derekslinz

Generates static visual content across 20+ formats via Flux, Nano Banana Pro (Gemini 3 Pro), and GPT-Image-1. Covers blog header illustrations, editorial art, Mermaid flowcharts, technical architecture diagrams, D3.js dashboards, taxonomies, timelines, 2x2 framework matrices, comparisons, annotated screenshots, recipe cards, aphorism/quote cards, conceptual maps, stat cards, comic panels, YouTube thumbnails, PAI pack icons, and brand-logo wallpapers. Named workflows: Essay, D3Dashboards, Visualize, Mermaid, TechnicalDiagrams, Taxonomies, Timelines, Frameworks, Comparisons, AnnotatedScreenshots, RecipeCards, Aphorisms, Maps, Stats, Comics, YouTubeThumbnailChecklist, AdHocYouTubeThumbnail, CreatePAIPackIcon, LogoWallpaper, RemoveBackground. SKILLCUSTOMIZATIONS loads PREFERENCES.md, CharacterSpecs.md, and SceneConstruction.md. --remove-bg flag produces transparent-background PNG (can produce black backgrounds — verify visually). Up to 14 reference images per request (5 human, 6 object Gemini API limit). Output s

Generate illustrations, technical diagrams, mermaid flowcharts, infographics, header images, thumbnails, comics, and PAI pack icons using multiple rendering backends. USE WHEN art, header images, visualizations, mermaid, flowchart, technical diagram, infographic, PAI icon, pack icon, YouTube thumbnails, ad hoc thumbnails, annotated screenshots, aphorisms, comics, comparisons, D3 dashboards, embossed logo wallpaper, essay illustration, frameworks, maps, recipe cards, remove background, stats, taxonomies, timelines, brand wallpaper, visualize, generate image, Midjourney, compose thumbnail, generate prompt.

Visual and video content creation — illustrations, diagrams, mermaid flowcharts, infographics, header images, PAI pack icons, thumbnails, comics, and programmatic video via Remotion. USE WHEN art, header images, visualizations, mermaid, diagrams, flowcharts, infographics, pack icons, video, animation, motion graphics, Remotion, video rendering, YouTube thumbnails, comics, comparisons, frameworks, maps, timelines, taxonomies, stats, aphorisms, recipe cards, annotated screenshots, D3 dashboards, embossed logo wallpaper, remove background, essay illustration, technical diagrams, content to animation, generate image, Midjourney.

Generate prioritized PAI upgrade recommendations via 4 parallel threads: Thread 0 (prior-work audit — reads current Algorithm, PATTERNS.yaml, hooks, settings, recent ISAs, and KNOWLEDGE to assign Prior Status tags), Thread 1 (user context — TELOS goals, active projects, PAI system state), Thread 2 (source collection — Anthropic releases, YouTube channels, GitHub trending, custom sources), Thread 3 (internal reflections — Algorithm execution Q1/Q2 patterns). Output format: Discoveries table ranked by interestingness, then tiered Recommendations (CRITICAL/HIGH/MEDIUM/LOW) each with Prior Status (NEW/PARTIAL/DISCUSSED/REJECTED/DONE), then full Technique Details with before/after code. Every recommendation cites file:line evidence from Thread 0 — already-implemented items go to Skipped, never re-surfaced. Workflows: Upgrade, MineReflections, AlgorithmUpgrade, ResearchUpgrade, FindSources, TwitterBookmarks. USE WHEN upgrade, system upgrade, check Anthropic, new Claude features, algorithm upgrade, PAI upgrade, chec

Extract system improvements from content AND monitor external sources (Anthropic ecosystem, YouTube). USE WHEN upgrade, improve system, system upgrade, analyze for improvements, check Anthropic, Anthropic changes, new Claude features, check YouTube, new videos, algorithm upgrade, mine reflections, find sources, research upgrade, PAI upgrade.

Developer utilities and tools — CLI generation, skill scaffolding, agent delegation, system upgrades, evals, documents, parsing, audio editing, Fabric patterns, Cloudflare infrastructure, browser automation, meta-prompting, and aphorisms. USE WHEN create CLI, build CLI, command-line tool, wrap API, add command, upgrade tier, TypeScript CLI, create skill, new skill, scaffold skill, validate skill, update skill, fix skill structure, canonicalize skill, parallel execution, agent teams, delegate, workstreams, swarm, upgrade, improve system, system upgrade, check Anthropic, algorithm upgrade, mine reflections, find sources, research upgrade, PAI upgrade, eval, evaluate, test agent, benchmark, verify behavior, regression test, capability test, run eval, compare models, compare prompts, create judge, view results, document, process file, create document, convert format, extract text, PDF, DOCX, XLSX, PPTX, Word, Excel, spreadsheet, PowerPoint, presentation, slides, consulting report, large PDF, merge PDF, fill form,

