Assess the visual quality of images, films, slides, and site captures against a brief and craft criteria. Two vision judges score the work and rank defects, guiding bounded revision; delivery is gated on a passing critique, with human calibration labels recorded separately.
Directs visual quality across images, films, slides, and site captures through a direction council, two vendors' vision judgments against anchored craft criteria, ranked defects, bounded iteration, gated delivery, and recorded human calibration labels. USE WHEN critique this, art direction, quality loop, rate the visuals, is this pro, iterate until it's great, deliver the render, art council. NOT FOR producing the artifact itself (use the appropriate image, motion, story-film, video-essay, web-design, or slide-production capability), for text writing audits, or for rating and rendering an ISA (ISA).
Run score Not tested
See how to installArtDirection evaluates images, films, slides, and site captures against a brief that records the audience, references, visual direction, and quality bar. A direction council resolves the visual intent into Direction.md. The skill then uses vision judges to score the work against craft criteria and list fixable defects in priority order. If revisions are needed, the critique can run for up to four rounds and report whether the work meets the bar or what remains. Only work with a passing critique can proceed to delivery. Human scores and comments can also be recorded as labels for later judge calibration.
Use it to review the appearance of an image or video before publication, turn a visual critique into a prioritized list of changes, or hand over approved work together with its evaluation record.
The judge vendors must be configured. First-time setup for films also requires ffmpeg. ArtDirection supports quality evaluation and delivery after production; it does not create the image, film, slide, or site capture. It is not for writing audits or evaluating and rendering an ISA.
This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.
AI checked the SKILL.md for operations that need care and for setup requirements. The score comes only from actually running the skill (hands-on test).
Not counted in the score. Rated by AI (OpenAI Codex) as of Oct 28, 2026. Treat it as a guide and read the original before installing.
Review the instructions the agent will receive before you install.
A shared quality loop for artistic deliverables: the Brief defines audience, register, references and bar; a Direction council resolves the visual intent into Direction.md; the domain skill produces the artifact against it; Critique yields two vendors' scores and ranked defects; iteration reaches the bar or reports the shortfall at four rounds; only a passing result reaches Deliver; and Calibrate records the principal's own verdict as evidence for later judge calibration. The domain skill makes the artifact; this skill supplies the quality evidence.
vendor_missing flag as weaker evidence.References/Rubric.md.| Intent | Trigger | File |
|---|---|---|
| Loop | Full quality loop or iterate to the bar | Intents/Loop.md |
| Direction | Art council or new visual direction | Intents/Direction.md |
| Critique | Rate the visuals or inspect a render | Intents/Critique.md |
| Deliver | Hand over a passing artifact | Intents/Deliver.md |
| Calibrate | Record the principal's score and note | Intents/Calibrate.md |
| File | Read when |
|---|---|
References/Rubric.md | writing a brief or reading a critique: the anchored axes, document and figure rules, defect shape and the Brief.json schema (References/BriefExample.json is a filled brief); Critique reads it at runtime |
Setup.md | first-time setup: the two judge vendors' access, ffmpeg for films, and a no-cost proof |
Run with bun skills/ArtDirection/ prefixed to each tool path, from the config root.
| Tool | CLI contract |
|---|---|
| Critique | Tools/Critique.ts --video <mp4> | --image <png> [--images <glob>] --brief <Brief.json> [--bar 8.5] [--samples 12] [--concurrency N] [--vendors openai,anthropic] [--sample-seed <n>] [--out <dir>] [--json] [--allow-identity] |
| Deliver | Tools/Deliver.ts --artifact <file> [--critique <Critique.json>] --to <dir> |
| Calibrate | Tools/Calibrate.ts --artifact <file> --verdict <1-10> --note "<text>" |
Each intent file carries its tool's defaults, refusals and exit codes.
User customizations live at <configRoot>/LIFEOS/USER/CUSTOMIZATIONS/SKILLS/ArtDirection/ (configRoot is $CLAUDE_CONFIG_DIR when set, else ~/.claude). When it exists, its PREFERENCES.md, configurations and resources override the defaults here; when absent, the defaults stand. First-time setup (accounts, keys, config, a proof it works) is in Setup.md.
"calibration": "<target>". Critique then adds that Calibrate target's Taste.json (the principal's labeled likes and dislikes) to the judge prompt and records its labels_hash in the report; a target with no profile yet is noted under outstanding. Briefs without the field produce the prompt they always did.~/.claude/LIFEOS/USER/CUSTOMIZATIONS/SKILLS/ArtDirection/labels.jsonl (fields in Intents/Calibrate.md).art_judges in <configRoot>/LIFEOS/USER/CUSTOMIZATIONS/SKILLS/ArtDirection/Config.md (OpenAI, Anthropic and Google have seats; a missing file or key stops the critique with an error naming both). That folder's PREFERENCES.md, when present, is appended to References/Rubric.md as install-specific judging rules, and check_set.version hashes the two together. OpenAI vision runs as codex exec -i through the codex CLI signed in to ChatGPT (Assay/Tools/OpenAIVision.ts; no API key is read); Anthropic vision runs through LIFEOS/TOOLS/Inference.ts image input (the claude CLI on the subscription), never falling back to another vendor. Panel selection (--vendors) is in Intents/Critique.md. No credentials belong in briefs or logs.LIFEOS/TOOLS/models.ts: CROSS_VENDOR.openaiJudge for OpenAI and the high rung of EFFORT_MODEL for Anthropic, never pinned here..claude location.Deliver.ts because a first-draft video reached the principal with no critique on 2026-09-17, while the rule lived only in prose (the story is in the USER extension's History.md).concept (does the artifact carry its idea as one metaphor a stranger reads at a glance), and overall follows concept most. Changed 2026-09-28 after the principal's first Calibrate scores showed the old craft-first rubric ranking the scored artifacts almost at random (the measurement is in the USER extension's History.md).User: "iterate until it's great" on a render → Loop intent → Brief.json and Direction.md exist, critique rounds run until the artifact passes the bar, or the four-round cap is reported with its shortfall.
User: "rate the visuals" → Critique intent → Critique.json with both vendors' scores, ranked defects and a pass, fail or unavailable verdict.
User: "that one's a 6, the type is cramped" → Calibrate intent → one label appended with verdict 6 and the note in the principal's words.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Find and fetch vendor cybersecurity reports, then compare their findings on topics such as ransomware, breaches, cloud security, and AI. Analyses identify the reports consulted and cite each figure by vendor, year, and report, including where sources disagree.
Compare a component's own design needs with the goals of the larger system through three structured passes. The result identifies conflicts, recommends an appropriate scope, and assesses whether the proposed design fits the whole.
Find quotes that fit a text’s themes, with attribution and a short reason for each suggestion. Add sourced quotes, research thinkers, and organize a quote collection by theme and usage history to avoid repetition.
Create blog illustrations, technical diagrams, comparisons, comics, and icons through workflows tailored to each format. The skill guides composition, color, and model selection, then stages generated images for review before they are used in a project.
Find arXiv papers by topic, research category, or paper ID. Retrieve titles, authors, abstracts, and links, check new submissions, and add AlphaXiv's AI-generated overviews when available to help decide which papers to read.
Evaluate prompts, models, and agents with code checks or calibrated model judges, then compare results across repeated trials or A/B runs. It reports reliability measures and can turn subjective decisions into structured judgment questions and evaluation pipelines.