[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F9GKSDV47AE8CWQ89R38EC":3,"skill-same:01M7F9GKSDV47AE8CWQ89R38EC":49},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M7F9GKSDV47AE8CWQ89R38EC","general-video",null,"The fallback workflow for authoring custom HyperFrames video compositions at any length or format — longer or multi-scene pieces, brand \u002F sizzle reels, montages, title cards, static loops, and freeform compositions. Input- and length-agnostic. If a specialized workflow clearly fits the input — a marketed product, a website, a topic explainer, a GitHub PR, existing footage, a short motion graphic, or a Remotion port — prefer it (see \u002Fhyperframes); use this only as the general fallback when none fit.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fgeneral-video-rove\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: general-video\ndescription: \"The fallback workflow for authoring custom HyperFrames video compositions at any length or format — longer or multi-scene pieces, brand \u002F sizzle reels, montages, title cards, static loops, and freeform compositions. Input- and length-agnostic. If a specialized workflow clearly fits the input — a marketed product, a website, a topic explainer, a GitHub PR, existing footage, a short motion graphic, or a Remotion port — prefer it (see \u002Fhyperframes); use this only as the general fallback when none fit.\\n\"\nmetadata: {\"tags\":\"orchestrator, general-video, fallback, freeform, composition-authoring\"}\n---\n# general-video — general video workflow\n\n> **Confirm the route before you build.** This is the **fallback** for custom composition authoring. If the input clearly fits a specialized workflow, prefer it: topic explainer → `\u002Ffaceless-explainer`; GitHub PR → `\u002Fpr-to-video`; existing footage → `\u002Fembedded-captions` · `\u002Ftalking-head-recut`; short unnarrated motion graphic → `\u002Fmotion-graphics`. **Out of scope**: live \u002F at-render-time data, NLE-style editing of a finished video, or producing footage HyperFrames can't capture. Unsure? **Read `\u002Fhyperframes` first.**\n\n**Build exactly what was asked.** A title card is a title card — not a title card + three supporting scenes + captions. If extra scenes or elements would genuinely improve the piece, _propose_ them; don't add them silently. For small edits (fix a color, adjust one duration, add one element), skip the planning steps and go straight to the build.\n\n## Approach\n\n### Discovery — open-ended requests only\n\nFor vague, exploratory requests (\"make something for our brand\", \"a cool intro\") — understand intent before picking colors:\n\n- **Audience** — who watches? developers \u002F executives \u002F general consumers?\n- **Platform** — where does it play? social (15s) \u002F website hero \u002F product demo \u002F internal?\n- **Priority** — what matters most? motion quality \u002F content accuracy \u002F brand fidelity \u002F speed?\n- **Variations** — one best shot, or 2-3 meaningfully different options (different pacing, energy, or structure — not just color swaps)?\n\nFor specific requests (\"add a title card\", \"fix the timing on scene 3\"), skip discovery.\n\n### Step 1 — Design system → `hyperframes-design`\n\nEstablish the visual identity first. If the project has a design spec, read it (precedence `frame.md` → `design.md` → `DESIGN.md`; treat it as brand truth — exact colors, fonts, constraints).\n\n**If no spec exists, you MUST read BOTH `hyperframes-design\u002Freferences\u002Fhouse-style.md` AND `hyperframes-design\u002Freferences\u002Fvideo-composition.md` before choosing any color or font.** `house-style.md` gives the \"interpret the prompt \u002F generate real content\" opener, lazy-default list, and layer recipe; `video-composition.md` gives the video-medium density \u002F scale \u002F **foreground detailing** (data bars, registration marks, monospace metadata, \"8-10 elements, two the user didn't ask for\") that separates \"produced\" from \"generated.\" Reading only one is the most common miss — `video-composition.md` is the one agents skip, and it is exactly the one that prevents flat, centered, web-page-looking output. Do not self-invent a palette and skip these; crossing into `hyperframes-design` is mandatory here, not an optional branch. From there, also pull a named style\u002Fmood → `references\u002Fvisual-styles.md` as needed. The spec\u002Fstyle defines the **brand**, not the composition rules.