Spot it. Save it. Free, local-first Chrome extension for images, videos and prompts. Explore 2,000+ curated cases and connect your library to AI Agents via MCP. 提示词导演
JavaScript ai-artai-videochrome-extensionclaude-codecodexhiggsfieldjimenglocal-firstmcpmidjourneymoodboardprompt-engineeringprompt-libraryprompt-managerreference-libraryseedancevisual-bookmarksweb-clipper
import { defaultSkillExtractionInstruction } from './skill-extraction-instruction.js';
export { defaultSkillExtractionInstruction } from './skill-extraction-instruction.js';
import {
createComposerSession,
normalizeComposerSettings,
referenceSourcePartsForAsset
} from "./composer.js";
import { executeComposerTurnWithService } from "./composer-service.js";
import { entryMediaAssets } from "./media.js";
export function defaultSkillVisualInstruction(localeValue = "zh-CN") {
return localeValue === "en"
? "Describe reusable visual choices that serve the goal. Distinguish transferable patterns from source-specific details, do not judge completeness, and ignore contact-sheet borders and labels."
: "描述服务于目标的可复用视觉选择,区分可迁移规律与案例专属内容,不评价完整性;忽略联系表边框和编号本身。";
}
export function buildSkillExtractionRequest(input = {}) {
const locale = input.locale === "en" ? "en" : "zh-CN";
const goal = clean(input.goal);
if (!goal) throw new Error(locale === "en" ? "Describe what you want to extract" : "请先说明希望提炼什么");
const sources = (Array.isArray(input.sources) ? input.sources : []).flatMap((source, index) => {
const prompt = multiline(source?.prompt);
const analysis = multiline(source?.analysis);
const parts = normalizeAnonymousSourceParts(source?.parts);
return prompt || analysis || parts.length ? [{ number: index + 1, prompt, analysis, parts }] : [];
});
if (!sources.length) throw new Error(locale === "en" ? "The selected cases have no usable text" : "所选案例没有可用于提炼的文字资料");
const vision = (Array.isArray(input.visualAnalyses) ? input.visualAnalyses : []).map(multiline).filter(Boolean);
const sourceText = sources.map((source) => [
locale === "en" ? `Source ${source.number}` : `匿名来源 ${source.number}`,
...(source.parts.length
? exactAnonymousSourceGroups(source.parts).map((group) => `[${group.labels.map((kind) => skillSourceLabel(kind, locale)).join(" + ")}]\n${group.text}`)
: [
source.prompt ? `${locale === "en" ? "Original prompt" : "原提示词"}:\n${source.prompt}` : "",
source.analysis ? `${locale === "en" ? "Existing visual analysis" : "已有画面分析"}:\n${source.analysis}` : ""
])
].filter(Boolean).join("\n")).join("\n\n");
const visualText = vision.length ? `\n\n${locale === "en" ? "Confirmed visual contact-sheet analyses" : "已确认的视觉联系表分析"}:\n${vision.map((item, index) => `${index + 1}. ${item}`).join("\n")}` : "";
const extractionInstruction = multiline(input.instructionOverride) || defaultSkillExtractionInstruction(locale);
if (locale === "en") return [
"Create the executable Markdown body of a portable creative Skill.",
`Extraction goal: ${goal}`,
extractionInstruction,
"Do not include YAML frontmatter, provenance, local identifiers, project names, URLs, or claims about unseen images.",
sourceText + visualText
].join("\n\n");
return [
"请生成一份可移植创作 Skill 的可执行 Markdown 正文。",
`本次提炼目标:${goal}`,
extractionInstruction,
"不要输出 YAML frontmatter、来源证据、本地编号、项目名、网址,也不要声称看过未提供的图片。",
sourceText + visualText
].join("\n\n");
}
// Existing extraction batch target only: every fragment is processed and then
// synthesized. This is never an input quota or a reason to discard source text.
