CtrlK
BlogDocsLog inGet started
Tessl Logo

meme-generation

Generate real meme images by picking a template and overlaying text with Pillow. Produces actual .png meme files.

66

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, highly actionable body with clear sequenced workflows and validation loops, held back only by inline duplication of template data and the absence of signaled reference-file navigation.

Suggestions

Move the curated-template table into templates.json (or a reference file) and link to it from SKILL.md, keeping only a brief pointer inline.

Add clearly signaled one-level-deep references for any deeper detail (e.g., 'See scripts/templates.json for the full field layout of each curated template').

DimensionReasoningScore

Conciseness

Lean body with no padding or explanation of concepts Claude already knows; every section and code block earns its place.

3 / 3

Actionability

Provides fully executable commands (generate_meme.py with --search/--image/--bars/--list) plus concrete copy-paste examples and a SKILL_DIR discovery snippet.

3 / 3

Workflow Clarity

Two clearly sequenced modes with numbered steps; Mode 2 includes an explicit vision-verification feedback loop and a Verification section with checkpoints.

3 / 3

Progressive Disclosure

Scripts/templates.json are real bundle files referenced by command rather than dumped inline, but the curated-template table is duplicated inline and there are no clearly-signaled one-level-deep reference links to deeper material.

2 / 3

Total

11

/

12

Passed

Description

72%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A crisp, third-person description that names concrete actions and a clear niche, but it omits any explicit 'when to use' trigger guidance, which caps completeness.

Suggestions

Add a 'Use when...' clause naming natural user phrasings (e.g., 'Use when the user asks to make or generate a meme about a topic, situation, or frustration').

Include common trigger variations such as 'meme this' or 'funny image' to improve trigger-term coverage.

DimensionReasoningScore

Specificity

Names multiple concrete actions — 'picking a template', 'overlaying text with Pillow', 'Produces actual .png meme files' — matching the top anchor.

3 / 3

Completeness

The 'what' is explicit, but there is no 'Use when...' clause or equivalent trigger for 'when', which the rubric caps at 2.

2 / 3

Trigger Term Quality

'meme images' and 'meme files' are natural terms, but common user variations like 'make a meme' or 'meme this' are absent, so coverage is partial.

2 / 3

Distinctiveness Conflict Risk

The meme niche with template/text-overlay/.png specifics is clear and unlikely to trigger the wrong skill.

3 / 3

Total

10

/

12

Passed

Validation

75%

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

Validation12 / 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

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

12

/

16

Passed

Repository
NousResearch/hermes-agent
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.