diff --git a/skills/4k-vfx/SKILL.md b/skills/4k-vfx/SKILL.md index f9c1c6d..ed15905 100644 --- a/skills/4k-vfx/SKILL.md +++ b/skills/4k-vfx/SKILL.md @@ -1,6 +1,7 @@ --- name: 4k-vfx description: >- + Use when the user asks for 4k vfx or a task matching the examples below. Turn a plain video clip into a cinematic 4K AI-VFX shot. Give Claude a video and the change you want; it reads EVERY frame via local contact sheets and understands the audio, writes a diff --git a/skills/anime-soccer/SKILL.md b/skills/anime-soccer/SKILL.md index 82d28e7..457cce5 100644 --- a/skills/anime-soccer/SKILL.md +++ b/skills/anime-soccer/SKILL.md @@ -1,6 +1,7 @@ --- name: anime-soccer description: >- + Use when the user asks for anime soccer or a task matching the examples below. Put the USER into a ~45s Japanese-anime football short as the hero — from their photo + their favorite team + the opponent. Anime-fies the user's face into a consistent character sheet, designs a dramatic 3-act match (come on → equalizer diff --git a/skills/app-sizzle/SKILL.md b/skills/app-sizzle/SKILL.md index 1d04b59..7134567 100644 --- a/skills/app-sizzle/SKILL.md +++ b/skills/app-sizzle/SKILL.md @@ -1,6 +1,7 @@ --- name: app-sizzle description: > + Use when the user asks for app sizzle or a task matching the examples below. Generate cinematic 1080p iOS app teaser videos from real App Store screenshots, with a GPT-image-2 enhancement pass on each selected screen before generation. Output is a beat-driven cinematic teaser built from GPT-enhanced screenshots, @@ -570,6 +571,7 @@ Typical run time is 4-8 minutes. All pre-generation stages before the first paid | Kling fallback | 5-15 min | Capacity wait or worker handoff may temporarily show `queued`; follow the Kling queued/handoff recovery runbook | | Download verification | <30s | Local sanity check before delivery | + ## Engine Choice: Seedance Primary, Kling Fallback Seedance is the default because it handles polished motion-graphics references and 1080p app teasers well. Kling is the fallback for moderation, balance, or Seedance timeout failures because it is more permissive on some screen content and uses `quality_mode="pro"` for 1080p. diff --git a/skills/app-store-screens/SKILL.md b/skills/app-store-screens/SKILL.md index db3216f..dd9b540 100644 --- a/skills/app-store-screens/SKILL.md +++ b/skills/app-store-screens/SKILL.md @@ -1,6 +1,7 @@ --- name: app-store-screens description: > + Use when the user asks for app store screens or a task matching the examples below. Generate 5–6 App Store screenshots in a given brand's aesthetic from a `brand.md`, raw product screenshots, or a public App Store listing fetched through Pika MCP. Story-driven (hook → value → features → proof → close), splashy, on-brand. @@ -517,6 +518,7 @@ Typical run time is 10-25 minutes, depending on how much user confirmation is ne | HTML composite + render | 5-10 min | Six 1290x2796 PNGs plus contact sheet | | QA revisions | variable | Copy tweaks are cheap; new imagery is slower | + ## Failure Modes | Symptom | Cause | Fix | diff --git a/skills/baseball-trend/SKILL.md b/skills/baseball-trend/SKILL.md index c73bb8a..2885b73 100644 --- a/skills/baseball-trend/SKILL.md +++ b/skills/baseball-trend/SKILL.md @@ -1,6 +1,7 @@ --- name: baseball-trend description: > + Use when the user asks for baseball trend or a task matching the examples below. Viral fake "ESPN behind-home-plate broadcast cutaway" of a user — broadcast-style still + 15s Kling-omni clip with native two-announcer commentary that names the user. Fixed trend: Yankees vs Red Sox ALCS Game 3 at Fenway Park, premium seats, scorebug + chyron @@ -242,6 +243,7 @@ Typical run time is 4-7 minutes: | Kling video | 3-5 min | One 15s pro render with native commentary | | Delivery check | <30s | Verify final URL and obvious identity/chyron continuity | + ## Failure modes | Symptom | Cause | Fix | diff --git a/skills/build-a-brand/SKILL.md b/skills/build-a-brand/SKILL.md index e2b5955..b3d6f58 100644 --- a/skills/build-a-brand/SKILL.md +++ b/skills/build-a-brand/SKILL.md @@ -1,6 +1,7 @@ --- name: build-a-brand description: > + Use when the user asks for build a brand or a task matching the examples below. Build a practical brand identity from any input — an idea, an existing website, a list of reference brands, product photos, or "I want to rebrand X". Default to a fast quick-brand path for