All skills
hoodini avatar

/image-master

@83e2083

Master prompt-engineer for photoreal, artifact-free AI still images on ANY tool (Reve, Midjourney, Flux, GPT-image, Imagen, Nano Banana, Stable Diffusion). Builds prompts that hit National-Geographic-grade realism — true skin/fur texture (no plastic), correct anatomy/hands/faces, physically coherent light/shadows/reflections, clean legible text — while engineering deliberate visual IMPACT (color contrast, composition, awe/adrenaline, a striking point of view). Runs a gated process: lock the point-of-view and build the 8-block Capture Stack BEFORE generating, then run a forensic pre-submit inspection against the known artifact list. Use whenever the goal is a single still image that must look REAL and hold up under close inspection — contest entries, hero shots, product/character/wildlife/architecture/concept art, or any time AI images come out plastic, distorted, or fake. Composes with nano-banana-2 (execution) and director (motion). Hebrew triggers: תמונה, תמונות, פוטוריאליזם, ריאליזם, לייצר תמונה, פרומפט לתמונה, בלי עיוותים, עור פלסטיק, ידיים מעוותות, פרצוף מעוות, חדות, נשיונל ג'יאוגרפיק.

Use this Skill: https://skilld.dev/gh/hoodini/ai-agents-skills/image-master

This session only. Nothing lands on disk.

references00-INDEX.md

≈976 tokens on demand. Your agent reads this file only when SKILL.md points to it.

image-master references — index

The SKILL.md carries the load-bearing core you apply by heart. These chapters are the depth, read on demand.

File What's in it Read when
01-realism-anatomy-skin.md Hands, faces, bodies, the plastic-skin attack vocabulary, negative-vs-positive per tool A human/animal subject must hold up: anatomy, hands, faces, skin
02-physics-light-optics.md One-light discipline, reflections/catchlights, real camera+lens banks, atmosphere/depth, materials, motion, the anti-pattern blacklist Making the image physically and optically believable (the NatGeo look)
03-typography-text.md The quote-short-caps trinity, per-model text reliability, background-text-vague rule, composite-in-post workflow, Hebrew Any signage, poster, logo, label, or rendered text
04-impact-and-composition.md Color recipes, composition for eye-path, drama/chiaroscuro/scale/decisive-moment, single-image narrative devices Engineering deliberate emotional + visual punch
05-prompt-library.md Copy-paste 8-block skeletons per discipline + fully worked examples (incl. the war-from-animals series) You want a ready scaffold or a worked model to adapt
06-tool-adapters.md Reve 2.0 deep notes + per-tool quirks (MJ, Flux, GPT-image, Imagen, Nano Banana, SD) and how to translate one prompt across tools Tuning a built prompt for a specific generator
07-pre-submit-inspection.md The forensic QA checklist mapping to the 13 penalized artifacts; pre-flight (on prompt) + post-flight (on output) Before locking/submitting any image
08-series-consistency.md Series cohesion (Style Lock), recurring-character consistency, the full-prompt hard rule, the worked 10-image animal-war bible Building a SET that must feel unified and keep characters consistent
09-magazine-cover-treatment.md Editorial cover layer: composite-type workflow, caption craft (kicker+headline), the design-system lock, IP safety, the worked "WITNESS" captions Adding a magazine masthead + short stylized caption to each image
10-directing-emotion.md The decisive emotional moment, animal affect cues, the signature heart-breaking micro-detail, the war-in-the-eye device, the emotion gate Making a frame ACHE — when output is technically clean but neutral/dead
11-finishing-layer.md The 10/10 difference-makers: wet-eye layered reflections, eye-muscle expression, real tear physics, strand-level fur + selective focus, true non-airbrushed colour, the honest emotional hooks (gaze, neoteny, identifiable victim), the FINISHING STACK clause Pushing a near-final image from 9 to 10 — indistinguishable-from-real + maximum emotional pull
12-award-winning-composition.md What wins photo contests (10 common denominators) + the stop-scroll techniques (scale juxtaposition, eye-mirror & water reflections, unusual angles, layering, subject-breaks-text-plane depth cover, decisive moment, gaze, selective focus, colour) + the Range+Vision portfolio strategy Designing world-class, contest-winning concepts with sophistication, depth, and range
13-conceptual-message-images.md Conceptual/message-driven image patterns (irony, role-reversal, juxtaposition, self-confrontation, split-frame), execution rules for multi-person scenes, the DE-BRAND/IP disqualifier rule, English-text-only Building idea-driven social-commentary images that carry a message (the winning Vision)

The master rule across every chapter: prompt toward specific photographic reality, away from the retouched-stock average; describe what you DO want, not what you forbid.

Currency: the AI-tool layer (chapters 03/05/06 model notes) drifts monthly — re-verify a model's text/negative/aspect behavior before relying on it. The physics, anatomy, light, color, and composition craft (01/02/04) is stable.

Source: SKILL.md on GitHub

No alerts3mo3 checks · Risk SAFE
  • Gen Agent Trust Hub3mo

    The skill is a comprehensive instructional framework for AI image prompt engineering. It consists entirely of Markdown documentation and does not contain any executable code, scripts, or mechanisms for data exfiltration. All external references are informative and point to legitimate AI and photography resources.

  • Socket3mo

    No alerts

  • Snyk3mo

    Risk: LOW · No issues

Signed by skilld at 83e2083. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 days ago.

Steadyupdated 4 months ago

README badge

README badge for hoodini/ai-agents-skills/image-master