メニュー
Bulk file ingestion and self-evolving memory organization using relationship discovery. Auto-discovers relationships between stories, adds YAML frontmatter, regenerates indexes. Works incrementally — safe to run multiple times.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Use this skill whenever the user asks to implement, build, fix, ship, add, refactor, migrate, or change ANY code — features, bugs, plugins, skills, migrations, hooks, rules, configs, in any repo. Triggers on 'build X', 'fix Y', 'implement Z', 'ship this to <plugin>', a ticket id with code work. This is the Agentic SDLC pipeline; do NOT hand-roll `codex exec` or ad-hoc git/PR shipping — route through Stage 0 (claim), the 9 core stages, the Gate-A.5 change-manifest gate, Gate-A.7 design-review gate, Stage 5.5/5.6/5.7/5.8 quality gates, and Stage 10 (completion).
Activate real-time prompt sharpening and persona detection. Use when the user says "co-dialectic", "cod", "codi on", "improve my prompts", "prompt sharpening", "teach me to prompt", or wants to improve their AI communication skills. Provides status line, persona system, caliber enforcement, prompt improvement, context management, auto-codification protocols, and auto-verification by stakes (Protocol 8 — fires hallucination-detector / judge-panel / unknown-unknown / canonical-claim verifier automatically before every substantive output, scaled to the stakes of the artifact).
Surfaces one-week and two-week follow-up nudges for applications that are applied and awaiting response, with a plain-text draft ready for the human to approve. Draft-only: never sends. Use when the user asks what to follow up on, stale applications, application nudges, or job-search follow-ups.
Detects explicitly shareable career milestones in the job pipeline and surfaces draft-only brand-post prompts. Fail-closed by firewall design: no shareable flag means no suggestion. Use when the user asks for milestone brand moments, career-to-brand prompts, or shareable pipeline milestones.
Career OS home screen and central router. Two jobs: show the dashboard and route every action to the correct skill. Mission Control reads and presents but never directly edits persistence files.
Maps your network to target companies. Discovers warm intro paths, scores connection strength (5-level scale), ingests new contacts from conversation, and recommends who to reach out to and how. Also detects relationship origin (where/when you met) and cohort clusters (people from the same company/era). Records inbound recruiter DMs that came from the user's public posts as brand-attributed pipeline opportunities. Say "who do I know at [Company]", "how do I know [Name]", "tell me about [Contact]", or "a recruiter DM'd me after seeing my post".
| name | organize |
| description | Bulk file ingestion and self-evolving memory organization using relationship discovery. Auto-discovers relationships between stories, adds YAML frontmatter, regenerates indexes. Works incrementally — safe to run multiple times. |
| triggers | ["organize","organize my files","ingest career files","link my stories","index my stories"] |
Ingests existing career files into the brain/ structure and discovers relationships between them. Cross-references stories by shared companies, people, competencies, and themes.
Safe to run multiple times — incremental by design.
Always start your response with this header so the user knows a Career OS skill is responding:
━━━ Career OS: Organize ━━━
This is a conversational skill. Claude reads the user's files, classifies them, confirms with the user, then organizes.
When brain/stories/STORY_INDEX.md does NOT exist.
Scan the context folder recursively for career-relevant files:
.md, .txt, .docx, .pdfbrain/, .git/, node_modules/, Resumes & Cover Letters/ (already organized)Classify each file into one of:
| Type | Destination | Detection signals |
|---|---|---|
| Story | brain/stories/ | Contains narrative about a project, achievement, or experience |
| Contact | network/people/ | Contains info about a person — name, company, relationship |
| Resume | Resumes & Cover Letters/ | Contains employment history, skills summary |
| Cover letter | Resumes & Cover Letters/ | Addressed to hiring manager, references specific role |
| JD | brain/reference/jd-samples/ | Job posting content — requirements, responsibilities |
| Notes | Leave in place | General notes, not career-specific enough to classify |
| Other | Leave in place | Binary files, non-career content |
ALWAYS present classification to user before any changes:
I found these career-relevant files:
| File | Type | Action |
|------|------|--------|
| my-google-story.md | Story | → brain/stories/google-story.md |
| john-doe-notes.md | Contact | → network/people/john-doe.md |
| resume-2025.pdf | Resume | → Resumes & Cover Letters/ |
| random.txt | Notes | Leave in place |
Approve these changes? I won't move anything until you confirm.
On user approval:
brain/stories/STORY_INDEX.mdbrain/identity/glossary.md with extracted entities~/.career-os-state/pending-organize if it existsgit add brain/ "Resumes & Cover Letters/" && git commitWhen brain/stories/STORY_INDEX.md EXISTS.
If no new files found:
All files are organized. Running relationship discovery on existing stories...
Then run relationship discovery only and report any new connections found.
After files are organized, cross-reference all stories to find connections.
From each story, extract:
For each pair of stories:
related_stories frontmatterReport connections found:
Relationship discovery complete:
• "google-ml-platform" ↔ "google-team-scaling" — shared: Google, ML, leadership
• "startup-pivot" ↔ "product-launch" — shared: product strategy, cross-functional
• 3 new entities added to glossary
---
title: Descriptive Story Title
companies:
- Google
- Anthropic
people:
- Jane Smith
- John Doe
competencies:
- engineering leadership
- system design
- cross-functional collaboration
technologies:
- Python
- Kubernetes
- LLMs
themes:
- scaling teams
- technical strategy
interview_questions:
- Tell me about a time you scaled a team
- Describe a technical decision with significant trade-offs
related_stories:
- google-team-scaling
- startup-pivot
---
---
name: Jane Smith
companies:
- Google (2020-2023)
- Anthropic (2023-present)
relationship: former colleague
warmth: 3 # 1=cold, 2=network, 3=warm-professional, 4=warm-offline, 5=inner-circle
channel: linkedin
last_contact: 2026-03-01
context: Worked together on ML platform team at Google
---
# Story Index
Generated by Career OS organize skill. Do not edit manually — will be regenerated.
| Story | Companies | Competencies | Related |
|-------|-----------|-------------|---------|
| [google-ml-platform](stories/google-ml-platform.md) | Google | system design, ML | google-team-scaling |
| [google-team-scaling](stories/google-team-scaling.md) | Google | leadership, hiring | google-ml-platform |
| [startup-pivot](stories/startup-pivot.md) | StartupCo | product strategy | product-launch |
After organizing, update brain/identity/glossary.md with:
Merge with existing glossary content — never overwrite what's already there.