CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

x-fern-default-test-custom-commands

How to author custom commands for the x-fern-default-test CLI using the co-generated SDK.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

—

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./seed/cli/x-fern-default/.agents/skills/custom-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 content is lean, concrete, and well structured, with an executable code example, a useful regeneration-safety table, and working build commands. Its main defects are an empty 'Available SDK Clients' section that promises a list it never delivers, a fourfold repetition of the .fernignore fact, and the absence of a post-build verification step. Addressing the stub section and adding a verify step would bring it to top scores.

Suggestions

Fill in or remove the empty 'Available SDK Clients' section — either show how to discover sub-clients (e.g., where in the generated SDK crate to look) or point to the generated code, instead of promising 'the following sub-clients' and listing none.

State the .fernignore protection once (e.g., only in the regeneration table) and drop the repetitions in the architecture diagram, step 1, and the closing paragraph.

Add an explicit verification step after building, such as running `x-fern-default-test --help` or invoking the new command to confirm registration before proceeding.

DimensionReasoningScore

Conciseness

The body is tight and assumes competence (no explanation of Rust, clap, or what a CLI is), but the .fernignore protection fact is stated four times (architecture diagram, step 1, the regeneration table, and the closing paragraph) and could be trimmed. This is 'efficient; minor instances that could be trimmed' rather than 3, since there is no padding beyond that one repeated fact.

4 / 5

Actionability

The register() example is concrete and executable, and the build/run commands are copy-paste ready, matching 'mostly executable guidance'. It is not a 5 because section 2 'Available SDK Clients' promises 'the following sub-clients' but lists none, leaving a real gap in the examples' coverage of common cases.

4 / 5

Workflow Clarity

There is a clear numbered sequence (edit custom.rs, register, build, run) plus regeneration guidance, matching 'clear sequence with most checkpoints present'. It is not a 5 because there is no explicit verification step (e.g., checking the command appears via --help or a test run before shipping), though the operations are non-destructive so no cap applies.

4 / 5

Progressive Disclosure

The single-file skill is well organized with clear section headers and no nested or buried references, and nothing here clearly belongs in a separate file. The empty 'Available SDK Clients' stub is a minor organization gap, keeping this at 'good structure' rather than a 5.

4 / 5

Total

16

/

20

Passed

Description

57%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 is concise and names a highly distinctive, conflict-free niche, but it only states a single action and entirely omits any 'when to use this' trigger guidance. It reads like a title rather than a complete description. Adding a 'Use when...' clause with natural trigger phrases and one or two more concrete actions would lift most dimensions.

Suggestions

Add an explicit trigger clause, e.g. 'Use when adding or modifying commands in the x-fern-default-test CLI, or when the user mentions extending that CLI or its co-generated SDK.'

Enumerate one or two more concrete actions, such as 'register commands in custom.rs, call the typed SDK client, and keep them safe across fern generate' to raise specificity.

Include natural synonyms users would actually say ('add a command to the CLI', 'extend x-fern-default-test') to improve trigger-term coverage.

DimensionReasoningScore

Specificity

The description names the domain ('x-fern-default-test CLI') and one concrete action ('author custom commands'), matching the anchor for 1-2 concrete actions without comprehensive coverage. It does not list several specific actions (registering commands, wiring the SDK client, regeneration safety), so it is not a 4.

3 / 5

Completeness

The 'what' is clear (authoring custom commands for this CLI using the co-generated SDK), but there is no 'Use when...' clause or equivalent trigger guidance anywhere, which caps completeness at 3 per the judging guidelines. It is not a 2 because the 'what' half is concrete, not vague.

3 / 5

Trigger Term Quality

'custom commands', 'CLI', and 'SDK' are relevant keywords a user might say, but common natural variations like 'add a command', 'extend the CLI', or 'fern generate' are missing. This matches 'some relevant keywords but missing common variations or synonyms' rather than the fuller coverage of a 4.

3 / 5

Distinctiveness Conflict Risk

The uniquely named tool 'x-fern-default-test' gives this a clear niche; no other skill would plausibly trigger for this request. Anti-drift check: a 4 requires 'minor overlap risk with closely related skills', and no such closely related skill surface exists given the one-of-a-kind tool name.

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

fern-api/fern

Path

seed/cli/x-fern-default/.agents/skills/custom-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.