founder-kit users, and offer the full 14-16-page guidelines as an opt-in upgrade. Use @@ -688,6 +689,7 @@ Total full target: ~25–45 min wall-clock excluding user response time. Recent --- + ## Failure modes ### Recovering from upstream 5xx on generate_image diff --git a/skills/content-director/SKILL.md b/skills/content-director/SKILL.md index fe64e52..4c09217 100644 --- a/skills/content-director/SKILL.md +++ b/skills/content-director/SKILL.md @@ -1,6 +1,7 @@ --- name: content-director description: >- + Use when the user asks for content director or a task matching the examples below. All-in-one content director that bundles FOUR format specialists — talking-to-camera, silent POV, dance, and stitch/duet — behind a single front door. Ingests the user's Instagram or TikTok handle, then in Stage 0 asks which KIND of trend they want to make diff --git a/skills/explainer/SKILL.md b/skills/explainer/SKILL.md index f11360f..76c6c65 100644 --- a/skills/explainer/SKILL.md +++ b/skills/explainer/SKILL.md @@ -1,6 +1,8 @@ --- name: explainer -description: ~60-80s explainer video for any URL — GitHub repo, product page, docs site, blog post, or launch. Canonical workflow for URL walkthroughs. Use when the user asks to "explain this URL / repo / website / product", "make a walkthrough video for [url]", "demo this site", "Loom-style explainer of [url]", "explainer for github.com/...", or "explain this product link". Drives a real browser through the URL, generates an avatar lipsync, and composites in a 1280×800 macOS Sonoma frame with a 246-pixel bottom-left avatar circle. GitHub URLs activate a repo-aware mode (README scan + live-demo detection); other URLs use a generic page-walkthrough flow. +description: >- + Use when the user asks for explainer or a task matching the examples below. + ~60-80s explainer video for any URL — GitHub repo, product page, docs site, blog post, or launch. Canonical workflow for URL walkthroughs. Use when the user asks to "explain this URL / repo / website / product", "make a walkthrough video for [url]", "demo this site", "Loom-style explainer of [url]", "explainer for github.com/...", or "explain this product link". Drives a real browser through the URL, generates an avatar lipsync, and composites in a 1280×800 macOS Sonoma frame with a 246-pixel bottom-left avatar circle. GitHub URLs activate a repo-aware mode (README scan + live-demo detection); other URLs use a generic page-walkthrough flow. argument-hint: [--focus angles] [--avatar url] [--voice id] [--live-url url] [--lipsync-provider pika|kling] [--no-captions] [--preview] --- @@ -577,6 +579,7 @@ Typical wall-clock is 5-10 minutes with Pika lipsync, or 10-30+ minutes with Kli | Lipsync | 2-5 min Pika / 5-30 min Kling | Kling is opt-in because it is the long pole | | PiP + captions | 1-3 min | Captions skipped when `--no-captions` is set | + ## Known gaps (carried as follow-up server-side work) - **Kling avatar mode and prompt are available.** To enable polished-presenter mode, pass `--lipsync-provider kling` and the Step 9 call should add `mode: "pro"` plus a prompt like `"talking head, face centered, mouth syncs to audio, minimal head movement, professional presenter"`. This is the quality lever for reducing dramatic head motion in the lipsync. diff --git a/skills/fix-my-look/SKILL.md b/skills/fix-my-look/SKILL.md index 77948ff..c5379df 100644 --- a/skills/fix-my-look/SKILL.md +++ b/skills/fix-my-look/SKILL.md @@ -1,6 +1,7 @@ --- name: fix-my-look description: > + Use when the user asks for fix my look or a task matching the examples below. Change ANYTHING inside a video — background, scene, lighting, outfit, weather, mood — from a free-form prompt, while keeping the EXACT original facial identity, motion, speech, audio AND closest supported output ratio. Edits the diff --git a/skills/founder-product-video/SKILL.md b/skills/founder-product-video/SKILL.md index b5ce8a9..3507c25 100644 --- a/skills/founder-product-video/SKILL.md +++ b/skills/founder-product-video/SKILL.md @@ -1,6 +1,7 @@ --- name: founder-product-video description: >- + Use when the user asks for founder product video or a task matching the examples below. Generate a 65-second founder-style product video from a product URL + user-supplied imagery. Output is a 16:9 1080p MP4 — 4 × 15s SeeDance acts of a talking founder + 5s branded end card + background music. The user's actual product