auteur

Design and build cinematic, award-level web pages.

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./optional-skills/creative/auteur/SKILL.md

Quality

Content

73%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, actionable overview with excellent workflow sequencing and validation gates, and it uses progressive disclosure well by pointing to one-level-deep reference files. Its weaknesses are rhetorical verbosity that could be trimmed and a missing templates/ directory whose files are referenced but not bundled.

Suggestions

Tighten the editorial prose (film-director metaphor, em-dash asides, slogans like "a default is slop") to reduce token cost without losing the methodology.

Add the missing `templates/` directory (COMMIT-SHEET.md, DESIGN.md, scroll-flight-engine.js, CINEMA-QA.md) or remove/redirect the references, since four cited paths resolve to nothing in the bundle.

Inline one or two short canonical code snippets (e.g. the IntersectionObserver/ScrollTrigger pattern) so the most common case is copy-paste ready without loading a reference file.

Dimension	Reasoning	Score
Conciseness	The body is dense with skill-specific content (banned-patterns table, critical numbers, commit-sheet, phase/route tables) and avoids explaining concepts Claude already knows, but it carries noticeable rhetorical padding (the extended film-director metaphor, em-dash asides, editorializing like "a default is slop") that could be tightened.	3 / 5
Actionability	It gives concrete executable commands (e.g. `node scripts/slopscan.mjs <src-dir>`, `npm install playwright`), precise numeric specs (contrast ≥ 4.5:1, durations 100–160ms, LCP < 2.5s), a seven-field commit-sheet, and a banned-patterns table with replacements; the gap is that most copy-paste code recipes live in the reference files rather than inline.	4 / 5
Workflow Clarity	Multi-step work is clearly sequenced via the phase table (0–4) and routing rules, with explicit validation gates (slopscan exit 0, screenshot review, numeric rubric, CINEMA-QA) and a feedback loop ("If any gate fails — fix and re-run"), so the destructive/batch cap does not apply.	5 / 5
Progressive Disclosure	SKILL.md is a clear overview with a well-signaled one-level-deep "Reference files" section that lists all 11 present reference files with load triggers; the organization gap is that `templates/COMMIT-SHEET.md`, `templates/DESIGN.md`, `templates/scroll-flight-engine.js`, and `templates/CINEMA-QA.md` are referenced in the body but no `templates/` directory exists in the bundle.	4 / 5
	Total	16 / 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 clear and domain-specific but terse: it states what the skill does without any explicit use-when trigger guidance and with only two named actions. It is distinguishable but not sharply differentiated from general web-design skills.

Suggestions

Add an explicit "Use when..." clause naming concrete triggers, e.g. "Use when a landing page, hero, or marketing site must look cinematic or award-level rather than generic."

Expand the action list beyond "design and build" to surface specific capabilities (scroll-directed storytelling, multi-screen design systems, asset generation, anti-slop QA).

Include natural synonyms users say ("landing page", "hero section", "scroll animation", "design system") to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ("web pages") and two concrete actions ("Design and build") plus quality modifiers ("cinematic, award-level"), but the modifiers describe output character rather than additional actions, so coverage is not comprehensive.	3 / 5
Completeness	It gives a clear "what" (design and build cinematic, award-level web pages) but no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	"cinematic" and "web pages" are natural terms a user might say, but common synonyms and variations (landing page, hero, scroll animation, website) are absent from the description.	3 / 5
Distinctiveness Conflict Risk	"cinematic, award-level" narrows the niche, but "design and build web pages" is a broad category that overlaps with sibling web-design skills, so conflict risk remains.	3 / 5
	Total	12 / 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: NousResearch/hermes-agent
Path: optional-skills/creative/auteur/SKILL.md
Commit: 68fa7e9

Reviewed: 3 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.