\n\n**Find the angle (vague brief, no spec):** before picking colors, write ONE sentence — what does this name\u002Fword\u002Ftopic evoke, and what visual _world_ (metaphor, setting, instrument, motif) expresses it? E.g. a cybersecurity tool → vault doors \u002F perimeter scan lines \u002F lock tumblers; a meditation app → tide, breath, slow light bloom. Read the _meaning_ of the subject, not just its letters; pick a concrete angle over a literal restyle. This is the cheap substitute for prompt expansion (Step 2) on single-scene pieces, where expansion is correctly skipped — and it is the difference between a designed concept and a generic logo-on-a-gradient.\n\n\u003CHARD-GATE>\nBefore writing ANY composition HTML, verify you have ALL FOUR:\n1. **A visual identity** grounded in the spec or `house-style.md` — not invented on the spot. (Reaching for `#333`, `#3b82f6`, or `Roboto`? You skipped it.)\n2. **A one-sentence concept angle** (the \"find the angle\" step) for anything beyond a trivial edit — not a literal restyle of the prompt words.\n3. **A font pairing from the embed list** (`hyperframes-design\u002Freferences\u002Ftypography.md` → \"Fonts that embed\") chosen on purpose — not `Inter`\u002F`Helvetica Neue`\u002F`system-ui` by default, and never an un-embedded display font you're just hoping renders (un-bundled names embed only if auto-captured locally — and cloud renders won't capture them).\n4. **A foreground\u002Fdensity plan from `video-composition.md`** — the anchor-to-edges, 8-10-elements, foreground-metadata, background-texture rules. (Centered stack on a flat color with fewer than ~6 elements and no edge-anchored detail? You skipped it — that is the generic tell.)\n\u003C\u002FHARD-GATE>\n\n### Step 2 — Prompt expansion → `hyperframes-design`\n\nRun for every multi-scene composition (skip for single-scene pieces and trivial edits). Ground the request against the design spec + house style into a consistent intermediate that downstream work reads the same way. See `hyperframes-design\u002Freferences\u002Fprompt-expansion.md`.\n\n### Step 3 — Plan\n\nBefore writing HTML, think at a high level:\n\n1. **What** — the viewer experience: narrative arc, key moments, emotional beats.\n2. **Structure** — how many compositions, sub-comp vs inline, which tracks carry video \u002F overlays \u002F captions. For the monolithic-single-file vs modular-sub-comp call, see `\u002Fhyperframes\u002Fcore\u002Freferences\u002Fcomposition-patterns.md` § Two Architectures (rule of thumb: ≥3 hard scene cuts, or any reused scene → modularize; a short single-scene piece stays one file).\n3. **Rhythm** — name the pattern before implementing (e.g. `fast-fast-SLOW-SHADER-hold`); see `hyperframes-design\u002Freferences\u002Fbeat-direction.md`.\n4. **Timing** — which clips drive duration, where transitions land, the pacing.\n5. **Layout** — build the end state first (see below).\n6. **Animate** — then add motion via `hyperframes-motion`.\n\n## Layout Before Animation\n\nPosition every element where it sits at its **most visible moment** — fully entered, correctly placed, not yet exiting. Write that as static HTML + CSS first. **No GSAP yet.**\n\n**Why:** if you position elements at their animated start state (offscreen, scaled to 0, opacity 0) and tween to where you _think_ they land, you are guessing the final layout — overlaps stay invisible until render. Build the end state first and you see and fix layout problems before adding motion.\n\n1. **Identify the hero frame** for each scene — the moment the most elements are simultaneously visible. That is the layout you build.\n2. **Write static CSS** for that frame. The content container must fill the scene with padding, not absolute offsets:\n\n```css\n.scene-content {\n  display: flex;\n  flex-direction: column;\n  justify-content: center;\n  width: 100%;\n  height: 100%;\n  padding: 120px 160px; \u002F* padding positions content; fills any scene size *\u002F\n  gap: 24px;\n  box-sizing: border-box;\n}\n```\n\nNever use `position: absolute; top: Npx` on a content container — it overflows when content is taller than the space. Reserve absolute positioning for decoratives.\n\n> ⚠ **The `width\u002Fheight: 100%` above only resolves if every ancestor has a resolved height.** The root `\u003Cdiv data-composition-id>` and any wrapper between it and `.scene-content` must be sized (`position: relative; width: 1920px; height: 1080px` on the root — see `\u002Fhyperframes\u002Fcore` → \"Root must be sized\"). Skip this and the flex container collapses to ~0, content piles into the **top-left corner**, and the first glyph clips at x=0 — while `lint`\u002F`inspect` still report 0 issues. And **always keep the `padding`** (≥80px) on `.scene-content`: it is the title-safe margin. Never replace it with bare `gap`.