicit validation checkpoints and mixes actions with reference material.

Suggestions

Add an explicit build/validation checkpoint in the workflow (e.g., "After editing, run `cargo build`; if it fails, fix compile errors and rebuild before running the command") to create a real feedback loop.

Reframe the numbered "Adding a Custom Command" list as pure sequential actions (edit custom.rs → build → run/debug) and move the "Available SDK Clients" and "Key Patterns" material into a separate reference section so the workflow reads cleanly.

Fill or remove the empty "Available SDK Clients" section, which promises sub-clients but delivers only a placeholder parenthetical.

DimensionReasoningScore

Conciseness

The body is lean and skill-specific — it explains only acme-cli particulars (.fernignore, sdk.rs bridge, register()) and never pads with concepts Claude already knows, so most tokens earn their place.

3 / 3

Actionability

A complete register() template with clap args, the client()/block_on() calls, typed-model imports, and real build commands (cargo build, RUST_LOG=debug) make the guidance concrete and copy-paste ready.

3 / 3

Workflow Clarity

The edit→build→run sequence is present and the build step is an implicit checkpoint, but there is no explicit validation/feedback loop, and the numbered "Adding a Custom Command" steps conflate actions with reference sections.

2 / 3

Progressive Disclosure

The single SKILL.md is organized into clear, well-signaled sections (Overview, Architecture, Adding a Custom Command, Key Patterns, Regeneration Safety, Build & Test) with a summary table and no nested references; for this focused, self-contained task no external files are needed.

3 / 3

Total

11

/

12

Passed

Description

57%

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 is distinctive and names a clear niche, but it states only a single action and lacks any explicit "Use when..." trigger guidance. Adding a trigger clause and one or two more concrete verbs would raise its score.

Suggestions

Add an explicit "Use when..." clause (e.g., "Use when extending the acme-cli CLI with new subcommands") so Claude knows when to invoke this skill.

List a couple of concrete actions (e.g., "register, wire, and compile custom subcommands") instead of the single verb "author" to improve specificity.

Replace or augment "co-generated SDK" with a more natural phrase users would actually say to improve trigger-term quality.

DimensionReasoningScore

Specificity

"How to author custom commands for the acme-cli CLI using the co-generated SDK" names the domain (acme-cli CLI) and one concrete action (author custom commands), but does not list multiple specific concrete actions as the score-3 anchor requires.

2 / 3

Completeness

The description states what the skill does (author custom commands for acme-cli) but has no "Use when..." clause or equivalent explicit trigger guidance, so per the judging guideline completeness is capped at 2.

2 / 3

Trigger Term Quality

"custom commands" and "acme-cli" are natural terms a user might say, but "co-generated SDK" is technical jargon and common variations are missing, matching the score-2 anchor rather than comprehensive coverage.

2 / 3

Distinctiveness Conflict Risk

The product-specific phrase "acme-cli CLI" carves out a clear niche with distinct triggers that are unlikely to conflict with other skills, matching the score-3 anchor.

3 / 3

Total

9

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
fern-api/fern
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.