원클릭으로 Manus에서 모든 스킬 실행

ingest-brain-dump

스타12

포크2

업데이트2026년 6월 10일 02:43

Full orchestrator for stream-of-consciousness input pasted or dictated into the Claude Code session. Pipeline: explore-second-brain (find related files) → semantic segmentation → verify-idea (dedupe check) → process-content (create Template A files) → validate_template.py → user approval → save. Use when user pastes unstructured text or dictates a voice note into chat and says "brain dump", "process this", "ingest this", "save this", "what should we do with this". One paragraph may contain 3 ideas; 5 paragraphs may be 1 idea — always semantic, never algorithmic chunking. NOT for phone inbox (use a phone-inbox ingest skill if configured). NOT for podcast snips (use a snip-processing skill if configured). NOT for bookmark exports (use a bookmarks-ingest skill if configured). For a LARGE existing source export (notes-app dump, chat history, voice-note archive), use /mine — it triages the source, then calibrates the agent's judgment on small batches before the bulk pass. Preserves the owner's exact language — no

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

Manus에서 실행

출처

Loringtonian

Loringtonian/second-brain-template

GitHub 저장소 열기 Creator 저장소 보기

다운로드

Manus에서 실행

Ingest Brain Dump

Step 0 — Silent Context Load

Before doing anything else, silently Read each file in required_context_files (listed in frontmatter) if it is not already in your context. Do NOT announce the reads. Do NOT ask permission. This ensures the skill has the orientation it needs without bloating sessions that don't invoke it.

Files:

Orientation_Docs/INTELLECTUAL_LANDSCAPE.md
Orientation_Docs/COGNITIVE_PROFILE.md
Orientation_Docs/KEYWORD_GUIDE.md
Orientation_Docs/CONTENT_TAXONOMY.md
Orientation_Docs/ORIENTATION.md

Orchestrates brain dump ingestion: explore → classify → verify → create → validate.

Quick Start

User provides unstructured content
Search Second Brain for related files
Separate into distinct ideas (semantic, not algorithmic)
For each idea: verify not duplicate → create file → validate template
Present approval proposal → execute approved actions

Workflow Checklist

Copy and track:

- [ ] Step 1: Load context (ORIENTATION.md, KEYWORD_GUIDE.md, CONTENT_TAXONOMY.md)
- [ ] Step 2: Invoke explore-second-brain - find related files
- [ ] Step 3: Classify content semantically - identify distinct ideas
- [ ] Step 4: For each NEW_IDEA:
      - [ ] Invoke verify-idea - check duplicates
      - [ ] If NOT_FOUND: create Template A
      - [ ] Run validate_template.py - confirm compliance
- [ ] Step 5: Present approval proposal (see references/output-templates.md)
- [ ] Step 6: Execute approved actions
- [ ] Step 7: Report summary

Critical Principles

SEMANTIC SEPARATION - Never algorithmic chunking. Identify ideas by conceptual boundaries.
PRESERVE EXACT LANGUAGE - The owner's keywords are sacred. No paraphrasing.
VERIFY BEFORE CREATE - Always check for duplicates first.
VALIDATE AFTER CREATE - Run template validation on every new file.

Content Classification

Identify type for each segment:

Type	Action
NEW_IDEA	Create Template A in [Category]/
TODO	Add to project TODO file
AUGMENT	Propose addition to existing file
PREDICTION	Create in Predictions/
READING_LIST	Add to AA_Lists/READING_LIST.md
QUESTION	Log only, don't create file

See references/routing-rules.md for full routing table.

Source Detection

Source	Template
Claude Code conversation	A (owner's words THIS conversation)
Voice dictation / voice notes	A (owner's words only)
External podcast / bookmark	B (external content, attribute)

Verification Step

After creating any file, validate:

python3 .claude/scripts/validate_template.py "[filepath]"

If invalid: fix issues immediately. Only proceed when all files pass.

Approval Proposal

See references/output-templates.md for format.

Present each idea with:

Proposed path
Keywords
Project connections
Y/N prompt

Wait for explicit approval before creating files.