\n\n3. **Add entrances** — animate FROM offscreen\u002Finvisible TO the CSS position with `gsap.from()` (in sub-compositions prefer `gsap.fromTo()` so the start state is explicit; see `\u002Fhyperframes\u002Fcore\u002Freferences\u002Fsub-compositions.md`). The CSS position is ground truth; the tween is the journey to it.\n4. **Exits are transition-handled** — per the scene-transition rules in `hyperframes-motion\u002Ftransitions\u002F`, only the **final** scene animates elements out; between scenes the transition IS the exit.\n\n**Shared space across time:** if element A exits before element B enters in the same area, both still need correct CSS positions for their respective hero frames — timeline ordering keeps them from coexisting, and the layout step catches accidental overlap. Layered glows\u002Fshadows and z-stacked depth are _intentional_ overlap; the step is about catching _unintentional_ collisions (two headlines on top of each other, content bleeding off-frame).\n\n## Build — delegate to the domain skills\n\nThis maps the skill's full surface (see the `description`) to its references — non-exhaustive; when an intent isn't listed, route through `hyperframes-design` (look\u002Fconcept), `hyperframes-motion` (motion), `\u002Fhyperframes\u002Fcore` (contract). **The first row is ADDITIVE — read it AND your intent row, not one or the other.**\n\n| Building…                                                             | Read first (in order)                                                                                                                                                                                |\n| --------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| **ALWAYS — every non-trivial piece, on top of your intent row below** | `hyperframes-design\u002Freferences\u002Fhouse-style.md` + `references\u002Fvideo-composition.md` (also gated in Step 1 \u002F HARD-GATE; the \"produced, not generated\" foreground detailing)                          |\n| **Kinetic typography \u002F text-forward**                                 | `hyperframes-motion\u002Ftechniques.md` (kinetic type) + `adapters\u002Fgsap-easing-and-stagger.md` + `rules\u002Fkinetic-beat-slam.md`                                                                          |\n| **Title card \u002F lower-third \u002F overlay \u002F PiP \u002F text-behind-subject**    | `hyperframes-design\u002Freferences\u002Fcomposition-patterns.md` + (for the centered\u002Fsized frame) `\u002Fhyperframes\u002Fcore` → \"Root must be sized\"                                                                 |\n| **Logo \u002F brand-mark reveal**                                          | `hyperframes-motion\u002Frules\u002Fsvg-path-draw.md` (draw-on) + `rules\u002F3d-text-depth-layers.md` + `rules\u002Fscale-swap-transition.md`                                                                        |\n| **Data \u002F stats \u002F numbers**                                            | `hyperframes-motion\u002Frules\u002Fcounting-dynamic-scale.md` + `rules\u002Fstat-bars-and-fills.md` + `hyperframes-design\u002Freferences\u002Fdata-in-motion.md`                                                       |\n| **Product \u002F app \u002F UI demo**                                           | `hyperframes-motion\u002Frules\u002F3d-page-scroll.md` + `rules\u002Fcursor-click-ripple.md` + `rules\u002Fpress-release-spring.md`                                                                                   |\n| **Multi-scene \u002F transitions**                                         | `hyperframes-motion\u002Ftransitions\u002Foverview.md` **then** `transitions\u002Fcatalog.md` (you are not done after the overview — the GSAP recipe is in the catalog)                                          |\n| **Modular \u002F sub-compositions**                                        | `\u002Fhyperframes\u002Fcore\u002Freferences\u002Fcomposition-patterns.md` + `references\u002Fsub-compositions.md`                                                                                                             |\n\n## Output checklist → `\u002Fhyperframes\u002Fcli`\n\n- [ ] `npx hyperframes lint` and `npx hyperframes validate` pass (block on results)\n- [ ] design adherence verified if a spec (`frame.md` \u002F `design.md`) exists — checklist in `hyperframes-design\u002Freferences\u002Fdesign-adherence.md`\n- [ ] `npx hyperframes inspect` passes, or every overflow is intentionally marked\n- [ ] contrast warnings addressed; for multi-scene work, review the animation map (`hyperframes-motion\u002Fscripts\u002Fanimation-map.mjs`)\n- [ ] deliver the preview; render to MP4 only on explicit request\n- [ ] surface the preview **only at handoff** (it is the stable, final preview); don't pop one mid-build — build-phase snapshots are headless\n\n","# general-video — general video workflow\n\n> **Confirm the route before you build.