CtrlK
BlogDocsLog inGet started
Tessl Logo

url-form-encoded-api-custom-commands

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

52

Quality

57%

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

Quality

Content

72%

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

The body is concise, well-organized, and provides mostly executable code, but the 'Available SDK Clients' section is an empty placeholder and the workflow lacks explicit validation checkpoints. Filling in the sub-client list and adding a verify/build-check step would address the lowest-scoring dimensions.

Suggestions

Replace the empty 'Available SDK Clients' placeholder with concrete sub-client names and a usage example so the guidance is complete and actionable.

Add an explicit validation checkpoint to the workflow, e.g. 'cargo build' to confirm the custom command compiles before running it.

Trim the small overlap between the Architecture file tree and the Regeneration Safety table to keep the content fully tight, though this is minor.

DimensionReasoningScore

Conciseness

The body is lean, assumes competence (no explanation of what a CLI, SDK, or Rust is), and uses a compact file tree plus tight code blocks where every section earns its place, matching the 'lean and efficient' anchor; it is not the 'mostly efficient but could be tightened' level below despite minor table/section overlap.

3 / 3

Actionability

The main examples are concrete and executable (full register() handler, super::sdk::client(ctx)/block_on patterns, real cargo build commands), but the 'Available SDK Clients' section is a placeholder listing no actual sub-clients, which is incomplete and missing key details, fitting the 'some concrete guidance but incomplete' anchor rather than the fully copy-paste-ready level above.

2 / 3

Workflow Clarity

Steps are clearly sequenced (edit custom.rs, use SDK clients, apply key patterns, then build/test) but there are no explicit validation checkpoints such as verifying the command compiles or runs, matching the 'steps listed but validation gaps' anchor and not the 'clear sequence with explicit validation' level above.

2 / 3

Progressive Disclosure

The skill is short and has no bundle files or external references, yet is organized into clear, well-labeled sections (Overview, Architecture, Adding a Custom Command, Regeneration Safety, Build & Test), which per the simple-skill guideline earns the top anchor; it is not the 'some structure but could be better organized' level below.

3 / 3

Total

10

/

12

Passed

Description

42%

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 clearly identifies a niche tool and action in third-person voice but relies on product jargon rather than natural user triggers and lacks any explicit 'Use when' guidance. Strengthening trigger terms and adding usage triggers would raise its weakest dimensions.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should invoke this skill, e.g. 'Use when extending the url-form-encoded-api CLI with new user-authored commands.'

Replace or supplement jargon like 'co-generated SDK' with natural trigger terms a user might actually say, such as 'add a custom CLI command' or 'extend the CLI'.

List multiple concrete actions (register commands, wire the SDK client, run async calls from sync handlers) to move specificity toward the top anchor.

DimensionReasoningScore

Specificity

Names the domain and a concrete action ("author custom commands" for the CLI "using the co-generated SDK") but does not enumerate multiple specific actions like registering commands or wiring SDK clients, fitting the 'names domain and some actions' anchor rather than the 'lists multiple specific concrete actions' level above.

2 / 3

Completeness

It states what the skill does ("author custom commands for the url-form-encoded-api CLI") but provides no 'Use when...' or equivalent trigger guidance, so per the judging guidelines completeness caps at 2 and does not reach the explicit-what-and-when level above.

2 / 3

Trigger Term Quality

The keywords are product-specific jargon ("url-form-encoded-api CLI", "co-generated SDK") that a user would not naturally say; there are no common natural-language trigger terms, matching the 'no natural keywords; technical jargon' anchor and not the 'some relevant keywords' level above.

1 / 3

Distinctiveness Conflict Risk

The very specific tool name ("url-form-encoded-api") gives it a clear niche unlikely to conflict with other skills, matching the 'clear niche with distinct triggers' anchor; it is clearly more specific than the 'somewhat specific but could overlap' level below.

3 / 3

Total

8

/

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.