Compose CUSTOM agents from Base Traits + Voice + Specialization, and manage predefined functional TEAMS. Traits combine expertise (security, technical, research), personality (skeptical, analytical, enthusiastic), and approach (thorough, rapid, systematic). ComposeAgent.ts merges base + user config, outputs unique prompt + ElevenLabs voice + prosody. Predefined teams: engineering, architecture, marketing, design, security, research, content, strategy — each YAML-configured with roles, tensions, and specialist members. Observer team variant: read-only oversight agents that vote continue/halt/escalate against the tool-activity audit log (high-blast-radius or unattended runs only). USE WHEN create custom agents, spin up agents, specialized agents, agent personalities, available traits, list traits, agent voices, compose agent, spawn parallel agents, launch agents, engineering team, architecture team, marketing team, design team, security team, research team, content team, strategy team, get the team on this, obs

Scrape social media platforms, business data, and e-commerce via Apify actors — Instagram profiles/posts/hashtags/comments, LinkedIn profiles/jobs/posts, TikTok profiles/hashtags/videos/comments, YouTube channels/search/comments, Facebook posts/groups/comments, Google Maps business search with contact/review/image extraction, Amazon products/reviews/pricing, and general-purpose multi-page web crawling with custom pageFunction extraction logic. File-based TypeScript wrappers (scrapeInstagramProfile, searchGoogleMaps, scrapeAmazonProduct, scrapeWebsite, etc.) filter and transform data in code before returning to model context, achieving 95-99% token savings over direct MCP protocol. Parallel multi-platform queries via Promise.all for social listening dashboards. Lead enrichment pipeline: Google Maps → qualified filter → optional LinkedIn enrichment. Competitive analysis across Instagram, YouTube, and TikTok simultaneously. USE WHEN scrape Instagram, scrape LinkedIn, scrape TikTok, scrape YouTube, scrape Faceboo

Audits a commercial-photography catalog for entries that require a signed model release. Four-tier classification (HARD-FLAG / SOFT-FLAG / OK / EXEMPT) keyed to identifiability-to-the-general-public, not facial recognition alone. Stricter bar for children (parental release) and workers at workplaces. Mandatory 2048px-long-edge downscale before viewing any image — pixels falsify description-only assumptions every time. Pairs with property-release-review for the rights side of the same catalog. USE WHEN model release review, person release, can I sell this print, identifiable person audit, candid model audit, child in catalog, worker in catalog, portrait release audit. NOT FOR property/architecture/artwork rights (use property-release-review).

Workflow for processing JPEG photos: view each image, generate a descriptive title (5–9 words), 60–90 word description, and 8–12 keywords; reverse-geocode any embedded GPS coordinates via Nominatim to add specific location detail; embed all metadata as IPTC fields using exiftool (without creating backup files); and rename each file to a hyphenated version of its title. USE when the user says things like: "tag these photos", "add metadata to my images", "generate keywords for photos", "embed IPTC data", "rename photos with descriptive names", "process these JPEGs", "add titles and descriptions to my photos", "geolocate my photos", or any request involving generating and embedding photo metadata at scale. Trigger even if only one of these steps is mentioned — the full workflow adds value every time.

Audits a commercial-photography catalog for entries that require property releases, trademark clearance, or copyright analysis on depicted subjects (buildings, interiors, permanent public artwork, branded venues, signage, vehicles). Four-bucket disposition (remove / delist / SOFT-FLAG / OK / EXEMPT). Mandatory 2048px-long-edge downscale before viewing any image. Sibling skill: model-release-review for the persons-in-frame side. USE WHEN property release, image rights, can I sell this print, trademark in catalog, copyright in catalog, freedom-of-panorama question, sculpture in frame, venue in frame, branded building, catalog rights audit. NOT FOR persons / model releases (use model-release-review).

Step 2 of 5 in the photo intake pipeline. Assesses each candidate photo against technical, editorial, and print-readiness criteria before the image moves to legal review. Produces a PASS / CONDITIONAL PASS / FAIL verdict per image. On FAIL, surfaces specific reasons and waits for user instruction — takes no destructive action. Mandatory 2048px downscale before the model views any image, plus a deterministic measurement pass (bundled Pillow/numpy extractor) that grounds the technical and print-readiness verdicts in real metrics. USE WHEN: quality check, quality gate, review photos before publishing, are these good enough, editorial review, technical review, print-ready check, assess photos. NOT FOR: metadata tagging (use /Photo-Metadata-Helper), rights audits (use /property-release-review and /model-release-review), final publishing (use /reviewed-photo-publish).

