菜单
Use this skill when adding, repairing, or validating Jiang Lens evidence marks, source refs, lens-point anchors, episode-to-lens links, hover payloads, and backlink surfaces across Markdown and episode read JSON.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | jiang-provenance-linker |
| description | Use this skill when adding, repairing, or validating Jiang Lens evidence marks, source refs, lens-point anchors, episode-to-lens links, hover payloads, and backlink surfaces across Markdown and episode read JSON. |
Use this when the main task is linkage: source spans, evidence hovers, lens points, backlinks, transcript jumps, or validation of those surfaces.
Use versioned refs:
video:<source-slug>@transcript:v1#seg-0001
article:<article-id>@text:v1#p-0001
interview:<interview-id>@transcript:v1#seg-0001
Do not invent refs. Verify target segments exist.
Use:
[visible phrase]{evidence="video:<source-slug>@transcript:v1#seg-0001"}
Rules:
Lens point syntax:
<!-- lens-point id="stable-id" concept="concept-family" evidence="video:<source-slug>@transcript:v1#seg-0001" -->
<span id="stable-id" class="lens-point-anchor"></span>
Compact reusable idea text...
Rules:
Episode marks can cite existing lens points:
{
"text": "The guide is part of the trap.",
"lens_points": ["lens-point:guide-trap-necessary-guide"],
"refs": [
"video:predictive-history-6m1z-v3wgok@transcript:v1#seg-0014"
]
}
Only link a phrase to a lens point when both are specific enough. The episode phrase needs source refs, and the lens point must already exist in generated link data.
Run:
node ops/scripts/compile-content.mjs
node ops/scripts/validate-content.mjs
Inspect generated link data when needed:
node -e "const i=require('./website/src/data/lens/link-index.json'); console.log((i.lens_points||[]).map(p=>p.id+' -> '+p.url).join('\n'))"
For website-visible changes, run:
cd website && npm run build
Use this skill when a Jiang Lens autonomous agent needs to discover, claim, perform, validate, and hand off repo work without overwriting other agents or confusing authored, raw, and generated artifacts.
Use this skill after every published Jiang Lens episode, or when reassessing an existing episode, to decide and record how that source mutates the corpus, existing lens pages, lens points, atlas structure, chronology, and canon candidates.
Use this skill as the integration map for Jiang Lens work after episode publication, selecting the narrower corpus impact, concept writing, atlas maintenance, provenance linking, judging, or canon promotion skill needed for the task.
Use this skill when importing synced Jiang Lens source artifacts, resolving YouTube metadata dates, creating canonical source transcripts, and preparing transcript packets for semantic agents.
Use this skill as the integration map for turning one already-transcribed Jiang Lens video from synced Drive artifacts into a website-visible episode or interview, delegating detailed work to the narrower ingest, transcript, read-writing, and publishing skills.
Use Jiang Lens Moltnet through the local moltnet CLI: read episode-floor on request, send explicit room messages, and respect each participant's configured wake policy.