** This is the **fallback** for custom composition authoring. If the input clearly fits a specialized workflow, prefer it: topic explainer → `\u002Ffaceless-explainer`; GitHub PR → `\u002Fpr-to-video`; existing footage → `\u002Fembedded-captions` · `\u002Ftalking-head-recut`; short unnarrated motion graphic → `\u002Fmotion-graphics`. **Out of scope**: live \u002F at-render-time data, NLE-style editing of a finished video, or producing footage HyperFrames can't capture. Unsure? **Read `\u002Fhyperframes` first.**\n\n**Build exactly what was asked.** A title card is a title card — not a title card + three supporting scenes + captions. If extra scenes or elements would genuinely improve the piece, _propose_ them; don't add them silently. For small edits (fix a color, adjust one duration, add one element), skip the planning steps and go straight to the build.\n\n## Approach\n\n### Discovery — open-ended requests only\n\nFor vague, exploratory requests (\"make something for our brand\", \"a cool intro\") — understand intent before picking colors:\n\n- **Audience** — who watches? developers \u002F executives \u002F general consumers?\n- **Platform** — where does it play? social (15s) \u002F website hero \u002F product demo \u002F internal?\n- **Priority** — what matters most? motion quality \u002F content accuracy \u002F brand fidelity \u002F speed?\n- **Variations** — one best shot, or 2-3 meaningfully different options (different pacing, energy, or structure — not just color swaps)?\n\nFor specific requests (\"add a title card\", \"fix the timing on scene 3\"), skip discovery.\n\n### Step 1 — Design system → `hyperframes-design`\n\nEstablish the visual identity first. If the project has a design spec, read it (precedence `frame.md` → `design.md` → `DESIGN.md`; treat it as brand truth — exact colors, fonts, constraints).\n\n**If no spec exists, you MUST read BOTH `hyperframes-design\u002Freferences\u002Fhouse-style.md` AND `hyperframes-design\u002Freferences\u002Fvideo-composition.md` before choosing any color or font.** `house-style.md` gives the \"interpret the prompt \u002F generate real content\" opener, lazy-default list, and layer recipe; `video-composition.md` gives the video-medium density \u002F scale \u002F **foreground detailing** (data bars, registration marks, monospace metadata, \"8-10 elements, two the user didn't ask for\") that separates \"produced\" from \"generated.\" Reading only one is the most common miss — `video-composition.md` is the one agents skip, and it is exactly the one that prevents flat, centered, web-page-looking output. Do not self-invent a palette and skip these; crossing into `hyperframes-design` is mandatory here, not an optional branch. From there, also pull a named style\u002Fmood → `references\u002Fvisual-styles.md` as needed. The spec\u002Fstyle defines the **brand**, not the composition rules.\n\n**Find the angle (vague brief, no spec):** before picking colors, write ONE sentence — what does this name\u002Fword\u002Ftopic evoke, and what visual _world_ (metaphor, setting, instrument, motif) expresses it? E.g. a cybersecurity tool → vault doors \u002F perimeter scan lines \u002F lock tumblers; a meditation app → tide, breath, slow light bloom. Read the _meaning_ of the subject, not just its letters; pick a concrete angle over a literal restyle. This is the cheap substitute for prompt expansion (Step 2) on single-scene pieces, where expansion is correctly skipped — and it is the difference between a designed concept and a generic logo-on-a-gradient.\n\n\u003CHARD-GATE>\nBefore writing ANY composition HTML, verify you have ALL FOUR:\n1. **A visual identity** grounded in the spec or `house-style.md` — not invented on the spot. (Reaching for `#333`, `#3b82f6`, or `Roboto`? You skipped it.)\n2. **A one-sentence concept angle** (the \"find the angle\" step) for anything beyond a trivial edit — not a literal restyle of the prompt words.\n3. **A font pairing from the embed list** (`hyperframes-design\u002Freferences\u002Ftypography.md` → \"Fonts that embed\") chosen on purpose — not `Inter`\u002F`Helvetica Neue`\u002F`system-ui` by default, and never an un-embedded display font you're just hoping renders (un-bundled names embed only if auto-captured locally — and cloud renders won't capture them).