Step 5 of 5 in the photo intake pipeline. Takes a photo that has cleared metadata, quality, property, and model review and pushes it live — writes the catalog entry, creates the sales-platform product and child prices (one per supported print size), regenerates derived lists (for-sale, gallery, sitemap), moves the file from intake to the published location, and archives the original. Mandatory dry-run before any live sales-platform mutation. Mandatory 2048px-long-edge downscale for any pre-flight visual verification. USE WHEN: publish photo, list this print, push to sales, add to catalog, go live, finalize listing, complete the intake pipeline. NOT FOR: metadata tagging (use photo-metadata-helper), quality gating (use quality-review), rights audits (use property-release-review / model-release-review), or unpublishing a live entry (that's the remediation pipeline in property-release-review).

The fundamental theory and practice of selecting the strongest photographs from a large shoot — for print, wall-art, a portfolio, or client delivery. Use this skill whenever the user wants to "find the best shots", "pick keepers", "cull", "photo review", "review my photos/shoot", "go through my photos", "narrow down a shoot", "choose prints", "select wall-art candidates", or sort through hundreds/thousands of frames, even if they don't say the word "cull". It teaches the core discipline (you can't pick the best of a series until you've seen all of it), how to read photo groups (recognizing HDR / panorama / focus-stack merge sets and incidental shutter bursts vs. true pick-one bursts), judging an image's edited-and-cropped potential rather than its as-shot thumbnail, and the human + dispassionate-eye partnership that guards against sentimental bias — grounded in a concrete Adobe Lightroom (cloud/CC) workflow (Assisted Culling Stack, Photo Merge, safe color labels) but applicable in any tool.

Audits a commercial-photography catalog for entries that require a signed model release. Four-tier classification (HARD-FLAG / SOFT-FLAG / OK / EXEMPT) keyed to identifiability-to-the-general-public, not facial recognition alone. Stricter bar for children (parental release) and workers at workplaces. Mandatory 1024px-long-edge downscale before viewing any image — pixels falsify description-only assumptions every time. Pairs with property-release-review for the rights side of the same catalog. USE WHEN model release review, person release, can I sell this print, identifiable person audit, candid model audit, child in catalog, worker in catalog, portrait release audit. NOT FOR property/architecture/artwork rights (use property-release-review).

Workflow for processing JPEG photos: view each image, generate a descriptive title (5–9 words), 60–90 word description, and 8–12 keywords; reverse-geocode any embedded GPS coordinates via Nominatim to add specific location detail; embed all metadata as IPTC fields using exiftool (without creating backup files); and rename each file to a hyphenated version of its title. USE when the user says things like: "tag these photos", "add metadata to my images", "generate keywords for photos", "embed IPTC data", "rename photos with descriptive names", "process these JPEGs", "add titles and descriptions to my photos", "geolocate my photos", or any request involving generating and embedding photo metadata at scale. Trigger even if only one of these steps is mentioned — the full workflow adds value every time.

Audits a commercial-photography catalog for entries that require property releases, trademark clearance, or copyright analysis on depicted subjects (buildings, interiors, permanent public artwork, branded venues, signage, vehicles). Four-bucket disposition (remove / delist / SOFT-FLAG / OK / EXEMPT). Mandatory 1024px-long-edge downscale before viewing any image. Sibling skill: model-release-review for the persons-in-frame side. USE WHEN property release, image rights, can I sell this print, trademark in catalog, copyright in catalog, freedom-of-panorama question, sculpture in frame, venue in frame, branded building, catalog rights audit. NOT FOR persons / model releases (use model-release-review).

Step 2 of 5 in the photo intake pipeline. Assesses each candidate photo against technical, editorial, and print-readiness criteria before the image moves to legal review. Produces a PASS / CONDITIONAL PASS / FAIL verdict per image. On FAIL, surfaces specific reasons and waits for user instruction — takes no destructive action. Mandatory 1024px downscale before viewing any image. USE WHEN: quality check, quality gate, review photos before publishing, are these good enough, editorial review, technical review, print-ready check, assess photos. NOT FOR: metadata tagging (use /Photo-Metadata-Helper), rights audits (use /property-release-review and /model-release-review), final publishing (use /publish).