菜单
Manually trigger workspace sync - git pull of the code/data clones, then a push-all backup. 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 | sync |
| disable-model-invocation | true |
| description | Manually trigger workspace sync - git pull of the code/data clones, then a push-all backup. EXPLICIT INVOCATION ONLY - never auto-trigger. |
| argument-hint | [pull|backup] |
| metadata | {"author":"Misha Hanin","email":"misha.hanin@odinix.com","version":"2.0"} |
| allowed-tools | Bash(python3:*), Bash(git:*), Read |
| model | haiku |
| x-heading-orchestration | {"parallel_safe":false,"shared_state":[],"triggers":["sync","full corp sync","pull updates"]} |
| x-heading-capability | {"what":"Manually syncs the workspace with plain git: pulls the latest code (and data) with `git pull --ff-only`, then backs up via `scripts/push-all.py`. This replaced the retired workspace-sync.py copy-and-orphan-delete engine.\n","how":"Run /sync (explicit-invocation-only, never auto-triggers) to pull then back up, or scope it with /sync pull | backup. pull = git pull --ff-only on the engine and data clones; backup = push-all.py.\n","when":"Use to pull updates or back up between sessions. To publish corporate changes out to all execs use /push-updates; for a backup alone use /backup (push-all).\n"} |
| x-heading-routing | {"category":"Operations","triggers":["NEVER auto-trigger. Explicit `/sync` only."],"exclusions":["Push to execs -> /push-updates"],"compound":"No","router":"manual"} |
Manually sync the workspace using plain git. This replaced the retired
workspace-sync.py mechanism (see
plans/2026-06-26-retire-workspace-sync-disk-import.md): there is no longer a
copy-and-orphan-delete engine, no scheduled sync task, and no risk of the old
"delete the engine tree" failure. Sync is now two simple, non-destructive
operations.
git pull --ff-only on the engine clone (.heading-os)
and the data overlay (.heading-os-data). Fast-forward only, so a divergent
local history surfaces as a plain error instead of an implicit merge.
1b. Corporate content (execs) - python scripts/sync-corporate.py refreshes the
gitignored .corporate-repo/ clone of heading-os-corporate, read in place via
get_corporate_root(). It self-no-ops on the CEO workspace, so it runs
unconditionally in the pull sequence (no skill-level branch).python scripts/push-all.py commits and pushes BOTH repos
to their private origin/main with the pre-push secret scan and [0 0]
ahead/behind verification.First-run record recovery after a clean deploy is a separate one-shot:
python scripts/import-legacy-records.py --from <old-records-path>(local, non-destructive). It is NOT part of /sync.
/sync - pull, then backup/sync pull - git pull --ff-only on the engine and data clones only/sync backup - python scripts/push-all.py only.heading-os-data sibling, or HEADING_OS_DATA if set).git -C <engine-root> pull --ff-only and
git -C <data-root> pull --ff-only, then python scripts/sync-corporate.py
(refreshes .corporate-repo/ on execs; no-ops on the CEO workspace). Show each
result.python scripts/push-all.py and show its output./sync: pull first, then backup.git pull non-fast-forward: "Local history diverged - reconcile manually
(git -C <root> status) before syncing; /sync will not force or merge.".env and retry; never pass --no-verify.".env."--no-verify or force-push to work around a failed gate.