CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

url-form-encoded-api-custom-commands

How to author custom commands for the url-form-encoded-api CLI using the co-generated SDK.

Quality

74%

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/url-form-encoded/.agents/skills/custom-commands/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 a lean, highly actionable guide with copy-paste-ready Rust registration code, a clear edit→build→run workflow, and a useful regeneration-safety table. Its main weakness is the "Available SDK Clients" section, which announces a listing it never delivers, leaving command authors without concrete SDK method examples.

DimensionReasoningScore

Conciseness

The body is lean throughout: a three-sentence overview, a compact architecture diagram, one tight code example, pattern snippets, a regeneration table, and four build commands — no explanations of concepts Claude already knows and no padding. It clearly matches the level-5 anchor (every token earns its place) rather than merely having minor trimmable instances (level 4).

5 / 5

Actionability

The register() example is copy-paste-ready Rust, the key patterns (client(ctx), block_on, typed imports) are concrete, and the build/run/RUST_LOG commands are executable. It falls short of level 5 because "Available SDK Clients" promises "the following sub-clients" but lists none, leaving a concrete gap in what methods a command author can actually call.

4 / 5

Workflow Clarity

The sequence is clear — edit custom.rs (protected by .fernignore), build with cargo, run the command, debug with RUST_LOG — and the Regeneration Safety section explains what to do after fern generate. Minor validation gaps (no explicit check that the command registered or what to do on build failure) keep it at level 4 rather than 5; it is well above level 3 since checkpoints like the .fernignore guarantee and debug flag are present and this is not a destructive/batch workflow.

4 / 5

Progressive Disclosure

No bundle files (references/, scripts/, assets/) exist and none are referenced, and the ~107-line body is well organized into Overview, Architecture, Adding a Custom Command, Regeneration Safety, and Build & Test. It stops short of level 5 partly because it exceeds the under-50-lines simple-skill exception and partly because the empty sub-clients section is a placeholder that would be better filled or split into a generated reference file.

4 / 5

Total

17

/

20

Passed

Description

53%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 appropriately specific and highly distinct thanks to naming the exact CLI and SDK mechanism, but it omits any explicit "when to use" trigger guidance and offers only a single action verb with no synonyms or natural trigger variations. Adding a "Use when..." clause with natural trigger phrases would lift completeness and trigger-term quality substantially.

Suggestions

Add an explicit trigger clause, e.g., "Use when adding or modifying commands in the url-form-encoded-api CLI, or when the user asks to extend the CLI with new commands."

Enumerate the concrete capabilities beyond just authoring, e.g., "...register clap commands, call the typed SDK from sync handlers, and survive fern regenerate safely."

Include natural trigger synonyms such as "custom command", "add a CLI command", and "extend url-form-encoded-api" so the description matches how users would actually phrase the request.

DimensionReasoningScore

Specificity

The description names a concrete domain and action — "author custom commands for the url-form-encoded-api CLI using the co-generated SDK" — but lists only that single action rather than several specific capabilities. It is not generic (ruling out 2), but it does not list several specific actions with minor coverage gaps (ruling out 4).

3 / 5

Completeness

The "what" is clear (authoring custom commands for this CLI via the co-generated SDK), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is not score 2 because the "what" is specific and concrete, not vague.

3 / 5

Trigger Term Quality

"custom commands", "CLI", and "SDK" are relevant keywords a developer in this codebase would plausibly say, but no variations or synonyms are present (e.g., "add a command", "extend the CLI"). Keyword coverage exists but common variations are missing, matching the level-3 anchor rather than the good-but-incomplete coverage of level 4.

3 / 5

Distinctiveness Conflict Risk

Naming the specific "url-form-encoded-api" CLI carves out a clear niche with minimal overlap risk against other skills. It falls short of the level-5 anchor because that anchor's example includes explicit distinct trigger phrases ("Use when..."), which this description lacks; it is clearly above level 3 since the niche is far more specific than a broad file-type domain.

4 / 5

Total

13

/

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/url-form-encoded/.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.