export const SKILL_EXTRACTION_BATCH_TARGET_CHARACTERS = 337_500;
export function skillExtractionWorkload(input = {}) {
const sources = normalizeSkillSources(input.sources);
const batches = partitionSkillSources(sources, input.maxBatchCharacters);
const textCharacters = sources.reduce((sum, source) => sum + skillSourceCharacters(source), 0);
return {
sourceCount: sources.length,
textCharacters,
batches,
textBatchCount: batches.length,
synthesisRequestCount: batches.length > 1 ? 1 : 0,
requestCount: batches.length + (batches.length > 1 ? 1 : 0),
overSingleRequest: batches.length > 1,
tokenEstimate: estimateSkillTokens([
clean(input.goal),
multiline(input.instructionOverride) || defaultSkillExtractionInstruction(input.locale),
...sources.flatMap((source) => source.parts?.length ? source.parts.map((part) => part.text) : [source.prompt, source.analysis])
].join("\n"))
};
}
export function estimateSkillTokens(value = "") {
const text = String(value ?? "");
const cjk = (text.match(/[\p{Script=Han}\p{Script=Hiragana}\p{Script=Katakana}\p{Script=Hangul}]/gu) ?? []).length;
const other = text.replace(/[\p{Script=Han}\p{Script=Hiragana}\p{Script=Katakana}\p{Script=Hangul}\s]/gu, "").length;
return {
min: cjk + Math.ceil(other / 4),
max: cjk * 2 + Math.ceil(other / 2),
kind: "local-range"
};
}
export async function extractCreativeSkillDraftBatched(input = {}, settingsValue = {}, options = {}) {
const workload = skillExtractionWorkload(input);
if (!workload.batches.length) return extractCreativeSkillDraft(input, settingsValue, options);
const partials = [];
let usage = {};
let lastModel = "";
for (const [index, sources] of workload.batches.entries()) {
options.onProgress?.({ phase: "text-batch", current: index + 1, total: workload.batches.length });
const result = await extractCreativeSkillDraft({ ...input, sources }, settingsValue, options);
partials.push(result.markdown);
lastModel = result.model;
usage = addUsage(usage, result.usage);
}
if (partials.length === 1) return { ...skillDraftMetadata(partials[0], input.goal), markdown: partials[0], usage, model: lastModel };
options.onProgress?.({ phase: "synthesis", current: 1, total: 1 });
const synthesized = await extractCreativeSkillDraft({
...input,
sources: partials.map((markdown) => ({ prompt: markdown, analysis: "" })),
visualAnalyses: [],
goal: input.locale === "en"
? `${clean(input.goal)}. The following intermediate drafts cover the complete source set. Merge repeated rules, retain useful differences and boundaries, and produce one executable method.`
: `${clean(input.goal)}。以下内容是完整来源经分批提炼得到的中间草稿;合并重复规则、保留有用差异与边界,形成一份统一可执行方法。`
}, settingsValue, options);
return { ...synthesized, usage: addUsage(usage, synthesized.usage) };
}
export async function extractCreativeSkillDraft(input = {}, settingsValue = {}, options = {}) {
const request = buildSkillExtractionRequest(input);
const composerSettings = normalizeComposerSettings(settingsValue.composer);
const session = createComposerSession({
targetType: input.targetType === "video" ? "video" : "image",
outputLanguage: input.locale === "en" ? "en" : "zh-CN",
routeMode: "chat",
aiProfile: input.aiProfile ?? composerSettings.lastAiProfile,
productionReviewEnabled: false
});
const result = await executeComposerTurnWithService({
session,
userMessage: request,
route: "chat",
instruction: request,
composerSettings
}, { ai: settingsValue.ai, vision: settingsValue.vision }, [], options);
const markdown = stripFence(result.text);
if (!markdown) throw new Error("模型没有返回可编辑的 Skill 草稿");
return { ...skillDraftMetadata(markdown, input.goal), markdown, usage: result.usage, model: result.model };
}
export async function analyzeCreativeSkillVisualBatch(input = {}, settingsValue = {}, options = {}) {
const locale = input.locale === "en" ? "en" : "zh-CN";
const goal = clean(input.goal);
const dataUrl = String(input.dataUrl ?? "").trim();
if (!goal || !dataUrl.startsWith("data:image/")) throw new Error(locale === "en" ? "The visual batch is incomplete" : "视觉批次数据不完整");
const labels = (Array.isArray(input.items) ? input.items : []).map((item) =>
`C${Math.max(1, Number(item.caseNumber) || 1)}.${Math.max(1, Number(item.imageNumber) || 1)}`
).join(", ");
const instruction = multiline(input.instructionOverride) || defaultSkillVisualInstruction(locale);
const request = locale === "en"
? `Analyze only the visible creative content for this Skill extraction goal: ${goal}. Labels ${labels || "C1.1"} preserve case and image order. ${instruction}`
: `只围绕这个 Skill 提炼目标分析可见创作内容:${goal}。标记 ${labels || "C1.1"} 用于保留案例归属和图片顺序。${instruction}`;
const composerSettings = normalizeComposerSettings(settingsValue.composer);
const profile = input.aiProfile;