\n4. **A foreground\u002Fdensity plan from `video-composition.md`** — the anchor-to-edges, 8-10-elements, foreground-metadata, background-texture rules. (Centered stack on a flat color with fewer than ~6 elements and no edge-anchored detail? You skipped it — that is the generic tell.)\n\u003C\u002FHARD-GATE>\n\n### Step 2 — Prompt expansion → `hyperframes-design`\n\nRun for every multi-scene composition (skip for single-scene pieces and trivial edits). Ground the request against the design spec + house style into a consistent intermediate that downstream work reads the same way. See `hyperframes-design\u002Freferences\u002Fprompt-expansion.md`.\n\n### Step 3 — Plan\n\nBefore writing HTML, think at a high level:\n\n1. **What** — the viewer experience: narrative arc, key moments, emotional beats.\n2. **Structure** — how many compositions, sub-comp vs inline, which tracks carry video \u002F overlays \u002F captions. For the monolithic-single-file vs modular-sub-comp call, see `\u002Fhyperframes\u002Fcore\u002Freferences\u002Fcomposition-patterns.md` § Two Architectures (rule of thumb: ≥3 hard scene cuts, or any reused scene → modularize; a short single-scene piece stays one file).\n3. **Rhythm** — name the pattern before implementing (e.g. `fast-fast-SLOW-SHADER-hold`); see `hyperframes-design\u002Freferences\u002Fbeat-direction.md`.\n4. **Timing** — which clips drive duration, where transitions land, the pacing.\n5. **Layout** — build the end state first (see below).\n6. **Animate** — then add motion via `hyperframes-motion`.\n\n## Layout Before Animation\n\nPosition every element where it sits at its **most visible moment** — fully entered, correctly placed, not yet exiting. Write that as static HTML + CSS first. **No GSAP yet.**\n\n**Why:** if you position elements at their animated start state (offscreen, scaled to 0, opacity 0) and tween to where you _think_ they land, you are guessing the final layout — overlaps stay invisible until render. Build the end state first and you see and fix layout problems before adding motion.\n\n1. **Identify the hero frame** for each scene — the moment the most elements are simultaneously visible. That is the layout you build.\n2. **Write static CSS** for that frame. The content container must fill the scene with padding, not absolute offsets:\n\n```css\n.scene-content {\n  display: flex;\n  flex-direction: column;\n  justify-content: center;\n  width: 100%;\n  height: 100%;\n  padding: 120px 160px; \u002F* padding positions content; fills any scene size *\u002F\n  gap: 24px;\n  box-sizing: border-box;\n}\n```\n\nNever use `position: absolute; top: Npx` on a content container — it overflows when content is taller than the space. Reserve absolute positioning for decoratives.\n\n> ⚠ **The `width\u002Fheight: 100%` above only resolves if every ancestor has a resolved height.** The root `\u003Cdiv data-composition-id>` and any wrapper between it and `.scene-content` must be sized (`position: relative; width: 1920px; height: 1080px` on the root — see `\u002Fhyperframes\u002Fcore` → \"Root must be sized\"). Skip this and the flex container collapses to ~0, content piles into the **top-left corner**, and the first glyph clips at x=0 — while `lint`\u002F`inspect` still report 0 issues. And **always keep the `padding`** (≥80px) on `.scene-content`: it is the title-safe margin. Never replace it with bare `gap`.\n\n3. **Add entrances** — animate FROM offscreen\u002Finvisible TO the CSS position with `gsap.from()` (in sub-compositions prefer `gsap.fromTo()` so the start state is explicit; see `\u002Fhyperframes\u002Fcore\u002Freferences\u002Fsub-compositions.md`). The CSS position is ground truth; the tween is the journey to it.\n4. **Exits are transition-handled** — per the scene-transition rules in `hyperframes-motion\u002Ftransitions\u002F`, only the **final** scene animates elements out; between scenes the transition IS the exit.\n\n**Shared space across time:** if element A exits before element B enters in the same area, both still need correct CSS positions for their respective hero frames — timeline ordering keeps them from coexisting, and the layout step catches accidental overlap. Layered glows\u002Fshadows and z-stacked depth are _intentional_ overlap; the step is about catching _unintentional_ collisions (two headlines on top of each other, content bleeding off-frame).\n\n## Build — delegate to the domain skills\n\nThis maps the skill's full surface (see the `description`) to its references — non-exhaustive; when an intent isn't listed, route through `hyperframes-design` (look\u002Fconcept), `hyperframes-motion` (motion), `\u002Fhyperframes\u002Fcore` (contract). **The first row is ADDITIVE — read it AND your intent row, not one or the other.