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

64%

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 ./skills/sn-image-base/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.

The body is a highly actionable reference with copy-paste commands and complete parameter tables, well-structured and pointing to a real one-level-deep spec file. Its main weakness is redundant repetition of env-var resolution and interface-type mappings across several sections.

Suggestions

Consolidate the repeated env-var resolution chains and interface-type mappings into a single authoritative table, then reference it from each tool section instead of restating it three to four times.

Surface the references/api_spec.md link inline within each tool's section (not only at the end) so the deferral is well-signaled where the reader encounters detail.

Add a short 'verify the result' note after the example calls (e.g., check JSON 'status == ok' before relying on the output) to add an explicit validation checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient reference material without explaining basic concepts, but the env-var resolution chains (CLI > env > default) and the openai-completions/anthropic-messages interface mapping are repeated across the per-tool tables, the 'Default Parameter Behavior' section, and the 'Mapping Between base-url and Interface Type' table, which could be tightened — matching the score-3 anchor rather than the lean score-4.	3 / 5
Actionability	It provides copy-paste-ready commands ('pip install -r requirements.txt', 'python scripts/sn_agent_runner.py sn-image-edit --prompt ... --images ...') and complete parameter tables with types, defaults, and env-var fallbacks, covering both minimal and override cases for every tool — fully matching the score-5 anchor.	5 / 5
Workflow Clarity	The install-then-invoke sequence is clear and the JSON output schema (with 'status' and 'elapsed_seconds', plus failure 'error' field) serves as an implicit validation checkpoint, but there are no explicit verify/retry feedback loops, fitting the score-4 'clear sequence with most checkpoints, minor gaps' anchor rather than score 5.	4 / 5
Progressive Disclosure	Content is well-organized into per-tool sections and defers full detail to a real one-level reference ('See references/api_spec.md for details', verified to exist), but that reference is signaled only once at the very end rather than inline per tool, placing it at score 4 instead of the well-signaled score-5 anchor.	4 / 5
	Total	16 / 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 clearly states what the skill does and carves a distinct infrastructure niche, but it omits any explicit 'when to use' trigger guidance and only offers moderate keyword coverage. Adding a concrete 'Use when...' clause with natural trigger terms would lift the completeness and trigger dimensions.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use when an upper-layer skill needs low-level SenseNova image generation, VLM recognition, or LLM text optimization') to satisfy the completeness trigger requirement.

Include common synonyms and variations users would actually say (e.g., 'image generation', 'text-to-image', 'VLM', 'vision', 'LLM', 'text rewriting') to improve trigger-term coverage.

Consider concrete per-tool action verbs ('generates images, recognizes image content via VLM, optimizes text via LLM') to move specificity toward a 4-5 anchor.

Dimension	Reasoning	Score
Specificity	Names the domain ('Base-layer skill for the SenseNova-Skills project') and three concrete capabilities ('image generation, recognition (VLM), and text optimization (LLM)'), but the actions are described at a broad API level rather than comprehensively, fitting the score-3 anchor rather than the multi-action score-4/5 anchors.	3 / 5
Completeness	The 'what' is clearly stated ('providing low-level APIs for image generation, recognition (VLM), and text optimization (LLM)'), but there is no 'Use when...' clause or equivalent positive trigger guidance — only a negative 'not user-facing and is intended for upper-layer skills only' — so per the rubric cap completeness stays at 3.	3 / 5
Trigger Term Quality	It includes relevant terms ('image generation', 'recognition (VLM)', 'text optimization (LLM)') but lacks common variations, synonyms, and file extensions that users would naturally say, matching the score-3 'some relevant keywords but missing common variations' anchor rather than the fuller coverage at score 4.	3 / 5
Distinctiveness Conflict Risk	It carves a clear niche as a SenseNova tier-0 infrastructure base layer that is explicitly 'not user-facing', making it mostly distinct with only minor overlap risk against other image/text skills, fitting the score-4 anchor rather than the fully-distinct score-5 anchor which requires explicit trigger phrases.	4 / 5
	Total	13 / 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: 5abde96

Reviewed: 10 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.