feat(skills,studio,media-use): the intent layer, review loop, and user memory — BRIEF.md, companion mode, recipes; /website-to-video folds into /product-launch-video (#2133)

* feat(studio,cli): per-frame board comments, self-refreshing storyboard, status-aware preview landing

Per-frame comment boxes on the storyboard board batch into
.hyperframes/frame-comments.json (a resubmit wins per frame; unconsumed
comments on other frames are kept). Submitted-but-unconsumed comments
stay visible — a toolbar banner plus a per-tile echo — until the agent
consumes the file; the banner also says what to do next (reply anything
in the agent chat).

The board keeps itself current: GET /projects/:id/signature exposes the
watcher-cached project signature, the storyboard payload carries the
signature it was derived from, and the view polls at 2s (hidden tabs
skipped, re-checked on visibility), refetching in place with no loading
flash. Posters bake the signature into their URL so tiles fill in as
sketches land and a poster that failed mid-write retries on the next
version; the empty state upgrades itself when STORYBOARD.md appears,
and its handoff prompt now points the agent at the review loop and uses
the parser's real status vocabulary (outline, not planned).

preview lands the browser on the storyboard view while the board is the
review surface — any frame built, or pure planning (srcs declared, none
on disk yet) — and on the timeline once the video is assembled.

* feat(skills): the review loop — plan, sketch, build as one shared process

hyperframes-core/references/review-loop.md is the single source for the
three-pass collaborative review: the plan proposed on a live board
(§ 1), wireframe sketches marked built with one layout question (§ 2 —
real words on plain blocks, run no CLI; a confirmed board is itself a
valid deliverable when the user asked for a storyboard, not a video),
the build dressing confirmed layouts (§ 3, worker or inline), and the
final look (§ 4). Autonomous runs skip every gate and keep one question
before render.

The three narrative workflows' Steps 3/4/6 collapse to references plus
their sketch stand-ins (captured-asset blocks for product-launch-video,
plain code panels for pr-to-video); the confirmed-sketch handoff stays
in each frame-worker prompt. general-video plans on a board for
multi-scene narrative pieces in collaborative mode — its sketch pass is
layout-before-animation with the user watching. The router treats
"I want a storyboard" as a process request rather than a route, and
closes exploratory intake by recommending a route plus how the run will
review.

The supporting contracts land next door: the comments channel (silent
submit, one reply picks it up, check the file before the words) in
brief-contract § 1; the sidecar schema and the built status rung in
storyboard-format; the mode question asked first and alone in the three
workflows' Step 0.

* feat(media-use): user memory — remembered preferences and frozen recipes

Two tiers of memory on media-use's existing two-tier storage split.

Preferences (lightweight): confirmed brief answers — destination, aspect,
language, mode, voice, style preset — recorded to the project's
.media/preferences.json (committed, the team inherits it) and promoted
to the personal ~/.media/preferences.json once the same value is
confirmed in two different projects (a sightings ledger accumulates the
cross-project evidence user-side, since project files can't see each
other). prefs.mjs get/record; merge reads project-over-user; a changed
value restarts its provenance.

Recipes (heavyweight): one approved run frozen as a named, versioned
bundle — frame.md, the storyboard skeleton (structure kept: durations,
transitions, srcs, Video direction; statuses reset to outline; content
blanked to per-frame fill-ins naming the beat's role), and the confirmed
brief values. Named folders, not content hashes: re-freezing bumps
version and archives <name>@v<N>; a freeze is already confirmed, so it
promotes to the user tier immediately. recipe.mjs freeze/list/use, plus
resolve --type recipe --entity <name> delegating like grade/lut.

16 new node --test cases; the media-use lib suite is 168/168.

* feat(skills): wire user memory into the brief and the review loop

brief-contract § 2 gains Remembered defaults: read the merged
preferences before Round 2 and let a remembered value become the
recommended option with a receipt naming its source project. Memory
changes the default, never the question — every ask-marked field still
gets asked, and what the request says this time beats what was picked
last time. Record only what the user actually confirmed (a defaulted
voice nobody chose is not an answer; a "go" that accepts the
recommended defaults is). The first record announces itself once;
after that the receipts carry the reminder. In autonomous mode a
remembered value becomes the decided value, receipt included.

The three narrative workflows read the remembered defaults before
Round 2, record the confirmed answers at the Step 0 gate, record the
chosen preset at the Step 2 gate (pr-to-video excepted — its preset is
fixed), and fall back to the remembered voice when the request names
none. general-video's discovery reads the same defaults.

Recipes wire in at both ends: Step 0 checks for a matching recipe
before the mode question — one question, plural-aware, and adopting
one fills the brief, skips the design step, and drafts the storyboard
from the frozen skeleton while every review gate still runs. The
review loop's final look (§ 4) offers the freeze once after approval,
and the confirmation teaches the recall phrase — the name is something
the system reminds the user of, never something they must remember.
The router recognizes a named recipe or "like last time" as a route.