if (!profile || profile.serviceId === "deepseek") throw new Error(locale === "en" ? "Select a configured vision model" : "请先配置并选择视觉能力模型");
const visualId = `skill-contact-sheet:${crypto.randomUUID()}`;
const session = createComposerSession({
targetType: "image",
outputLanguage: locale,
routeMode: "chat",
aiProfile: profile,
productionReviewEnabled: false,
referenceSnapshots: [{
entryId: visualId,
alias: "@VISUAL",
referenceKind: "vision",
referenceText: request,
imageRefs: [{ visualId, mimeType: String(input.mimeType ?? "image/jpeg") }]
}]
});
const result = await executeComposerTurnWithService({
session,
userMessage: request,
route: "chat",
instruction: request,
composerSettings
}, { ai: settingsValue.ai, vision: settingsValue.vision }, [{ visualId, dataUrl }], options);
const description = multiline(result.text);
if (!description) throw new Error(locale === "en" ? "The vision model returned no usable analysis" : "视觉模型没有返回可用分析");
return { description, usage: result.usage, model: result.model };
}
export function anonymousSkillSources(entriesValue = [], selectionsValue = [], options = {}) {
const selections = normalizeSourceSelections(selectionsValue);
const documents = options.documentTextByAsset instanceof Map ? options.documentTextByAsset : new Map();
return (Array.isArray(entriesValue) ? entriesValue : []).flatMap((entry) => {
const selection = selections.get(String(entry?.id ?? ""));
if (!selection) return [];
const selectedAssets = entryMediaAssets(entry).filter((asset) => asset.usage !== "poster" && (selection.assetIds === null || selection.assetIds.has(String(asset.id))));
const mediaPrompts = new Map((Array.isArray(entry?.mediaPrompts) ? entry.mediaPrompts : [])
.map((item) => [String(item?.assetId ?? ""), multiline(item?.text)]));
const hasSelectedVideo = selectedAssets.some((asset) => asset.kind === "video");
const parts = [
selection.includeEntryText && multiline(entry?.text)
? { kind: "original_prompt", text: multiline(entry.text) } : null,
...selectedAssets.flatMap((asset) => {
if (asset.kind === "video") {
return referenceSourcePartsForAsset(entry, asset.id, {
sourceIds: selection.sourceIds,
analysisIds: selection.analysisIds
}).map(({ kind, text }) => ({ kind, text }));
}
const promptText = mediaPrompts.get(String(asset.id));
const documentText = asset.kind === "document" ? multiline(documents.get(String(asset.id))) : "";
const visualText = !asset?.visionAnalysis?.invalidated
? multiline(asset?.visionAnalysis?.reconstructionPrompt ?? asset?.visionAnalysis?.description) : "";
return [
promptText ? { kind: "original_prompt", text: promptText } : null,
documentText ? { kind: "document_text", text: documentText } : null,
visualText ? { kind: "image_analysis", text: visualText } : null
].filter(Boolean);
})
].filter(Boolean);
const normalizedParts = normalizeAnonymousSourceParts(parts);
const prompt = normalizedParts.filter((part) => ["original_prompt", "document_text"].includes(part.kind)).map((part) => part.text).join("\n\n");
const analysis = normalizedParts.filter((part) => !["original_prompt", "document_text"].includes(part.kind)).map((part) => part.text).join("\n");
return normalizedParts.length ? [{
prompt,
analysis,
...(hasSelectedVideo ? { parts: normalizedParts } : {})
}] : [];
});
}
function normalizeSourceSelections(values) {
const source = Array.isArray(values) ? values : [];
if (source.every((item) => typeof item === "string" || typeof item === "number")) {
return new Map(source.map((entryId) => [String(entryId), { includeEntryText: true, assetIds: null }]));
}
return new Map(source.flatMap((selection) => {
const entryId = clean(selection?.entryId);
if (!entryId) return [];
return [[entryId, {
includeEntryText: selection?.includeEntryText !== false,
assetIds: new Set((Array.isArray(selection?.assetIds) ? selection.assetIds : []).map(String)),
sourceIds: Array.isArray(selection?.sourceIds) ? selection.sourceIds.map(String) : null,
analysisIds: (Array.isArray(selection?.analysisIds) ? selection.analysisIds : []).map(String)
}]];
}));
}
function skillDraftMetadata(markdown, goalValue) {
const heading = String(markdown ?? "").match(/^#\s+(.+)$/mu)?.[1]?.trim() || "";
return {
callName: heading,
description: clean(goalValue)
};
}
export function creativeRunEvidenceCandidates(runsValue = [], skillIdValue = "") {
const skillId = clean(skillIdValue);
return (Array.isArray(runsValue) ? runsValue : []).flatMap((run) => {
const usedSkill = (Array.isArray(run?.appliedSkills) ? run.appliedSkills : [])
.some((skill) => clean(skill?.skillId) === skillId);
if (!skillId || !usedSkill) return [];
return (Array.isArray(run?.outputs) ? run.outputs : []).flatMap((output) => {
const keep = multiline(output?.judgment?.keep);
