plant-store-custom-commands

How to author custom commands for the plant-store CLI using the co-generated SDK.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./seed/cli/oauth-client-credentials-openapi/with-wire-tests/.agents/skills/custom-commands/SKILL.md

Quality

Content

92%

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

The content is concise, highly actionable, and clearly sequenced, with executable Rust examples and exact file paths throughout. The only weakness is progressive disclosure: all material lives inline in a single ~120-line file with no split-out reference material.

Suggestions

Move the SDK sub-client table and key-pattern snippets into a references/ file (e.g. SDK_REFERENCE.md) and link to it from a concise 'Available SDK clients' pointer, improving progressive disclosure.

Add a short 'Verify your command' checkpoint after 'cargo build' (e.g. 'plant-store --help should list your new command') to make the workflow's validation explicit.

Consolidate the file listings in Architecture and Regeneration Safety into one table with a 'Regenerated?' column to remove the mild duplication.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: it jumps straight into architecture, executable Rust snippets, and tables without explaining what a CLI or SDK is, and every section earns its place. The slight overlap between the Architecture block and Regeneration Safety table serves a distinct purpose (regeneration status) rather than padding, so it does not drop to level 2.	3 / 3
Actionability	Guidance is fully executable: a complete register() handler with clap args and SDK calls, exact file paths, 'cargo build', and 'RUST_LOG=debug plant-store' invocations — copy-paste ready, matching 'Fully executable code/commands; specific examples'.	3 / 3
Workflow Clarity	Adding a command is sequenced as numbered steps (edit custom.rs → build → run) with the regeneration-safety section explaining what is preserved vs overwritten. Authoring custom commands is an additive, non-destructive task, so the missing validation checkpoint does not trigger the level-2 cap for destructive/batch operations.	3 / 3
Progressive Disclosure	The body is well-sectioned (Overview, Architecture, Adding a Custom Command, Regeneration Safety, Build & Test) but at ~120 lines everything is inline with no bundle files or one-level-deep references; the under-50-line exception does not apply, matching 'Some structure but ... content that should be separate is inline'.	2 / 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 specific to a clear niche and states the core action well, but omits explicit 'use when' trigger guidance and relies on some technical jargon. Adding a natural-language trigger clause would raise both completeness and trigger-term quality.

Suggestions

Add a 'Use when...' clause naming natural triggers, e.g. 'Use when extending the plant-store CLI with new commands or wiring custom handlers to the generated SDK.'

Replace or supplement 'co-generated SDK' with user-facing terms like 'the generated typed SDK client' to improve trigger-term quality.

Mention concrete action variations (register, wire auth, call SDK methods) to lift specificity from one action to several.

Dimension	Reasoning	Score
Specificity	The phrase 'author custom commands for the plant-store CLI using the co-generated SDK' names the domain and a concrete action, but lists only one action rather than multiple specific concrete actions, matching the level-2 anchor 'Names domain and some actions, but not comprehensive'.	2 / 3
Completeness	It clearly states what the skill does ('author custom commands') but lacks any 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Natural terms like 'custom commands' and 'plant-store CLI' are present, but 'co-generated SDK' is technical jargon and common variations a user might say (e.g. 'add a command', 'extend the CLI') are missing, matching 'Some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	The 'plant-store CLI' niche is highly specific with distinct triggers and is unlikely to fire for unrelated skills, matching 'Clear niche with distinct triggers; unlikely to conflict'.	3 / 3
	Total	9 / 12 Passed

Validation

100%

Warnings & errors only

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/oauth-client-credentials-openapi/with-wire-tests/.agents/skills/custom-commands/SKILL.md
Commit: 134b13f

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.