* docs(skills): the sketch pass names check, not the deprecated validate

* feat(skills): intent-layer references — process, route briefs, capability menu, BRIEF.md format

* feat(media-use): brief skeleton as the recipe's fourth artifact; flow/storyboard preference keys

* feat(skills): the intent layer conducts every brief — workflows execute BRIEF.md

* feat(skills): retire the mode preference key; sync catalog surfaces for intent layer

* refactor(skills): dedupe router vs intent-layer guidance — one owner per rule

* feat(skills): the design ask — own spec, pick by eye from showcases, or defer

* docs(skills): the design ask says the honest line on capture routes

* feat(skills): product-launch-video absorbs website-to-video as the tour angle

* refactor(skills): keep product-launch-video pristine — a tour is brief intent, not a pipeline branch

* feat(skills): production loop + genre lenses; general-video goes freeform (route yours, laws hold)

* refactor(skills): /hyperframes is the front door - route tables and scope lists leave the workflows

* docs(skills): review-loop pass across skill catalog

* fix(cli): pass project dir to openStudioBrowser in background-server path

* feat(skills): add pitch-round reference - verbalized sampling concept gate

* feat(skills): wire pitch round into intent layer - completeness triage + route eligibility

* feat(skills): editorial capability recommendations, handoff disciplines, menu-probe split

* feat(skills): pitches carry their machinery; source-only-formed requests pitch the telling

* feat(skills): companion goes director - ceiling treatment plus blueprint/rule citation discipline

* fix(scripts): sandbox npx-leak guard - private npm global prefix keeps npx on the branch CLI

* chore(skills): resync manifest hash after formatter pass reflowed general-video tables

* fix(skills): recipe freeze reads workflow from BRIEF.md; style_preset records require workflow scope

Two holes found by a live companion-run freeze: the agent-supplied --workflow
contradicted the run's actual workflow (recipe.json said faceless-explainer,
brief-skeleton said general-video), and the style_preset lookup missed because
the preference had been recorded under the bare key.

