CtrlK
BlogDocsLog inGet started
Tessl Logo

cli-hub-meta-skill

Discover agent-native CLIs for professional software. Access the live catalog to find tools for creative workflows, productivity, AI, and more.

59

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./cli-hub-meta-skill/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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 body is strongly actionable — executable commands throughout, a well-sequenced matrix workflow with preflight validation, scoped installs, dry-run previews, resume, and doctor auditing. Its weaknesses are redundancy (install steps repeated across three sections) and mildly promotional filler, plus it relies on an external URL for the catalog rather than any bundled reference material.

Suggestions

Consolidate the three repetitions of the install steps (Quick Start, 'How to Use', 'Example Workflow') into one section to tighten token usage.

Trim promotional phrasing ('empowering agents to conduct complex workflows', 'CLI-Hub covers a broad range of software') and replace the 'What Can You Do?' bullet list with a pointer to the catalog or a compact examples section.

Consider bundling a small local reference (e.g. references/catalog-summary.md or a category cheat sheet) so catalog navigation does not depend solely on a live external URL.

DimensionReasoningScore

Conciseness

The body is mostly lean with no explanations of concepts Claude already knows, but install instructions appear three times (Quick Start, 'How to Use', 'Example Workflow') and 'What Can You Do?' with 'CLI-Hub covers a broad range of software... empowering agents' reads as promotional filler that could be trimmed.

3 / 5

Actionability

Every section gives copy-paste-ready commands: 'pip install cli-anything-hub', 'cli-hub search image', 'cli-hub matrix preflight video-creation --json', 'cli-anything-kdenlive --json project create --name my-project', with concrete exit codes (0/3/1/2) and flags (--capability, --dry-run, --resume) covering the common cases.

5 / 5

Workflow Clarity

The matrix workflow has an explicit validation step ('preflight before you install', 'exit 3 = gaps', '--fix-hints'), scoping rules for batch installs ('do not bulk-install... use --capability... --dry-run to preview'), and error-recovery feedback loops ('Retry failures with cli-hub matrix install <name> --resume' and 'audit an install with cli-hub matrix doctor <name>'), which matches the top anchor despite this being a batch-install context.

5 / 5

Progressive Disclosure

No bundle files exist, so all guidance is inline in a single ~108-line file with clear sections (Quick Start, Workflow Matrices, Live Catalog, How It Works, More Info). Structure is good and the bulk catalog content is appropriately kept external via a clearly signaled URL rather than inlined, though the body is over 50 lines and sections like 'What Can You Do?' plus the redundant 'How to Use' could be split or trimmed for tighter organization.

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 communicates a clear niche and a two-part capability (discover CLIs, access a live catalog) in third person, but it omits any 'when to use' trigger guidance and leans on generic category words ('productivity', 'AI', 'and more') instead of concrete natural keywords. Adding an explicit 'Use when...' clause with concrete user-sayable terms would lift both completeness and trigger quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to use professional software (image editing, 3D modeling, video production, office suites) via command-line tools or asks to install/run tools like GIMP or Kdenlive.'

Replace generic category words ('productivity, AI, and more') with concrete natural keywords and synonyms users would actually say (image editing, video editing, 3D modeling, audio, live streaming, CLI).

State the primary concrete actions more specifically (e.g. 'search the catalog, install a CLI, run it with JSON output') to improve specificity and distinctiveness.

DimensionReasoningScore

Specificity

The description names the domain ('agent-native CLIs for professional software') and two concrete actions ('Discover... CLIs', 'Access the live catalog... to find tools'), but coverage is not comprehensive and 'creative workflows, productivity, AI, and more' is generic category listing rather than specific actions.

3 / 5

Completeness

The 'what' is reasonably clear (discover/install CLIs for professional software via a live catalog), but there is no 'Use when...' clause or any equivalent trigger guidance, capping completeness at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

It contains some relevant keywords users would say ('CLIs', 'creative workflows', 'productivity', 'AI'), but misses the natural phrases and synonyms a user would actually utter when needing this skill (e.g. 'image editing', 'video production', 'command-line tool', 'install gimp'), relying on a trailing 'and more'.

3 / 5

Distinctiveness Conflict Risk

The niche (a catalog/marketplace of agent-native CLIs) is fairly distinct with low conflict risk against typical skills, though 'productivity, AI, and more' broadens it into minor overlap territory with general productivity/AI skills.

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
HKUDS/CLI-Anything
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.