sn-image-base

Base-layer skill for the SenseNova-Skills project, providing low-level APIs for image generation, recognition (VLM), and text optimization (LLM). This skill does not preprocess inputs; it only calls backend services and returns results. This skill is not user-facing and is intended for upper-layer skills only.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/sn-image-base/SKILL.md

Quality

Content

82%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 highly actionable with executable CLI examples and comprehensive parameter tables, well structured with a one-level-deep reference to the API spec. Its main weakness is some redundancy in the env-var resolution explanation and a sparsely signaled reference pointer.

Suggestions

Consolidate the env-var resolution order into a single authoritative table and have the Tools List and prose sections reference it, removing the duplicated explanation at lines 164 and 173.

Promote the reference pointer into a clearly signaled markdown link (e.g., "See [api_spec.md](references/api_spec.md) for full request/response details") near the top of the Usage section instead of a terse code-span at the end.

Add a short note on how callers should react to status=failed (retry, surface error, or propagate) to close the workflow-clarity validation gap.

Dimension	Reasoning	Score
Conciseness	The body is largely efficient with dense, scannable parameter tables and copy-paste commands, but the env-var resolution order is restated in the Tools List tables, the Default Parameter Behavior table, and again in prose (lines 164 and 173), and the base-url/interface mapping is duplicated, which keeps it just below anchor 5.	4 / 5
Actionability	Usage provides fully executable, copy-paste-ready CLI commands covering the common variants (minimal, override base-url, override api-key, Anthropic-compatible), and the parameter tables give exact types, defaults, and env vars, matching the anchor for fully executable guidance.	5 / 5
Workflow Clarity	The call sequence (run sn_agent_runner.py with args, parse JSON output with status/elapsed_seconds) is clear and unambiguous for this non-destructive tool-calling skill, with the output format section documenting success/failure shapes; minor gap is the lack of explicit retry guidance when status=failed.	4 / 5
Progressive Disclosure	Sections are well organized (Overview, Tools List, Usage, Output Format) with API detail offloaded to a verified one-level-deep reference (references/api_spec.md exists), but the reference pointer is a terse code-span at the very end rather than a clearly signaled link, leaving minor organization gaps.	4 / 5
	Total	17 / 20 Passed

Description

71%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 specific and well-scoped to a distinct infrastructure niche, clearly stating what the skill does and its non-user-facing boundary. Its main weakness is the absence of an explicit "Use when..." trigger clause, which caps completeness at 3.

Suggestions

Add an explicit "Use when..." clause naming the natural trigger phrases (e.g., image generation, image recognition/VLM analysis, text optimization) so upper-layer skills know when to invoke it.

Include a few common synonyms or file/extension-adjacent terms users actually say to lift trigger term quality from 4 toward 5.

Keep the third-person voice but consider surfacing one concrete trigger phrase directly in the description rather than relying on the separate triggers field.

Dimension	Reasoning	Score
Specificity	The description enumerates three concrete capabilities ("image generation, recognition (VLM), and text optimization (LLM)") plus the explicit behavior "only calls backend services and returns results," giving comprehensive coverage of what the skill does.	5 / 5
Completeness	There is a clear "what" but no "Use when..." trigger clause; the "when" is only weakly implied by "intended for upper-layer skills only," and per the guideline a missing explicit trigger guidance caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant natural keywords like "image generation," "image recognition," and "text optimization" appear, but several are technical ("VLM," "LLM," "low-level APIs") and common synonyms/extensions users might say are missing, so it sits between anchor 3 and 5, nearer the strong side.	4 / 5
Distinctiveness Conflict Risk	The skill is scoped to a clear niche ("Base-layer skill," "low-level APIs," "not user-facing and is intended for upper-layer skills only"), minimizing overlap risk, though the description text alone does not enumerate distinct trigger phrases that would push it to anchor 5.	4 / 5
	Total	16 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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: OpenSenseNova/SenseNova-Skills
Path: skills/sn-image-base/SKILL.md
Commit: 61b60bb

Reviewed: 8 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.