const improve = multiline(output?.judgment?.improve);
const visualId = clean(output?.visual?.id);
if (!visualId || (!keep && !improve)) return [];
return [{
id: `${clean(run.id)}:${visualId}`,
runId: clean(run.id),
visualId,
title: clean(run.title) || clean(run.promptText).slice(0, 80),
prompt: multiline(run.promptText),
keep,
improve,
capturedAt: clean(output.capturedAt || run.createdAt)
}];
});
});
}
export function selectedCreativeRunEvidenceSources(runsValue = [], evidenceIdsValue = [], skillIdValue = "") {
const selected = new Set((Array.isArray(evidenceIdsValue) ? evidenceIdsValue : []).map(clean));
return creativeRunEvidenceCandidates(runsValue, skillIdValue)
.filter((item) => selected.has(item.id))
.map((item) => ({
prompt: item.prompt,
analysis: [
item.keep ? `值得保留:${item.keep}` : "",
item.improve ? `需要改进:${item.improve}` : ""
].filter(Boolean).join("\n")
}));
}
function stripFence(value) {
return multiline(value).replace(/^```(?:markdown|md)?\s*/i, "").replace(/\s*```$/, "").trim();
}
function normalizeSkillSources(values) {
return (Array.isArray(values) ? values : []).flatMap((source) => {
const prompt = multiline(source?.prompt);
const analysis = multiline(source?.analysis);
const parts = normalizeAnonymousSourceParts(source?.parts);
return prompt || analysis || parts.length ? [{ prompt, analysis, parts }] : [];
});
}
function partitionSkillSources(values, maxCharactersValue) {
const requested = Number(maxCharactersValue);
const maxCharacters = Number.isSafeInteger(requested) && requested > 0 ? requested : SKILL_EXTRACTION_BATCH_TARGET_CHARACTERS;
const fragments = values.flatMap((source) => splitSkillSource(source, maxCharacters));
const batches = [];
let current = [];
let characters = 0;
for (const source of fragments) {
const size = skillSourceCharacters(source);
if (current.length && characters + size > maxCharacters) {
batches.push(current);
current = [];
characters = 0;
}
current.push(source);
characters += size;
}
if (current.length) batches.push(current);
return batches;
}
function splitSkillSource(source, maxCharacters) {
if (skillSourceCharacters(source) <= maxCharacters) return [source];
const chunks = [];
for (const part of source.parts ?? []) {
for (let offset = 0; offset < part.text.length; offset += maxCharacters) {
chunks.push({ prompt: "", analysis: "", parts: [{ ...part, text: part.text.slice(offset, offset + maxCharacters) }] });
}
}
if (source.parts?.length) return chunks;
for (let offset = 0; offset < source.prompt.length; offset += maxCharacters) {
chunks.push({ prompt: source.prompt.slice(offset, offset + maxCharacters), analysis: "", parts: [] });
}
for (let offset = 0; offset < source.analysis.length; offset += maxCharacters) {
chunks.push({ prompt: "", analysis: source.analysis.slice(offset, offset + maxCharacters), parts: [] });
}
return chunks;
}
function skillSourceCharacters(source) {
return (source.parts ?? []).reduce((sum, part) => sum + part.text.length, 0)
|| source.prompt.length + source.analysis.length;
}
function normalizeAnonymousSourceParts(values) {
const allowed = new Set(["original_prompt", "video_reconstruction", "time_notes", "other_analysis", "image_analysis", "document_text"]);
return (Array.isArray(values) ? values : []).flatMap((part) => {
const kind = String(part?.kind ?? "").trim();
const text = multiline(part?.text);
return allowed.has(kind) && text ? [{ kind, text }] : [];
});
}
function exactAnonymousSourceGroups(parts) {
const groups = [];
const byText = new Map();
for (const part of parts) {
const key = multiline(part.text);
let group = byText.get(key);
if (!group) {
group = { text: part.text, labels: [] };
byText.set(key, group);
groups.push(group);
}
if (!group.labels.includes(part.kind)) group.labels.push(part.kind);
}
return groups;
}
function skillSourceLabel(kind, locale) {
const labels = locale === "en" ? {
original_prompt: "Original prompt",
video_reconstruction: "AI visual reconstruction",
time_notes: "Human time notes",
other_analysis: "Other analysis",
image_analysis: "Image analysis",
document_text: "Selected document"
} : {
original_prompt: "原始提示词",
video_reconstruction: "AI 视觉逆推",
time_notes: "人工时间点笔记",
other_analysis: "其他分析",
image_analysis: "图片分析",
document_text: "所选文档"
};
return labels[kind] || (locale === "en" ? "Source" : "来源");
}
function addUsage(left = {}, right = {}) {
const keys = new Set([...Object.keys(left || {}), ...Object.keys(right || {})]);
return Object.fromEntries([...keys].map((key) => [key, (Number(left?.[key]) || 0) + (Number(right?.[key]) || 0)]));
}
function multiline(value) {
return String(value ?? "").replace(/\r\n?/g, "\n").trim();
}
function clean(value) {
return multiline(value).replace(/\s+/g, " ");
}