comic-intent-parser
Phase-1 Layer-0 of the comic-author suite — turn ANY raw idea / a locked video skeleton / an audience note into ONE schema-valid intent_spec node that fixes the logline (an editorial climax), the tagline, and the named DUAL-IDENTITY design constraint the whole comic optimizes against. Codex-as-parser (raw bytes + schema, never Claude's gloss) + reviewer-independence + banned-vocab lint + confidence-gated under_review routing + a HARD user-approval gate. It NEVER invents panels, assets, or storyboard detail, and NEVER silently defaults — every assumption becomes an uncertainties[] entry. Use it whenever a comic starts from a fuzzy brief and you need a locked, auditable premise before outlining.
wanshuiyin · 已有静态检查记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add wanshuiyin/ARIS-Movie-Director --skill comic-intent-parser技能说明
name: comic-intent-parser description: "Phase-1 Layer-0 of the comic-author suite — turn ANY raw idea / a locked video skeleton / an audience note into ONE schema-valid intent_spec node that fixes the logline (an editorial climax), the tagline, and the named DUAL-IDENTITY design constraint the whole comic optimizes against. Codex-as-parser (raw bytes + schema, never Claude's gloss) + reviewer-independence + banned-vocab lint + confidence-gated under_review routing + a HARD user-approval gate. It NEVER invents panels, assets, or storyboard detail, and NEVER silently defaults — every assumption becomes an uncertainties[] entry. Use it whenever a comic starts from a fuzzy brief and you need a locked, auditable premise before outlining."
comic-intent-parser — the locked premise (Phase 1 · Layer 0)
The single entry point of the left third of Figure 1. Before any beat, panel, asset, or blueprint exists,
this skill turns a raw user brief (one line, a script, a locked video storyboard, an image, or a mix) into
one intent_spec wiki node that answers exactly three questions — (1) what the user wants, (2) the hard
constraints, (3) what is still ambiguous — and locks the comic's logline + tagline + dual-identity design
constraint. It is the Layer-0 step the 49-line comic-author SOP previously had
only as a one-line stub; this gives it a real 7-phase procedure, a schema-validation loop, a confidence gate,
a cross-model parse, and a hard user-approval gate. It hands intent:<slug> down to
comic-outline-creator. It is authoring, not rendering: it must never
invent characters/scenes (that is the storyboard layer) or write panel prompts / content_svg /
expected_literals (that is the asset/blueprint layer) — doing so is a hard gate veto.
raw idea / locked skeleton / audience ─▶ ⓪ snapshot raw input verbatim + sha256 (provenance)
▼
① CODEX structured parse — raw bytes + verbatim node_schema, Claude inserts NO interpretation
▼
② SCHEMA validation loop — validate the FULL node vs node_schema.json (≤ MAX_PARSE_ATTEMPTS, codex-reply on the SAME thread)
▼
③ CONFIDENCE routing — confidence<0.6 OR any impact==high uncertainty → status:"under_review"
▼
④ BANNED-VOCAB lint (final guard) — recursive word-boundary scan; on hit re-parse ONCE (out-of-band)
▼
⑤ fan-out reviewers → persist review:* nodes + `reviews` edges → THEN comic-cross-layer-gate <id> --gate intent (CC scope-sanity ‖ Codex xhigh ambiguity)
▼
⑥ USER APPROVAL — HARD gate; present logline + tagline + dual_identity + every uncertainty → wait for explicit "lock it"
▼
approved? ─ no ─▶ revise / re-ask (NEVER proceed)
│ yes
▼
⑦ status:"locked" → commit node + edges + INTENT_REPORT.md + handoff JSON
Constants (ported from the aris_movie intent-parser; adapt, never downgrade)
- REVIEWER_MODEL =
gpt-5.5, REVIEWER_EFFORT =xhigh— quality is independent of theefforttier; never downgrade the reviewer (perreviewer-routing). Gemini (auto-gemini-3) is added ONLY when the input carries an image/visual that needs extraction. - CONFIDENCE_THRESHOLD =
0.6— a self-honest 0.0–1.0 self-rating below this auto-routes tounder_review. - MAX_PARSE_ATTEMPTS =
3— schema-fix retries on the same Codex thread; on persistent failure writeparse_failed.md, never silently coerce a value to satisfy the schema. - SCHEMA_PATH =
../../schemas/node_schema.json— theintent_specbranch is the contract; nothing reaches the wiki withoutjsonschemaDraft202012 passing the FULL node. - NODE_TYPE =
intent_spec; NODE_ID =intent:<slug>; WIKI =wiki/nodes/intent_<slug>.json(the:→_for the filename); OUTPUT_DIR =intent-stage/(work area, traces, checkpoints). - BANNED_VOCAB (ported nearly verbatim from the video skill — our
content_svgblueprints +ART_BIBLE.mdalso forbid photographic/camera vocab):camera, lens, dolly, pan, zoom-shot, bokeh, depth-of-field, 8K, 4K, cinematic, photorealistic, lighting rig, f/1.8, shutter, frame-rate, voxel(case-insensitive, word-boundary). The intent layer states the STORY and constraints, not photographic direction.
What this skill writes — the intent_spec node (the contract boundary)
Per ../../schemas/node_schema.json (node_type: "intent_spec",
node_id: "intent:<slug>"), the payload REQUIRES all ten fields — none may be silently omitted:
| payload field | what it holds (authoring layer only) |
|---|---|
raw_input_refs | the verbatim snapshot pointer(s) + sha256 per source material (provenance, never a paraphrase) |
user_goal | what the user wants, in their terms — NOT a casting call, NOT a beat list |
audience | who reads it (e.g. "non-ML reader" ⇒ legibility constraint downstream) |
format | comic-equivalent of the video format fields: page_count/tier, page-grid intent (cover/single/grid/grid2x2/feature/finale), bake_lang (primary language → defaults.bake_lang) |
constraints | hard limits (length tier, deadline framing, what must/must-not appear) |
subjects | the characters the user mentioned — names + the one-line identity hint each; a later layer turns subjects → cast → one locked .png`` (do NOT invent a cast here) |
source_skeleton | if the input is an existing video/script: `{skeleton_id, beat_count, shot_ |