بنقرة واحدة
media-index
Maintain a local JSON index of reusable source media, transcripts, tags, and probe metadata.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
القائمة
Maintain a local JSON index of reusable source media, transcripts, tags, and probe metadata.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Plan, build, and fix short-form videos like an editor, using hook-first structure, caption-aware visual design, Remotion/FFmpeg assembly, and reject-regenerate review loops instead of one-shot automation.
Build a full short from brief to reviewed MP4 while keeping script, audio, visuals, captions, and validation aligned as one edit.
Generate and evaluate multiple short-form hook, title, cover, opening-frame, and platform-packaging variants before scripting or rendering, then choose a default and preserve the rationale.
Turn publish receipts and performance metrics into reusable style-profile or niche-profile updates that say what to repeat, kill, or test next.
Generate platform-specific publish metadata, fit checks, and upload checklists for short-form and social video without auto-uploading.
Review scripts, timelines, scene plans, or rendered shorts for retention and mobile pacing before final render approval or publish readiness.
| name | media-index |
| description | Maintain a local JSON index of reusable source media, transcripts, tags, and probe metadata. |
| allowedTools | ["shell","read","write"] |
| model | inherit |
| argumentHint | {"indexPath":"output/content-machine/library/media-index.v1.json","items":[{"path":"input/source.mp4","analysisPath":"output/content-machine/highlights/source-media-analysis.v1.json","tags":["podcast"]}]} |
| entrypoint | node --import tsx scripts/harness/media-index.ts |
| inputs | [{"name":"indexPath","description":"Path that will receive media-index.v1.json.","required":false},{"name":"items","description":"Media items to add or replace by path.","required":true}] |
| outputs | [{"name":"media-index.v1.json","description":"Local reusable media index."}] |
Use this after source media analysis when local assets should be reused or searched later. The index is JSON, local-only, and keyed by resolved file path.
Index evidence after scout/review; do not use media-index to decide
rights. The strict harness schema stores provenance under each item's
metadata, not as arbitrary top-level fields.
When indexing external or generated media, store enough evidence for reuse and publish review:
sourceUrl, provider, author, titlelicenseName, licenseUrl, attributionTextretrievedAt, fileHash, localPathusageMode: inspiration-only, code-native-rebuild,
downloaded-asset, generated-asset, or reference-providerrightsFlags: watermark, editorial-only, model-release risk,
trademark risk, Content ID risk, attribution requiredevidenceFiles: license screenshot, API response, source metadata, or
downloaded license fileplatformSource,
originalVideoUrl, extractRange, licenseCertificatePath,
permissionEvidencePath, contentIdRisk, attributionPlacement, and
mixRolereviewStatus: approved, needs-review, reference-only, or
rejectedpublish-prep can review a media index directly through
mediaIndexPath. generate-short also writes
provenance/asset-ledger.json; use media-index provenance for reusable
library assets and the asset ledger for the specific render run.
For AI-generated media, also store provider, model, prompt, negative prompt, reference assets, job id, status URL, settings, seed if available, cost, and output hash.
cat skills/media-index/examples/request.json | \
node --import tsx scripts/harness/media-index.ts