CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

baoyu-comic

Knowledge comics (知识漫画): educational, biography, tutorial.

Quality

69%

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 ./optional-skills/creative/baoyu-comic/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 a strong, highly actionable workflow document with excellent validation checkpoints and a clean one-level-deep reference structure. The main weaknesses are localized verbosity (an incident anecdote and duplicated warnings) and one orphaned bundle file.

Suggestions

Compress the 'Incident Apr 2026' paragraph in Step 7 to a one-line caution — the rule ('always pass absolute paths to curl -o, CWD can drift between batches') stands on its own without the four-sentence story.

Deduplicate the absolute-path warning: keep it in one place (Step 7) and let the Pitfalls entry be a one-line pointer, reclaiming ~6 lines of tokens.

Either reference references/base-prompt.md from SKILL.md or the workflow (or remove it if superseded), so every bundle file is discoverable.

DimensionReasoningScore

Conciseness

Most content is genuinely non-obvious and earns its place (Hermes tool constraints, aspect-ratio mapping, naming conventions, presets), but there are several spots that could be tightened: the multi-sentence 'Incident Apr 2026' anecdote, the philosophical timeout reasoning ('If the user is genuinely absent, they will be equally absent for all five questions...'), and the absolute-CWD-path warning repeated almost verbatim in both Step 7 and Pitfalls. This sits at 'mostly efficient but includes some unnecessary explanation' — below anchor 4's 'minor instances', above anchor 2 since the padding is localized rather than pervasive.

3 / 5

Actionability

Guidance is copy-paste ready throughout: exact file-naming patterns (prompts/NN-{cover|page}-[slug].md), a literal curl command with an absolute output path, an aspect-ratio mapping table, backup-suffix format, regenerate syntax ('3' or '2,5,8'), and a worked prompt-frontmatter YAML block. It matches 'fully executable; specific examples cover the common cases'.

5 / 5

Workflow Clarity

The 8-step workflow is presented as a progress checklist, a flow diagram, and a step-summary table, with explicit conditional review gates (Steps 4/6), a hard confirmation gate (Step 2), per-page validation ('verify the file exists and is non-empty before proceeding'), auto-retry on image failure, and backup-renaming before regeneration. This matches the anchor 'clear sequence with explicit validation steps; feedback loops for error recovery; checklists'.

5 / 5

Progressive Disclosure

SKILL.md works well as an overview: defaults and the core workflow stay inline while full definitions are pushed one level deep to real, verified files (references/art-styles/*.md, tones/*.md, presets/*.md, workflow.md, partial-workflows.md, auto-selection.md), with clear signals like 'load the file when a preset is picked'. However, references/base-prompt.md is orphaned — referenced neither from SKILL.md nor from any reference file — which is a minor organization gap that keeps it just below anchor 5.

4 / 5

Total

17

/

20

Passed

Description

47%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 identifies a clear niche with bilingual keywords, but reads as a category label rather than a capability statement: it has no action verb and no 'use when' trigger guidance. It would be substantially improved by two small additions.

Suggestions

State the action explicitly, e.g., "Creates original knowledge comics (educational, biography, tutorial) with configurable art style, tone, and layout" instead of the bare category label.

Add a 'when' clause with trigger phrases, e.g., "Use when the user asks to create an educational or biography comic, a tutorial comic, or mentions 知识漫画, 教育漫画, or Logicomix-style works" — this would lift the completeness cap.

Consider including a couple of common synonyms users actually say (comic strip, 漫画, graphic-novel style) to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

The description "Knowledge comics (知识漫画): educational, biography, tutorial" names the domain and three content subtypes, but contains no action verbs at all — it never states whether the skill creates, analyzes, or reads such comics. This matches the anchor 'Names the domain but actions are minimal or generic'; it falls short of score 3 because even the 1-2 concrete actions that anchor expects (e.g., 'creates comics') are absent.

2 / 5

Completeness

There is no 'when to use' clause whatsoever, and the 'what' is only weakly implied by a category label. Per the anchor 'Has a vague what and no when'; it is not score 3 because the what is a terse label rather than a clear statement of what the skill does.

2 / 5

Trigger Term Quality

Includes natural terms users would say — "Knowledge comics", "educational", "biography", "tutorial", and the Chinese "知识漫画" — giving good bilingual keyword coverage. A few natural variants are missing (e.g., bare "漫画", "comic strip", "graphic novel", "Logicomix-style", which only appears in the body), so it does not reach comprehensive anchor-5 coverage.

4 / 5

Distinctiveness Conflict Risk

"Knowledge comics" with educational/biography/tutorial subtypes carves a fairly distinct niche unlikely to grab unrelated skills. Minor overlap risk remains with general comic, storyboard, or image-generation skills, keeping it just below the minimal-conflict anchor.

4 / 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/creative/baoyu-comic/SKILL.md

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.