screenshots are composited onto product reveal shots @@ -1440,6 +1441,7 @@ Wall-clock budget per step. Total run is ~12–18 minutes, dominated by the para | [10] edit_concat + edit_audio_mix | 30–90s | server-side normalized concat and music mix | | **Total** | **12–18 minutes** | | + ## Defaults - 4 × 15s SeeDance acts, parallel, unique seeds (101, 202, 303, 404) diff --git a/skills/gameday/SKILL.md b/skills/gameday/SKILL.md index a7d2829..214cd9b 100644 --- a/skills/gameday/SKILL.md +++ b/skills/gameday/SKILL.md @@ -1,6 +1,7 @@ --- name: gameday description: >- + Use when the user asks for gameday or a task matching the examples below. Put a fan into the game. The user uploads one photo of themselves and names their favorite team; generate a 6-photo matchday-superfan carousel — six separate images of that same person at the game in their team's kit. Triggers: diff --git a/skills/kiss-cam/SKILL.md b/skills/kiss-cam/SKILL.md index f21fcde..c2b08e9 100644 --- a/skills/kiss-cam/SKILL.md +++ b/skills/kiss-cam/SKILL.md @@ -1,6 +1,7 @@ --- name: kiss-cam description: >- + Use when the user asks for kiss cam or a task matching the examples below. Generate a viral fake "in-arena Kiss Cam moment" of any two subjects — a fan-filmed phone shot of the MSG Jumbotron with retro Kiss Cam graphic + scoreboard, plus a 15s Kling v3-omni clip with PA-announcer commentary and @@ -222,6 +223,7 @@ Check that both faces stay consistent with their references, the kiss action com If a re-roll is needed at Step 1 the budget restarts there; at Step 2 only the video stage repeats. + ## Load-bearing phrases (keep verbatim) Don't edit these without a re-validation pass — they're empirical behavior dependencies, not stylistic choices. diff --git a/skills/language-swap/SKILL.md b/skills/language-swap/SKILL.md index b8d8c05..2e69972 100644 --- a/skills/language-swap/SKILL.md +++ b/skills/language-swap/SKILL.md @@ -1,6 +1,7 @@ --- name: language-swap description: > + Use when the user asks for language swap or a task matching the examples below. Translate and dub a video into another language. One worker call preserves each speaker's voice, translates the speech, and returns a fully A/V-synced video. Lipsync ON by default. Use when the user says "translate this video", "dub this in ", @@ -19,7 +20,6 @@ required-capabilities: - add_captions --- - # /pika:language-swap @@ -175,7 +175,3 @@ Reply with `final_video_url` + the translated transcript (from `dub_transcript_s | Lipsync step fails | `edit_lipsync` errors (no clear face track, provider 4xx) | Fall back through `variant` tiers (v2-pro → sync-3 → v2); if all fail, return the dubbed video without lip-matching and tell the user | Audio-replaced video, no lip-match | | Captions wrong language | Step 3 auto-transcription mis-detects language | Pass explicit `language` tag; if `dub_subtitles` exists, use `caption_mode="manual"` with it instead of auto | Manual `subtitles[]` | | Bilingual source row unavailable | User asked for bilingual subtitles but `source_subtitles` is absent | Use target-language captions and explain the source transcript was unavailable | Target-language captions only | - -## Compatibility - -Primary target: Claude Code. Uses standard MCP tools only. Works on Codex / Cursor / Claude Desktop. diff --git a/skills/persona-builder/SKILL.md b/skills/persona-builder/SKILL.md index 95a8b3b..1cac951 100644 --- a/skills/persona-builder/SKILL.md +++ b/skills/persona-builder/SKILL.md @@ -1,6 +1,7 @@ --- name: persona-builder description: > + Use when the user asks for persona builder or a task matching the examples below. Whip a person into a more marketable shape online. Read their socials and the way they talk, then deliver real talk about where the money is, what's holding them back, and what to fix — then ship the designed multi-page Influencer Persona PDF + a persona.md folder kit @@ -602,6 +603,7 @@ Tell the user the rough total up front. Total: ~30–60 min wall-clock excluding user response time. + ## Load-bearing phrases Verbatim anchors that go into gpt-image-2 prompts (or procedural rules that hold the recipe together). **Do not paraphrase or strip these when simplifying nearby prose** — they're empirical behavior dependencies, not writing style. Every entry here is referenced inline elsewhere in this file via `(load-bearing — …; see Load-bearing phrases section)`. diff --git