菜单
CEO-only: publish workspace content to all executives via the corporate repo. EXPLICIT INVOCATION ONLY - never auto-trigger.
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
Daily email intelligence processor. Scans incoming + outgoing 31C Exchange emails (ceo@31c.io via exchangelib/EWS), groups by conversation thread, categorizes for CRM actions, tasks, pipeline updates, knowledge capture, and relationship signals. Presents digest for approval before executing. Integrates with /prime for morning briefing. Trigger: '/email-intel', 'process emails', 'email digest', 'check my email'. Do NOT trigger for: sending email (use send-email.py), reading specific emails, email search queries, or Gmail operations.
Ultrathink principal-engineer review gate. Runs a Validate-Identify-Improve-Adjust (VIIA) pass over a target - a plan awaiting approval, just-executed work, a specific file or directory, or the entire workspace - then runs an adversarial refutation layer (Phase 2.5) with cross-family judge rotation (Claude / Gemini / Grok) and optional two-agent debate on BLOCKER + HIGH findings before presenting findings with concrete proposed fixes for batched approval. Blocks forward progress until approved. Triggers on "scrutinize", "stress-test this", "principal review", "validate and improve", "review the plan before I approve", "audit what you just did", "ultrathink review". Do NOT trigger for artifact grading alone (use /evaluate), fact-checking drafts (use /validate), or strategic reasoning (use /deep-think). Usage: /scrutinize [plan | execution | file:<path> | dir:<path> | workspace | trajectory:<run_id>] [--relentless] [--no-refute] [--include-low-confidence] [--include-ambiguous]
Second-opinion advisor. Consults Gemini, Grok, and Kimi in parallel for independent views on hard or high-stakes calls. Two modes: independent (all models see the problem only, reason fresh) and critique (all stress-test a draft). Distinct from /deep-think (Claude reasoning structured, alone) and /odin (Claude + the curated knowledge brain). Trigger when the user says: "council", "/council", "second opinion on", "consult the council", "what would Gemini/Grok/Kimi say about", "stress-test this with Gemini/Grok/Kimi", "council vote".
Reflective memory consolidation - performs a periodic pass over memory files, synthesizing recent learnings into durable, well-organized memories for future sessions. Validates technical claims against Context7, enforces security protocols, prunes stale entries, and produces a structured consolidation report. Use when the user says "dream", "/dream", "consolidate memories", "memory cleanup", "reflect on recent sessions", "update memories", or at the end of a productive session when significant new information was learned. Do NOT use for: simple memory writes (use auto-memory), knowledge base operations (use /zk), or session initialization (use /prime).
Odin - personal AI advisor with persistent knowledge brain. Ingests books, articles, videos, documents. Builds principles and positions. Gives referenced advice prioritizing learned knowledge. Nine modes: learn (ingest material), consult (give advice), reflect (review brain), recall (query brain), teach (direct learning), log (record an episode - something that happened), collect (scan business threads + captured comms for episodes you forgot to log), compile (unified linting across brain and ZK), skill-proposal (propose a reflection-derived how-to principle as a checklist step in a target skill - proposal only). Triggers on "Odin" as name/address, "ask Odin", "what would Odin say", "/odin". DO NOT trigger on "odin" as the Russian numeral "one" in phrases like "odin variant" or "another one". Only trigger when used as a proper name or form of address.
Workspace-wide semantic recall. Searches the local associative-memory index (scripts/memory-index.py: bge-m3 hybrid dense+BM25, on-machine, zero API cost) across everything meaningful in the workspace -- Odin brain, business threads, CRM, LinkedIn, context, reference, plans, deliverable outputs, knowledge, datastore extracts, and the auto-memory files -- then answers ONLY from the retrieved sources with file-path citations, or says "not in memory" when the index reports a gap. Use when the user asks "what do we know about X", "where did we decide Y", "have we touched Z before", "recall ...", "search my memory for ...", "find what we said about ...", or wants to surface a past decision / brief / contact / note by meaning rather than exact words. Do NOT use for: Odin-brain-only advice or episode dedup (use /odin recall, which is brain-scoped); external/world intelligence on a company or person (use /osint); capturing a NEW note (use /zk); plain exact-string file search (use Grep). This skill never fabricates be
| name | publish-corporate |
| disable-model-invocation | true |
| description | CEO-only: publish workspace content to all executives via the corporate repo. EXPLICIT INVOCATION ONLY - never auto-trigger. |
| metadata | {"author":"Misha Hanin","email":"misha.hanin@odinix.com","version":"1.1"} |
| argument-hint | [description of what to publish] |
| allowed-tools | Read, Write, Edit, Bash(python3:*), Bash(git:*), Glob, Grep |
| model | haiku |
| x-heading-orchestration | {"parallel_safe":false,"shared_state":["../heading-os-corporate/"],"triggers":["publish corporate","publish to executives","push to corporate"]} |
| x-heading-capability | {"what":"CEO-only: copies corporate-classified content from the DATA overlay (.heading-os-data) to the ../heading-os-corporate/ repo and pushes, so execs pull it with plain `git pull` (git-native; no scheduled hourly sync).\n","how":"Explicit invocation only - type /publish-corporate [what to publish]; never auto-triggers. It verifies admin role, runs a critical-leak scan, previews the file set for confirmation, then copies, commits, and pushes.\n","when":"Use for targeted selective publishing to executives. For a full versioned push including BUILD.json and CRM aggregate use /push-updates; for a personal workspace backup use /backup.\n"} |
| x-heading-routing | {"category":"Operations","triggers":["NEVER auto-trigger. Explicit `/publish-corporate` only."],"exclusions":["Full push with CRM -> /push-updates"],"compound":"No","router":"manual"} |
CEO-only skill. Copies corporate-classified content from the DATA overlay (.heading-os-data) to the heading-os-corporate repo for distribution to all executives. Canonical mechanism:
python scripts/publish-corporate.py --preview|--copy|--verify(reads the source from the data overlay, writes to ../heading-os-corporate/). Execs pull with plaingit pull— there is no scheduled sync.
.workspace-identity.json - verify role is "admin". If not, say "This skill is CEO-only." and stop.../heading-os-corporate/. If not, say "Corporate repo not found. Run initial setup first." and stop.$ARGUMENTS - Description of what to publish (e.g., "Updated strategy for Q2", "New competitor-intel skill", "Updated a competing vendor competitive document")Based on $ARGUMENTS, identify which files in ceo-main should be copied to the corporate repo.
Classification-driven publishing: classification resolves from config/routing-map.yaml (the single input; classification.json was removed in HEADING OS step 7). Post-cutover (step 8, 2026-06-14) publish ships ONLY files whose three-value routing destination is corporate — content, not code. Engine code is NOT published here; execs receive it by cloning the engine repo (.heading-os). The corporate set is content-only: datastore/, knowledge/shared/, the two context/ carve-outs, crm/ config/aliases/address-book, corporate/ daemon config. Use python scripts/classification-health.py --corporate-only to list it.
If $ARGUMENTS references a specific file currently classified as ceo-only (routed private), warn the CEO and ask if they want to reclassify it before publishing (add a rule to config/routing-map.yaml).
NEVER publish (safety check - overrides classification):
context/personal-info.md (CEO personal)context/people.md (CEO contacts)crm/contacts/* (CEO CRM data)datastore/books/* (CEO personal library)knowledge/fleeting/*, knowledge/meetings/*, knowledge/people/* (personal knowledge)knowledge/technology/*osint-api-credentials* (API keys).env (secrets).workspace-identity.json (per-workspace)outputs/* (CEO deliverables)threads/ (entire directory) - operational thread registry, ceo-only on every machinethreads/personal/** - explicitly listed even though covered by parent (defence in depth)private in config/routing-map.yaml (CEO-personal tooling — e.g. modem-tune.py, the fireside/service-host scripts, the one-off CEO-instance scripts, plus anything added later). Single source of truth: scripts.utils.workspace.get_ceo_only_scripts().Note: For full end-to-end push with BUILD.json versioning, use
/push-updatesinstead. This skill is for targeted selective publishing.
Show the user a clear list:
Files to publish to all executives:
1. context/strategy.md (modified 2026-03-19)
2. .claude/skills/competitor-intel/SKILL.md (new)
...
This will be available to executives the next time they run `git pull` on their corporate clone (git-native; no scheduled task).
Ask for confirmation: "Publish these files? (yes/no)"
Before copying, run the shared critical-leak scanner on every file in the publish set:
python scripts/sanitize-check.py <file1> <file2> ...
The scanner uses the primitives in scripts/utils/sanitize.py. It flags the narrow set of terms that must never land in corporate (vault codenames, ceo-only paths, private contact markers). On exit code 1, stop - surface the findings, ask the CEO to fix the source files, do not proceed to Step 3.
cd to corporate repo directorygit add -Agit diff --cached --stat to show what changed"Publish: {description from arguments}"VERSION file in corporate repoCHANGELOG.md:
## [1.0.1] - 2026-03-19
- {description from arguments}
- Files: {list of changed files}
"Bump version to 1.0.1""Published to the corporate repo. Executives will receive these updates the next time they run git pull on their corporate clone."