Integration

Skill	When
`explore-second-brain`	Step 2 - find related files
`verify-idea`	Step 4 - check duplicates
`process-content`	Create Template A (if needed)
`extract-todo`	Route TODOs to project files

Tier 2 Dependencies

Load before processing:

ORIENTATION.md - Templates, golden rules
KEYWORD_GUIDE.md - Vocabulary reference
CONTENT_TAXONOMY.md - Categories, folder mappings

이 저장소의 다른 Skills

같은 저장소

mine

Loringtonian/second-brain-template

Seed a brain from a LARGE existing source by TRIAGING it, then calibrating the agent's judgment on small batches, then bulk-mining. Use when the owner says "mine my [source]", "mine this export", "calibrate the mining", "idea mining", "process my archive", or "seed my brain from this export" — pointing at a sizable export (notes-app dump, chat history, voice-note archive, bookmarks, podcast snips). Phase 0 TRIAGE: categorize the source into keep/skip bins, sample the skip-bins, get owner approval per bin, build the target list. Phase 1 CALIBRATE: small batches → present COMPACT numbered proposals (verbatim quote + the agent's call + one-line reason, no tables) → owner corrects → write every correction back into the rules (CONTENT_TAXONOMY / KEYWORD_GUIDE / INTELLECTUAL_LANDSCAPE) → draft the full Template only after the calls are approved → repeat until a batch is clean. Phase 2 SET LOOSE: process the remainder autonomously, spot-check, re-calibrate on drift. Implements "invest in structure and calibrate the

2026-06-2212

setup

Loringtonian/second-brain-template

Onboard a human into THEIR own second brain — the guided interview that turns this blank template into their personalized system. Use when the user says "set this up", "let's set it up", "set up my second brain", "personalize", "personalise", "make this mine", "onboard me", "help me fill this in", "walk me through PERSONALIZE", or starts a fresh session wanting to begin. Drives the whole __FILL_FROM_USER__ fill-in via an interview. Resumable — pick up where you left off. NOT for ingesting content (use /ingest-brain-dump) — this is first-run setup.

2026-06-2212

group-related-ideas

Loringtonian/second-brain-template

Handles connections between related ideas. Options include creating folders, adding shared keywords, merging content, or rejecting false positives. Used when ingest-brain-dump identifies related content.

2026-06-1012

harness-review

Loringtonian/second-brain-template

Weekly self-improvement of the HARNESS itself — not project QA. Reviews the last N days of this brain's Claude Code session traces for harness-level friction (where the owner corrected the agent, repeated permission prompts, skills that misfired or weren't used, rules/memories the agent ignored, weak sub-agent prompts), drafts a proposal of findings, and the owner reviews + applies it finding-by-finding (gated — nothing auto-applies). Uses the in-session Workflow tool to fan out over trace chunks; no external services, no API keys. Use when the owner says "/harness-review", "review the harness", "self-review", "what's the agent getting wrong", or accepts the optional offer at the end of /weekly-maintenance.

2026-06-1012

process-content

Loringtonian/second-brain-template

Low-level mechanic that turns raw text into Template A/B files. Segments semantically (never algorithmic chunking), classifies each segment, creates files, runs validate_template.py. Does NOT sync from external sources — text must already be in context. Called by the ingestion skills (e.g. /ingest-example) as their file-creation stage; can also be invoked directly when user pastes content and says "make files from this", "turn this into Template A", "parse this into ideas". NOT for voice/phone inbox work (use an inbox-ingest skill), NOT for searching the brain (use explore-second-brain or semantic-search). If input has multiple distinct ideas, all are processed in one invocation.

2026-06-1012

semantic-search

Loringtonian/second-brain-template

Fast semantic search over Second Brain using local embeddings (BAAI/bge-large-en-v1.5, via `sb_embed.py`). Finds ideas by MEANING, not just keyword overlap. **Commands:** `search "query"` (top-k ranked matches, ~50ms cached), `verify "idea"` (duplicate check with DUPLICATE/OVERLAP/NOT_FOUND verdict), `similar path/to/file.md` (find files semantically close to an existing one), `stats` (index health). **Filters:** `--project "Project Name"`, `--category "Journal"`, `--top-k N`, `--json`. **Use semantic search for:** broad concept recall ("what do I have about coordination?"), rephrased-duplicate detection, unexpected-connection discovery, pre-ingestion dedupe. **Use grep instead when:** you know the exact term/phrase, doing project/category lookups by exact string, or confirming a specific filename. Grep is precise; semantic is recall-wide. Best practice: combine — semantic for broad recall, grep for precision matching. Invoked via "find ideas about X", "what do I have on X", "related to X", "similar to this i

