cli-anything-generator

Build, refine, test, validate, or list CLI-Anything harnesses for GUI applications in Cursor. Prefer slash commands /cli-anything, /cli-anything-refine, /cli-anything-test, /cli-anything-validate, and /cli-anything-list when available. This skill supports natural-language discovery of the generator; it does not replace those commands. Discovering already-published CLIs from CLI-Hub is a separate consumer skill (cli-hub-meta-skill).

Quality

66%

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 ./cursor-plugin/skills/cli-anything-generator/SKILL.md

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.

A lean, dispatcher-style overview that routes to slash commands and external reference files with concrete paths and explicit phase gates. Its gaps are the absence of an inline validation feedback loop and the fact that all referenced material lives outside the shipped bundle, so the skill body cannot stand alone.

Suggestions

Add an explicit inline validation checkpoint for the build/refine workflow (e.g. run /cli-anything-validate after each phase and fix before advancing) rather than only naming the validate command.

Ship the referenced files (references/HARNESS.md, references/commands/, scripts/) inside the skill bundle, or state plainly that they exist only in the installed plugin — as written, every reference resolves outside the skill.

Fold the path-remapping table into the references it translates (e.g. a note in HARNESS.md) to cut body tokens and remove a navigation hop.

Dimension	Reasoning	Score
Conciseness	The body is terse and directive — tables, short numbered steps, no concept explanations Claude already knows. It is not a 5 because the path-remapping table and consumer-path install instructions are operational detail that could be trimmed or moved to a reference.	4 / 5
Actionability	Provides a concrete slash-command table, a copy-paste-ready `npx skills add HKUDS/CLI-Anything --skill cli-hub-meta-skill -g -y`, explicit PLUGIN_ROOT resolution paths, and named helper scripts. Not a 5 because the core build workflow itself is deferred to external references rather than given inline.	4 / 5
Workflow Clarity	A clear numbered methodology sequence plus explicit phase gates ("Do not advance without completing the previous phase. Resume non-terminal runs") tracked in a progress file — most checkpoints are present. Not a 5 because an inline validate→fix→retry loop is absent; validation is only delegated to a separate `/cli-anything-validate` command.	4 / 5
Progressive Disclosure	The body is a genuine overview pointing one level deep to clearly signaled references (references/HARNESS.md, references/commands/, references/guides/) used on demand. Not a 5 because no bundle files ship with the skill — every reference points to an externally resolved PLUGIN_ROOT, and a remapping table is required to translate document paths, adding navigation friction.	4 / 5
	Total	16 / 20 Passed

Description

58%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.

A well-bounded description that names concrete actions and cleanly separates the generator from its slash commands and the consumer skill. Its main weakness is the absence of an explicit "Use when..." trigger clause and of the natural-language phrasings users would actually say, leaving it reliant on project-specific jargon for triggering.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to create, extend, or verify a command-line harness for a GUI application (e.g. GIMP, Inkscape) in Cursor."

Include natural synonyms users would say — "command-line tool", "CLI for an app", "wrap a GUI app in a CLI" — not just the project's own terms ("CLI-Anything harnesses", "CLI-Hub").

State when this skill (rather than a slash command) should fire: e.g. natural-language requests like "build a CLI for ./gimp" when the commands are unavailable.

Dimension	Reasoning	Score
Specificity	The description lists five concrete actions ("Build, refine, test, validate, or list CLI-Anything harnesses") plus the specific slash commands (/cli-anything-refine, /cli-anything-test, etc.), giving broad but slightly generic coverage. It falls short of a 5 because the actions are bare verbs without the concrete detail of the top anchor.	4 / 5
Completeness	The "what" is clear (build/refine/test/validate/list CLI-Anything harnesses), but there is no explicit "Use when..." clause — trigger guidance is only weakly implied by "supports natural-language discovery of the generator". Per the rubric guideline, a missing explicit trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Keywords present ("CLI", "harnesses", "GUI applications", "Cursor", "CLI-Hub") lean toward project jargon; the natural phrases a user would actually say ("make a CLI for this app", "command-line tool", file extensions) are missing. Better than a 2 because the domain terms are relevant and specific.	3 / 5
Distinctiveness Conflict Risk	The description explicitly demarcates boundaries ("it does not replace those commands"; the Hub consumer is "a separate consumer skill (cli-hub-meta-skill)"), giving a clear generator niche. Minor overlap risk remains with the plugin's own slash commands, which perform the same function, so it does not reach 5.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 7 missing, 2 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: HKUDS/CLI-Anything
Path: cursor-plugin/skills/cli-anything-generator/SKILL.md
Commit: 34f5195

Reviewed: 1 day 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.