Jeden Skill in Manus ausführen
mit einem Klick

Jeden Skill in Manus mit einem Klick ausführen

atom-concepts-backfill

Sterne0

Forks1

Aktualisiert12. Juni 2026 um 18:09

Bridge an upstream gap: extract_atoms never stamps `frontmatter.concepts` on page-derived atoms, but synthesize_concepts consumes ONLY that field — so concept synthesis is permanently skipped ("no atoms with concept refs"). This script batch-labels atoms lacking the field with 1-3 kebab-case shared-vocabulary topic labels (sonnet) and stamps them, so upstream synthesize_concepts can tier + materialize concepts/<label> pages. Idempotent: only touches atoms WITHOUT `concepts`; safe to rerun after each extract_atoms drain. Retires when the upstream fix lands.

Installation

Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.

In Manus ausführen

Quelle

ChenyqThu

ChenyqThu/jarvis-knowledge-os-v2

GitHub-Repository öffnen Creator-Repositorys ansehen

Download

In Manus ausführen

Verwandte BerufeSOC

Basierend auf der SOC-Berufsklassifikation

SoftwareentwicklerInformatik- und Mathematikberufe·SOC 15-1252

Datei-Explorer

2 Dateien

SKILL.md

readonly

name	atom-concepts-backfill
version	1.0.0
description	Bridge an upstream gap: extract_atoms never stamps `frontmatter.concepts` on page-derived atoms, but synthesize_concepts consumes ONLY that field — so concept synthesis is permanently skipped ("no atoms with concept refs"). This script batch-labels atoms lacking the field with 1-3 kebab-case shared-vocabulary topic labels (sonnet) and stamps them, so upstream synthesize_concepts can tier + materialize concepts/<label> pages. Idempotent: only touches atoms WITHOUT `concepts`; safe to rerun after each extract_atoms drain. Retires when the upstream fix lands.
triggers	["atom concepts backfill","backfill atom concepts","concepts backfill"]
mutating	true

atom-concepts-backfill — bridge for the extract_atoms → synthesize_concepts gap

上游断点（2026-06-11 定位，gbrain v0.42.37.0/v0.42.38.0）

src/core/cycle/synthesize-concepts.ts 头注释（设计意图）："when the Haiku 3-check from extract_atoms decides 'this atom is about concept X', it stamps the field" — :92 只消费 frontmatter.concepts。
src/core/cycle/extract-atoms.ts 的 page 提取路径从不写该字段（只写 type/atom_type/lesson/source_hash/source_quote/virality_score/ emotional_register）。
结果：所有 page-derived atoms 永远进不了 concept 合成（生产实证：696 atoms / 0 含 concepts / synthesize_concepts 连续 skip）。
上游 issue 已起草（见 TODO）；本脚本为 fork 侧桥接，上游修复后自动退场（届时新 atoms 自带 concepts，本脚本查询恒为空集）。

用法

# 必须从 repo root 跑（bun 自动加载 .env.local 的 crs 代理 key/base）。
# Claude Code shell 注入的 ANTHROPIC_BASE_URL 会覆盖 .env.local 并破坏
# key/base 配对 —— 先 unset（见 memory: pitfall-anthropic-base-url）。
unset ANTHROPIC_BASE_URL

bun run skills/kos-jarvis/atom-concepts-backfill/run.ts              # dry-run（只打标签分布，不写库）
bun run skills/kos-jarvis/atom-concepts-backfill/run.ts --limit 60 --apply   # 试点
bun run skills/kos-jarvis/atom-concepts-backfill/run.ts --apply     # 全量

默认 dry-run；--apply 才写库（jsonb merge concepts + concepts_by 审计标记，不动 body/chunks/embedding，无 re-embed 开销）。
--limit N / --batch N（默认 40/批）；KOS_CONCEPTS_MAX_SPEND 花费上限（默认 $5）；KOS_CONCEPTS_MODEL 模型覆盖（默认 claude-sonnet-4-6，按 Lucien 2026-06-09 路由：上游设计的 Haiku 档 → sonnet）。
词表跨批次累积并从已 stamp 的 atoms 预热，保证标签聚类（ synthesize_concepts 需要 ≥2 atoms 同标签才物化 T3 concept 页）。

验证回路

--limit 60 --apply 试点 → 看输出的 "cluster(s) with >=2 atoms"。
unset ANTHROPIC_BASE_URL && ~/.bun/bin/gbrain dream --phase synthesize_concepts --dir ~/brain → 确认 concepts/<label> 页出现（SELECT slug FROM pages WHERE frontmatter->>'synthesized_by' LIKE 'synthesize_concepts%'）。
全量 --apply；每次 extract_atoms drain 推进后重跑一次补新增。

Mehr aus diesem Repository

gleiches Repository

orphan-reducer

ChenyqThu/jarvis-knowledge-os-v2

Classify vector-similar pages against each orphan page via Haiku 4.5 and add typed inbound references (link_type="related", relation encoded in context). Goal: chip away at the 1803/1952 orphan pile (v1 wiki flat import) across multiple sweep runs. Default is --dry-run; --apply does DB link inserts + markdown sentinel upsert on candidate pages that exist on disk, then commits ~/brain changes.

2026-07-140

entity-dedup

ChenyqThu/jarvis-knowledge-os-v2

Merge WITHIN-SOURCE duplicate entity-variant pages (e.g. people/lucien + people/lucien-chen, companies/tp-link-system-inc + tp-link-systems-inc) into one canonical node: repoint links + facts + display-name aliases, register a slug redirect, soft-delete the alias pages. An LLM disambiguates each cluster (merge / ambiguous / distinct); ambiguous first-name-vs-multiple-full-names cases are quarantined, never merged. Default --dry (simulate + report, zero writes). Cross-source pages are NEVER touched — the two-axis design keeps them legitimately separate.

2026-07-130

enrich-sweep

ChenyqThu/jarvis-knowledge-os-v2

One-shot sweep that reads every page in the brain, extracts every person/company/concept/project mentioned via Haiku NER, dedupes, tiers by mention count + context, and creates stub pages for entities that lack one. Tier 2 candidates get Tavily web-search augmentation; Tier 3 stays brain-only (confidence: low). This is the primary G1 payoff skill from JARVIS-NEXT-STEPS.md §5.

2026-06-260

kos-patrol

ChenyqThu/jarvis-knowledge-os-v2

Daily sweep: runs kos-lint + staleness detection + knowledge-gap analysis, then produces a MEMORY-format digest ready to be appended to OpenClaw's MEMORY.md by the digest-to-memory skill (Sun 22:00 weekly). Also writes a dashboard to ~/brain/agent/dashboards/knowledge-health-<date>.md.

2026-06-150

corpus-ingest

ChenyqThu/jarvis-knowledge-os-v2

One-command bulk-ingest pipeline (D→I→K→W) for a single isolated source. Sequences the 7 fork stages — register → ingest → embed → enrich → graph → (per-entity synth, opt-in) → corpus-synth — over a folder of frontmatter'd .md files, each idempotent/incremental so re-runs only do new work. Turns a systematic corpus (product docs, FAQ, a research library) into a queryable knowledge asset: facts (RAG) + entities + graph + corpus-level viewpoints.

2026-06-020

corpus-synth

ChenyqThu/jarvis-knowledge-os-v2

Corpus-level Wisdom synthesis. Where synthesis-sweep deepens ONE entity, corpus-synth synthesizes a whole imported knowledge base into queryable "观点与洞察" pages — the corpus's major themes, cross-document tensions, transferable patterns, and open questions. Top-down: Opus reads a corpus map, proposes the themes, then deeply synthesizes each. Turns a freshly imported systematic KB into knowledge AND wisdom (not just RAG facts).

2026-06-020

name	atom-concepts-backfill
version	1.0.0
description	Bridge an upstream gap: extract_atoms never stamps `frontmatter.concepts` on page-derived atoms, but synthesize_concepts consumes ONLY that field — so concept synthesis is permanently skipped ("no atoms with concept refs"). This script batch-labels atoms lacking the field with 1-3 kebab-case shared-vocabulary topic labels (sonnet) and stamps them, so upstream synthesize_concepts can tier + materialize concepts/<label> pages. Idempotent: only touches atoms WITHOUT `concepts`; safe to rerun after each extract_atoms drain. Retires when the upstream fix lands.
triggers	["atom concepts backfill","backfill atom concepts","concepts backfill"]
mutating	true

atom-concepts-backfill — bridge for the extract_atoms → synthesize_concepts gap

上游断点（2026-06-11 定位，gbrain v0.42.37.0/v0.42.38.0）

src/core/cycle/synthesize-concepts.ts 头注释（设计意图）："when the Haiku 3-check from extract_atoms decides 'this atom is about concept X', it stamps the field" — :92 只消费 frontmatter.concepts。
src/core/cycle/extract-atoms.ts 的 page 提取路径从不写该字段（只写 type/atom_type/lesson/source_hash/source_quote/virality_score/ emotional_register）。
结果：所有 page-derived atoms 永远进不了 concept 合成（生产实证：696 atoms / 0 含 concepts / synthesize_concepts 连续 skip）。
上游 issue 已起草（见 TODO）；本脚本为 fork 侧桥接，上游修复后自动退场（届时新 atoms 自带 concepts，本脚本查询恒为空集）。

用法

# 必须从 repo root 跑（bun 自动加载 .env.local 的 crs 代理 key/base）。
# Claude Code shell 注入的 ANTHROPIC_BASE_URL 会覆盖 .env.local 并破坏
# key/base 配对 —— 先 unset（见 memory: pitfall-anthropic-base-url）。
unset ANTHROPIC_BASE_URL

bun run skills/kos-jarvis/atom-concepts-backfill/run.ts              # dry-run（只打标签分布，不写库）
bun run skills/kos-jarvis/atom-concepts-backfill/run.ts --limit 60 --apply   # 试点
bun run skills/kos-jarvis/atom-concepts-backfill/run.ts --apply     # 全量

默认 dry-run；--apply 才写库（jsonb merge concepts + concepts_by 审计标记，不动 body/chunks/embedding，无 re-embed 开销）。
--limit N / --batch N（默认 40/批）；KOS_CONCEPTS_MAX_SPEND 花费上限（默认 $5）；KOS_CONCEPTS_MODEL 模型覆盖（默认 claude-sonnet-4-6，按 Lucien 2026-06-09 路由：上游设计的 Haiku 档 → sonnet）。
词表跨批次累积并从已 stamp 的 atoms 预热，保证标签聚类（ synthesize_concepts 需要 ≥2 atoms 同标签才物化 T3 concept 页）。

验证回路

--limit 60 --apply 试点 → 看输出的 "cluster(s) with >=2 atoms"。
unset ANTHROPIC_BASE_URL && ~/.bun/bin/gbrain dream --phase synthesize_concepts --dir ~/brain → 确认 concepts/<label> 页出现（SELECT slug FROM pages WHERE frontmatter->>'synthesized_by' LIKE 'synthesize_concepts%'）。
全量 --apply；每次 extract_atoms drain 推进后重跑一次补新增。