a/skills/podcast/SKILL.md b/skills/podcast/SKILL.md index 7fdb819..b0efefe 100644 --- a/skills/podcast/SKILL.md +++ b/skills/podcast/SKILL.md @@ -1,6 +1,7 @@ --- name: podcast description: >- + Use when the user asks for podcast or a task matching the examples below. Two-host podcast video for any URL or free-form topic — 1 minute, 4 acts × ~15s, native multi-shot dialogue, optional voice cloning for Host A. Use when the user asks to "make a podcast", "podcast about [thing]", "podcast review of [url]", @@ -258,6 +259,7 @@ If the user or execution harness has a tight budget below 32 min, warn upfront t | Four Kling acts | 24-32 min | 4 × ~8 min sequential Kling Omni calls; dominant cost | | Concat + return | 30-90s | Final URL only; captions skipped by default | + ## Failure modes ### Recovering from upstream 5xx on capture_website / clone_voice / generate_video / edit_concat diff --git a/skills/stagefight/SKILL.md b/skills/stagefight/SKILL.md index 5bbc4f6..dbb1b2a 100644 --- a/skills/stagefight/SKILL.md +++ b/skills/stagefight/SKILL.md @@ -1,6 +1,7 @@ --- name: stagefight description: >- + Use when the user asks for stagefight or a task matching the examples below. Generate a viral "fan-filmed staged fight" clip — POV phone footage of two costumed performers having a choreographed cosplay battle on an elaborate themed stage at a live outdoor event, with a believable live-stage effect diff --git a/skills/ugc-ads/SKILL.md b/skills/ugc-ads/SKILL.md index 1e98e12..8a95a2c 100644 --- a/skills/ugc-ads/SKILL.md +++ b/skills/ugc-ads/SKILL.md @@ -1,6 +1,7 @@ --- name: ugc-ads description: >- + Use when the user asks for ugc ads or a task matching the examples below. Multi-cut jump-cut UGC product ad — HOOK + 3 JUMP CUTs + OUTRO, 15s, 9:16 vertical (3:4 optional, seedance only), POV first-person talking-head selfie, every beat has spoken dialogue with native lip-sync, 5-act narrative arc @@ -47,6 +48,7 @@ Typical end-to-end run: **6–12 minutes**. Breakdown: If the run exceeds 15 min without progress, something is wrong — inspect the tool-reported generation status and error message. + ## Pre-generation wall-clock guard Start a timer at skill start once the product URL is available and the cost gate has passed. Time spent waiting for the user's `proceed` reply is not prep time and must not trigger this guard. The first paid generation call is `generate_reference_video`, the long-pole paid stage, and it must be invoked within 5 minutes of skill start. If you have not invoked `generate_reference_video` within 5 minutes of skill start, stop before any paid generation call and report `failed_pre_generation_timeout` with what you have so far: fetched product facts, chosen category, avatar source, screenshot status, draft dialogue, and the exact blocker. Do not keep refining script wording, prompt grounding, or shot order. diff --git a/skills/vfx/SKILL.md b/skills/vfx/SKILL.md index 7f0afe7..21aada1 100644 --- a/skills/vfx/SKILL.md +++ b/skills/vfx/SKILL.md @@ -1,6 +1,7 @@ --- name: vfx description: >- + Use when the user asks for vfx or a task matching the examples below. Turn a plain video clip into a cinematic AI-VFX shot at 1080p by default (or 4K / 720p on request). Give Claude a video and the change you want; it reads EVERY frame via local contact sheets and understands the audio, diff --git a/skills/viral-hook/SKILL.md b/skills/viral-hook/SKILL.md index e1be6ce..7c2a656 100644 --- a/skills/viral-hook/SKILL.md +++ b/skills/viral-hook/SKILL.md @@ -1,6 +1,7 @@ --- name: viral-hook description: >- + Use when the user asks for viral hook or a task matching the examples below. Prepend a 4s viral hook + optional designed title to a user's video, then hard-cut into the real clip. An attention-grabbing event erupts into the user's OWN scene; the title is rendered in-scene by Seedance. One MCP call does the whole render. Requires Pika MCP. diff --git a/skills/voxel-it/SKILL.md b/skills/voxel-it/SKILL.md index 4171f05..8dd2bc2 100644 --- a/skills/voxel-it/SKILL.md +++ b/skills/voxel-it/SKILL.md @@ -1,6 +1,7 @@ --- name: voxel-it description: > + Use when the user asks for voxel it or a task matching the examples below. Voxel-It — turn any photo into a high-quality Minecraft screenshot, keeping the HUMAN subject(s) fully photorealistic while the rest of the frame becomes detailed Minecraft block geometry, then cinematic-color-grade the whole frame to