- freezeRecipe resolves the workflow from BRIEF.md frontmatter; the flag is a
  fallback for briefless projects and a contradicting flag is ignored (noted).
- recordPreference refuses a bare style_preset — the scoped key is the only
  writable shape; freeze tolerates legacy bare records via read fallback.
- review-loop § 4 / media-use SKILL / brief-format wording follow the machinery.
This commit is contained in:
WaterrrForever
2026-07-15 21:19:14 +08:00
committed by GitHub
parent ca69b6b080
commit b9be0b2625
143 changed files with 3831 additions and 5188 deletions
+34 -34
View File
@@ -9,10 +9,6 @@ description: >
real image's geometry into a chart. Usually under 10s (up to ~30s), no
narration or live-action subject; renders to MP4 or transparent overlay.
Longer / narrated / multi-scene → /general-video. Unclear → /hyperframes.
metadata:
{
"tags": "orchestrator, motion-graphics, kinetic-type, data-viz, logo-reveal, lower-thirds, news, tweet, webpage, asset-fusion, short-form, overlay, no-narration",
}
---
> **First, keep this skill fresh — run silently, don't ask:** `npx hyperframes skills update motion-graphics`. A fast no-op when everything is current; otherwise it refreshes this skill plus the core domain skills it depends on before you rely on them.
@@ -21,9 +17,9 @@ metadata:
# motion-graphics — dispatch entry
> **Confirm the route before Step 0.** This skill makes a **short, design-led, unnarrated motion graphic** (motion is the message; ~under 10s, no voice-over). A **longer, multi-scene, or narrated** treatment → `/general-video`; a **narrated video of a website** → `/website-to-video`; a **topic explainer** → `/faceless-explainer`; a **product promo** → `/product-launch-video`; **captions on existing footage** → `/embedded-captions`. **Out of scope**: live / at-render-time data, or footage it can't capture. Unsure motion-first-vs-narrated? **Read `/hyperframes` first.**
> **The front door is `/hyperframes`.** This skill makes a **short, design-led, unnarrated motion graphic** (motion is the message; ~under 10s, no voice-over). Anything longer, narrated, or multi-scene — or any uncertainty → read `/hyperframes` first: the intent layer owns every route decision.
This workflow is **autonomous by design** — at most one clarifying question (`agents/director.md`), then straight through to render; the collaborative/autonomous distinction in `../hyperframes-core/references/brief-contract.md` adds no gates here.
This workflow is **autonomous by design** — at most one clarifying question (`agents/director.md`), then build through verification without intermediate review. The intent layer (`/hyperframes` § 4) routes here directly without run-shape questions; a storyboard and companion session add little to a piece this short. Rendering is still user-gated: after checks and proof snapshots pass, ask the canonical “preview first, or render?” question from `../hyperframes-core/references/brief-contract.md`. When a `BRIEF.md` exists, read it before the director's question.
A short design-led motion graphic. **Asset-first**: decide the asset strategy and source real material _before_ designing the shot, then design the shot around what you have, then compose by reusing catalog capabilities. All artifacts go to `PROJECT_DIR = videos/<project-name>/` (created in Step 0); all paths below are relative to it.
@@ -34,8 +30,9 @@ A short design-led motion graphic. **Asset-first**: decide the asset strategy an
| source ◇ | Bash — media-use resolve (**skip if `asset_needs` is empty**) | `assets/` + `assets/index.md` | `phases/source/guide.md` |
| design | subagent — shot design around resolved assets | `shot-plan.json` (final: block(s) + layout + motion + positions) | `agents/director.md` (Part 2) |
| build | subagent — reuse-first composition | `compositions/index.html` | `agents/builder.md` |
| render | Bash — `hyperframes render` (MP4, or `--format webm/mov` for overlay) | `renders/video.mp4` | Step 5 |
| verify | Bash — `lint` / `inspect` -> repair subagent on failure | (fixes in place) | `agents/finalize.md` |
| verify | Bash — `lint`, `check`, proof snapshots; repair on failure | `snapshots/contact-sheet.jpg` | Step 5 |
| approve | Ask preview or render; wait for the answer | explicit render approval | Step 6 |
| render | Bash — `hyperframes render` (MP4, or `--format webm/mov` for overlay) | `renders/video.mp4` or transparent overlay | Step 6 |
`◇ source` runs only when the chosen category declares assets. Pure code/text categories (e.g. `kinetic-type`, most `charts`/`stat`) have `asset_needs: []` and skip straight from plan to design.
@@ -124,40 +121,43 @@ Dispatch a subagent (prompt = `agents/director.md` Part 2 + dispatch context inc
Dispatch a subagent. prompt = full `agents/builder.md` + dispatch context (`shot-plan.json`, `catalog-map.md`, the category's `module.md`, `references/motion-vocabulary.md`, `references/builder-contract.md`). **Reuse-first**: `npx hyperframes add <block>` + customize in place; hand-author only gaps + the asset-fusion affordance. Output `compositions/index.html` honoring the HF contract (paused GSAP timeline on `window.__timelines`, `class="clip"` + stable ids, `tl.seek(0)`, deterministic).
### Step 5 — Render (Bash)
### Step 5 — Verify (Bash → repair subagent on failure)
```bash
(cd "$PROJECT_DIR" && npx hyperframes render . --skill=motion-graphics -q draft -o ./renders/video.mp4)
(cd "$PROJECT_DIR" && npx hyperframes lint .)
(cd "$PROJECT_DIR" && npx hyperframes check .)
(cd "$PROJECT_DIR" && npx hyperframes snapshot --at <proof-times>)
```
Choose proof times that show the opening state, signature move, and final hold. Inspect the generated contact or snapshot sheet before continuing. On `lint`, `check`, or snapshot failure, dispatch the repair subagent (`agents/finalize.md`) for one in-place fix pass, then rerun the failed gate. Never change a fixed duration merely to hide a defect.
### Step 6 — Approve and render (Bash)
Ask one question: “preview first, or render?” If the user chooses preview, open Studio and return to the same approval gate after revisions:
```bash
(cd "$PROJECT_DIR" && npx hyperframes preview)
```
Render only after an explicit render answer:
```bash
(cd "$PROJECT_DIR" && npx hyperframes render . --skill=motion-graphics -q high -o ./renders/video.mp4)
# transparent overlay variant: --format webm (or mov)
```
### Step 6 — Verify (Bash → repair subagent on failure)
```bash
(cd "$PROJECT_DIR" && npx hyperframes check .)
```
exit 0 → done. On lint/inspect errors, dispatch the repair subagent (`agents/finalize.md`: snapshot QA + one in-place fix pass + re-render). Never change a fixed duration in repair.
### Report + optional preview
Report the final output (`renders/video.mp4`, or the `.webm` / `.mov` overlay variant) + duration. **Don't open a preview during the run.** Offer one only on request, started **after** render so it serves the final file:
```bash
(cd "$PROJECT_DIR" && npx hyperframes preview) # Studio UI; or `npx hyperframes play` for a shareable link
```
Flags live in the `hyperframes-cli` skill (`references/preview-render.md`).
Verify the output exists, is non-empty, and has the intended duration. The final handoff names the artifact, actual duration, composition or frame id, proof times, and the inspected contact or snapshot sheet. Flags live in `/hyperframes-cli``references/preview-render.md`.
## Resume table
| State | Continue from |
| -------------------------------------------------------- | ------------------------ |
| no `shot-plan.json` | Step 1 (plan) |
| `shot-plan.json` has `asset_needs`, no `assets/` | Step 2 (source) |
| `shot-plan.json` final, no `compositions/index.html` | Step 3/4 (design+build) |
| `compositions/index.html` exists, no `renders/video.mp4` | Step 5 (render) + Step 6 |
| `renders/video.mp4` exists | Report + stop |
| State | Continue from |
| -------------------------------------------------------- | -------------------------- |
| no `shot-plan.json` | Step 1 (plan) |
| `shot-plan.json` has `asset_needs`, no `assets/` | Step 2 (source) |
| `shot-plan.json` final, no `compositions/index.html` | Step 3/4 (design+build) |
| `compositions/index.html` exists, proof snapshots absent | Step 5 (verify) |
| checks and proof snapshots pass, no approved render | Step 6 (approval) |
| approved render exists | verify output, then report |
## Design notes (maintainers — execution does not read this)