2026-06-1012

name	ingest-brain-dump
description	Full orchestrator for stream-of-consciousness input pasted or dictated into the Claude Code session. Pipeline: explore-second-brain (find related files) → semantic segmentation → verify-idea (dedupe check) → process-content (create Template A files) → validate_template.py → user approval → save. Use when user pastes unstructured text or dictates a voice note into chat and says "brain dump", "process this", "ingest this", "save this", "what should we do with this". One paragraph may contain 3 ideas; 5 paragraphs may be 1 idea — always semantic, never algorithmic chunking. NOT for phone inbox (use a phone-inbox ingest skill if configured). NOT for podcast snips (use a snip-processing skill if configured). NOT for bookmark exports (use a bookmarks-ingest skill if configured). For a LARGE existing source export (notes-app dump, chat history, voice-note archive), use /mine — it triages the source, then calibrates the agent's judgment on small batches before the bulk pass. Preserves the owner's exact language — no paraphrasing.
required_context_files	["Orientation_Docs/INTELLECTUAL_LANDSCAPE.md","Orientation_Docs/COGNITIVE_PROFILE.md","Orientation_Docs/KEYWORD_GUIDE.md","Orientation_Docs/CONTENT_TAXONOMY.md","Orientation_Docs/ORIENTATION.md"]

Ingest Brain Dump

Step 0 — Silent Context Load

Files:

Orientation_Docs/INTELLECTUAL_LANDSCAPE.md
Orientation_Docs/COGNITIVE_PROFILE.md
Orientation_Docs/KEYWORD_GUIDE.md
Orientation_Docs/CONTENT_TAXONOMY.md
Orientation_Docs/ORIENTATION.md

Orchestrates brain dump ingestion: explore → classify → verify → create → validate.

Quick Start

User provides unstructured content
Search Second Brain for related files
Separate into distinct ideas (semantic, not algorithmic)
For each idea: verify not duplicate → create file → validate template
Present approval proposal → execute approved actions

Workflow Checklist

Copy and track:

- [ ] Step 1: Load context (ORIENTATION.md, KEYWORD_GUIDE.md, CONTENT_TAXONOMY.md)
- [ ] Step 2: Invoke explore-second-brain - find related files
- [ ] Step 3: Classify content semantically - identify distinct ideas
- [ ] Step 4: For each NEW_IDEA:
      - [ ] Invoke verify-idea - check duplicates
      - [ ] If NOT_FOUND: create Template A
      - [ ] Run validate_template.py - confirm compliance
- [ ] Step 5: Present approval proposal (see references/output-templates.md)
- [ ] Step 6: Execute approved actions
- [ ] Step 7: Report summary

Critical Principles

SEMANTIC SEPARATION - Never algorithmic chunking. Identify ideas by conceptual boundaries.
PRESERVE EXACT LANGUAGE - The owner's keywords are sacred. No paraphrasing.
VERIFY BEFORE CREATE - Always check for duplicates first.
VALIDATE AFTER CREATE - Run template validation on every new file.

Content Classification

Identify type for each segment:

Type	Action
NEW_IDEA	Create Template A in [Category]/
TODO	Add to project TODO file
AUGMENT	Propose addition to existing file
PREDICTION	Create in Predictions/
READING_LIST	Add to AA_Lists/READING_LIST.md
QUESTION	Log only, don't create file

See references/routing-rules.md for full routing table.

Source Detection

Source	Template
Claude Code conversation	A (owner's words THIS conversation)
Voice dictation / voice notes	A (owner's words only)
External podcast / bookmark	B (external content, attribute)

Verification Step

After creating any file, validate:

python3 .claude/scripts/validate_template.py "[filepath]"

If invalid: fix issues immediately. Only proceed when all files pass.

Approval Proposal

See references/output-templates.md for format.

Present each idea with:

Proposed path
Keywords
Project connections
Y/N prompt

Wait for explicit approval before creating files.

Integration

Skill	When
`explore-second-brain`	Step 2 - find related files
`verify-idea`	Step 4 - check duplicates
`process-content`	Create Template A (if needed)
`extract-todo`	Route TODOs to project files

Tier 2 Dependencies

Load before processing:

ORIENTATION.md - Templates, golden rules
KEYWORD_GUIDE.md - Vocabulary reference
CONTENT_TAXONOMY.md - Categories, folder mappings