CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

inference-sh-cli

Run 150+ AI apps (image, video, LLM) via inference.sh CLI.

57

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./optional-skills/devops/inference-sh-cli/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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 well-structured, highly actionable skill body: fully executable commands, a clear search-first workflow with auth checkpoints, and exemplary one-level-deep reference navigation. The only weakness is minor token redundancy from repeated search examples and a Local File Uploads section duplicated in running-apps.md.

DimensionReasoningScore

Conciseness

The body is lean, command-focused, and teaches nothing Claude already knows, but there is minor redundancy: the `infsh app list --search ...` commands repeat between the Workflow and Common Commands sections, and the Local File Uploads block duplicates content in `references/running-apps.md`. This fits 'efficient; minor instances ... that could be trimmed' rather than the fully lean anchor.

4 / 5

Actionability

Every section gives copy-paste-ready, executable commands with real app IDs and JSON inputs — install (`curl -fsSL https://cli.inference.sh | sh`), auth check (`infsh me`), search, and run examples covering image, video, file upload, and search cases. Matches 'fully executable; copy-paste ready ... specific examples cover the common cases'.

5 / 5

Workflow Clarity

The workflow is a clear three-step sequence (Search → Run → Parse) with an upfront authentication checkpoint (`infsh me`) and an error-recovery hint in Pitfalls (auth failure → `infsh login`). It falls short of 5 because recovery guidance is scattered in a Pitfalls list rather than an explicit validate → fix → retry loop within the workflow steps.

4 / 5

Progressive Disclosure

The SKILL.md is a clean overview: all four bundle files (`authentication.md`, `app-discovery.md`, `running-apps.md`, `cli-reference.md`) exist, are one level deep with no nested references, and each is clearly signaled with a one-line description in the Reference Docs section. Common cases stay inline while bulk detail lives in the references, matching the top anchor.

5 / 5

Total

18

/

20

Passed

Description

50%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 concise and names a clear platform niche, but it answers only the 'what' — there is no 'when to use' guidance, and it lacks natural trigger phrases like 'generate an image' or 'make a video'. All four dimensions land at the midpoint for the same root cause: missing trigger/usage context.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user asks to generate images or video, run AI apps, or mentions inference.sh/infsh.'

Include natural trigger phrases and synonyms users would actually say — 'generate an image', 'make a video', 'text-to-speech', 'avatar/lipsync', 'AI search' — to improve trigger_term_quality.

Enumerate 1-2 more concrete capabilities beyond 'run' (e.g. 'search 150+ AI apps, generate images and video, run AI search') to lift specificity.

DimensionReasoningScore

Specificity

Names the domain ("150+ AI apps (image, video, LLM)") and a single concrete action ("Run ... via inference.sh CLI"), matching the 'names domain and 1-2 concrete actions' anchor. It does not list several distinct actions (search, generate, upscale), so it falls short of 4.

3 / 5

Completeness

The description gives a clear 'what' ("Run 150+ AI apps ... via inference.sh CLI") but contains no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Terms like "image", "video", "LLM", "inference.sh", and "CLI" are relevant, but natural user phrasings ("generate an image", "make a video", "text-to-speech", "avatar") and synonyms are missing, fitting the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

"inference.sh CLI" establishes a distinct platform niche, but the broad category triggers "image, video, LLM" would also match dedicated image-generation or LLM skills, fitting 'somewhat specific but could still overlap with similar skills'.

3 / 5

Total

12

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository

NousResearch/hermes-agent

Path

optional-skills/devops/inference-sh-cli/SKILL.md

Revision

ed728c5

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill