Run any Skill in Manus with one click

pending-enrich

Stars0

Forks1

UpdatedMay 10, 2026 at 05:59

Queue schema for entity-mention signals that need later enrichment. Producer: OpenClaw Feishu signal-detector fork (external). Consumer: skills/kos-jarvis/enrich-sweep/run.ts. This file pins the on-disk format so both sides stay honest without shared code.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

ChenyqThu

ChenyqThu/jarvis-knowledge-os-v2

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

SKILL.md

readonly

name	pending-enrich
version	1.0.0
description	Queue schema for entity-mention signals that need later enrichment. Producer: OpenClaw Feishu signal-detector fork (external). Consumer: skills/kos-jarvis/enrich-sweep/run.ts. This file pins the on-disk format so both sides stay honest without shared code.
triggers	["pending enrich","enrich queue"]
tools	[]
mutating	false

pending-enrich queue

Bridge between Phase 2 (Feishu ambient signal capture) and Phase 3 (batch enrich-sweep). See docs/JARVIS-NEXT-STEPS.md §4-§5 for the phase context.

File

Path: ~/brain/agent/pending-enrich.jsonl (override via PENDING_ENRICH_PATH env var)

Format: JSONL. One self-contained JSON object per line, newline-terminated. Never pretty-printed. Never rewritten — only appended to by producers, only rotated (move + truncate) by the consumer after a successful sweep.

Line schema

{
  "ts": "2026-04-17T10:32:14Z",
  "name": "alice-example",
  "kind": "person",
  "context": "VC who invested in widget-co seed; mentioned by you on Feishu",
  "source": "feishu:oc_abc123#msg_456",
  "confidence": 0.7
}

Required fields

ts — ISO 8601 UTC timestamp of the mention
name — entity name as spoken / written; do not slugify here, dedup happens in enrich-sweep
kind — one of person | company | concept | project. If unknown, emit person and let enrich-sweep reclassify
context — 40-300 chars of surrounding text. This becomes the first line of the stub's State section if the entity gets promoted
source — opaque origin string. Convention:
- feishu:<chat_id>#<message_id> for Feishu bridge
- manual:<anything> for human-appended lines
- openclaw:<skill-name> for other OpenClaw skills

Optional fields

confidence — producer's self-reported 0-1 float. enrich-sweep ignores <0.5 unless mention recurs
aliases — array of alternate strings observed alongside name
url — canonical link if the mention came with one (tweet, article)

Producer responsibilities (OpenClaw side)

Append-only. Never read-modify-write. Open with O_APPEND semantics (appendFileSync in Node) to avoid races.
One message → zero-or-more lines. Multiple entities in a single Feishu message each emit their own line.
Skip trivia. Don't emit for: common first names alone ("John"), generic role titles ("the CEO"), personal pronouns.
Best-effort timestamp. If the message timestamp is unavailable, use new Date().toISOString().
Size discipline. If the file exceeds 10 MB, stop producing and alert — consumer is probably broken.

Consumer responsibilities (enrich-sweep side)

Rotate, don't truncate in place. At sweep start:
```
mv ~/brain/agent/pending-enrich.jsonl \
   ~/brain/agent/pending-enrich.processing.<ts>.jsonl
```
Process the rotated file. If the sweep crashes, the next run inherits the .processing.* file (and may find another fresh one).
Merge with in-brain scan. Queue entries are hints, not truth — enrich-sweep dedupes against (a) existing brain pages and (b) entities already extracted from the 86-page corpus via Haiku NER.
Archive after success. Move .processing.<ts>.jsonl to ~/brain/agent/pending-enrich-archive/ after a clean run.
Never edit a live queue file. Producers are racy by design.

Example lines

{"ts":"2026-04-17T09:12:03Z","name":"Naval Ravikant","kind":"person","context":"Lucien discussed Naval's 'Specific Knowledge' framework","source":"feishu:oc_hub#msg_7781","confidence":0.9}
{"ts":"2026-04-17T09:15:44Z","name":"Tavily","kind":"company","context":"chose Tavily over Brave for enrich-sweep Tier 2 web search","source":"feishu:oc_hub#msg_7784"}
{"ts":"2026-04-17T11:02:11Z","name":"context-engineering","kind":"concept","context":"new concept page created in ideas/ during morning sync","source":"manual:lucien-terminal"}

Non-goals

This queue is not a full event bus. It carries entity mention signals only. Original-thinking signals go straight through POST /ingest on kos-compat-api (see docs/FEISHU-SIGNAL-DETECTOR-SETUP.md).
This queue is not a task tracker. enrich-sweep decides what to enrich based on the whole brain, not just this queue.

Consumer: skills/kos-jarvis/enrich-sweep/SKILL.md
Producer setup: docs/FEISHU-SIGNAL-DETECTOR-SETUP.md
Upstream contract: skills/signal-detector/SKILL.md

More from this repository

same 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

atom-concepts-backfill

ChenyqThu/jarvis-knowledge-os-v2

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.

2026-06-120

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

name	pending-enrich
version	1.0.0
description	Queue schema for entity-mention signals that need later enrichment. Producer: OpenClaw Feishu signal-detector fork (external). Consumer: skills/kos-jarvis/enrich-sweep/run.ts. This file pins the on-disk format so both sides stay honest without shared code.
triggers	["pending enrich","enrich queue"]
tools	[]
mutating	false

pending-enrich queue

Bridge between Phase 2 (Feishu ambient signal capture) and Phase 3 (batch enrich-sweep). See docs/JARVIS-NEXT-STEPS.md §4-§5 for the phase context.

File

Path: ~/brain/agent/pending-enrich.jsonl (override via PENDING_ENRICH_PATH env var)

Line schema

{
  "ts": "2026-04-17T10:32:14Z",
  "name": "alice-example",
  "kind": "person",
  "context": "VC who invested in widget-co seed; mentioned by you on Feishu",
  "source": "feishu:oc_abc123#msg_456",
  "confidence": 0.7
}

Required fields

ts — ISO 8601 UTC timestamp of the mention
name — entity name as spoken / written; do not slugify here, dedup happens in enrich-sweep
kind — one of person | company | concept | project. If unknown, emit person and let enrich-sweep reclassify
context — 40-300 chars of surrounding text. This becomes the first line of the stub's State section if the entity gets promoted
source — opaque origin string. Convention:
- feishu:<chat_id>#<message_id> for Feishu bridge
- manual:<anything> for human-appended lines
- openclaw:<skill-name> for other OpenClaw skills

Optional fields

confidence — producer's self-reported 0-1 float. enrich-sweep ignores <0.5 unless mention recurs
aliases — array of alternate strings observed alongside name
url — canonical link if the mention came with one (tweet, article)

Producer responsibilities (OpenClaw side)

Append-only. Never read-modify-write. Open with O_APPEND semantics (appendFileSync in Node) to avoid races.
One message → zero-or-more lines. Multiple entities in a single Feishu message each emit their own line.
Skip trivia. Don't emit for: common first names alone ("John"), generic role titles ("the CEO"), personal pronouns.
Best-effort timestamp. If the message timestamp is unavailable, use new Date().toISOString().
Size discipline. If the file exceeds 10 MB, stop producing and alert — consumer is probably broken.

Consumer responsibilities (enrich-sweep side)

Rotate, don't truncate in place. At sweep start:
```
mv ~/brain/agent/pending-enrich.jsonl \
   ~/brain/agent/pending-enrich.processing.<ts>.jsonl
```
Process the rotated file. If the sweep crashes, the next run inherits the .processing.* file (and may find another fresh one).
Merge with in-brain scan. Queue entries are hints, not truth — enrich-sweep dedupes against (a) existing brain pages and (b) entities already extracted from the 86-page corpus via Haiku NER.
Archive after success. Move .processing.<ts>.jsonl to ~/brain/agent/pending-enrich-archive/ after a clean run.
Never edit a live queue file. Producers are racy by design.

Example lines

{"ts":"2026-04-17T09:12:03Z","name":"Naval Ravikant","kind":"person","context":"Lucien discussed Naval's 'Specific Knowledge' framework","source":"feishu:oc_hub#msg_7781","confidence":0.9}
{"ts":"2026-04-17T09:15:44Z","name":"Tavily","kind":"company","context":"chose Tavily over Brave for enrich-sweep Tier 2 web search","source":"feishu:oc_hub#msg_7784"}
{"ts":"2026-04-17T11:02:11Z","name":"context-engineering","kind":"concept","context":"new concept page created in ideas/ during morning sync","source":"manual:lucien-terminal"}

Non-goals

This queue is not a full event bus. It carries entity mention signals only. Original-thinking signals go straight through POST /ingest on kos-compat-api (see docs/FEISHU-SIGNAL-DETECTOR-SETUP.md).
This queue is not a task tracker. enrich-sweep decides what to enrich based on the whole brain, not just this queue.

Consumer: skills/kos-jarvis/enrich-sweep/SKILL.md
Producer setup: docs/FEISHU-SIGNAL-DETECTOR-SETUP.md
Upstream contract: skills/signal-detector/SKILL.md