**\n\n| Building…                                                             | Read first (in order)                                                                                                                                                                                |\n| --------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| **ALWAYS — every non-trivial piece, on top of your intent row below** | `hyperframes-design\u002Freferences\u002Fhouse-style.md` + `references\u002Fvideo-composition.md` (also gated in Step 1 \u002F HARD-GATE; the \"produced, not generated\" foreground detailing)                          |\n| **Kinetic typography \u002F text-forward**                                 | `hyperframes-motion\u002Ftechniques.md` (kinetic type) + `adapters\u002Fgsap-easing-and-stagger.md` + `rules\u002Fkinetic-beat-slam.md`                                                                          |\n| **Title card \u002F lower-third \u002F overlay \u002F PiP \u002F text-behind-subject**    | `hyperframes-design\u002Freferences\u002Fcomposition-patterns.md` + (for the centered\u002Fsized frame) `\u002Fhyperframes\u002Fcore` → \"Root must be sized\"                                                                 |\n| **Logo \u002F brand-mark reveal**                                          | `hyperframes-motion\u002Frules\u002Fsvg-path-draw.md` (draw-on) + `rules\u002F3d-text-depth-layers.md` + `rules\u002Fscale-swap-transition.md`                                                                        |\n| **Data \u002F stats \u002F numbers**                                            | `hyperframes-motion\u002Frules\u002Fcounting-dynamic-scale.md` + `rules\u002Fstat-bars-and-fills.md` + `hyperframes-design\u002Freferences\u002Fdata-in-motion.md`                                                       |\n| **Product \u002F app \u002F UI demo**                                           | `hyperframes-motion\u002Frules\u002F3d-page-scroll.md` + `rules\u002Fcursor-click-ripple.md` + `rules\u002Fpress-release-spring.md`                                                                                   |\n| **Multi-scene \u002F transitions**                                         | `hyperframes-motion\u002Ftransitions\u002Foverview.md` **then** `transitions\u002Fcatalog.md` (you are not done after the overview — the GSAP recipe is in the catalog)                                          |\n| **Modular \u002F sub-compositions**                                        | `\u002Fhyperframes\u002Fcore\u002Freferences\u002Fcomposition-patterns.md` + `references\u002Fsub-compositions.md`                                                                                                             |\n\n## Output checklist → `\u002Fhyperframes\u002Fcli`\n\n- [ ] `npx hyperframes lint` and `npx hyperframes validate` pass (block on results)\n- [ ] design adherence verified if a spec (`frame.md` \u002F `design.md`) exists — checklist in `hyperframes-design\u002Freferences\u002Fdesign-adherence.md`\n- [ ] `npx hyperframes inspect` passes, or every overflow is intentionally marked\n- [ ] contrast warnings addressed; for multi-scene work, review the animation map (`hyperframes-motion\u002Fscripts\u002Fanimation-map.mjs`)\n- [ ] deliver the preview; render to MP4 only on explicit request\n- [ ] surface the preview **only at handoff** (it is the stable, final preview); don't pop one mid-build — build-phase snapshots are headless\n\n",{"name":5,"metadata":24,"description":26},{"tags":25},"orchestrator, general-video, fallback, freeform, composition-authoring","The fallback workflow for authoring custom HyperFrames video compositions at any length or format — longer or multi-scene pieces, brand \u002F sizzle reels, montages, title cards, static loops, and freeform compositions. Input- and length-agnostic. If a specialized workflow clearly fits the input — a marketed product, a website, a topic explainer, a GitHub PR, existing footage, a short motion graphic, or a Remotion port — prefer it (see \u002Fhyperframes); use this only as the general fallback when none fit.\n","main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","06-前端与设计\u002Fgeneral-video-rove",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill general-video",{"tool":41,"command":42},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill general-video",{"tool":44,"command":45},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill general-video","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fgeneral-video-rove\u002FSKILL.md",true,[],[50,57,62,69,76,83],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":58,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]