最近新增
刚加入收藏的新技能，抢先试用。
Runtime Closeout
OmniNode-ai
One-dispatch runtime closeout — dispatches to node_runtime_closeout_orchestrator (canonical ORCHESTRATOR; preflight + fresh-deploy fitness gate + deploy reuse + runtime proof matrix over the bus, terminal ModelCloseoutReceipt)
review-canonry-contributions
SlopDotCash
Reviews exact-head Canonry contributions for correct metrics, surface parity and evidence. Use on an existing PR in Canonry/canonry; excludes implementation ownership, self-approval, security certification and payment decisions.
contribute-to-payzcode-ai
SlopDotCash
Prepare a bounded contribution to lysande62/payzcode-enterprise after its project permission, authority and security gates pass. Use for an existing approved Payzcode AI task, with real application evidence and exact-head attribution.
contribute-to-feed
SlopDotCash
Fixes and proves real defects in Feed (feedforagents/feed) inside its approved scope. Use for a reproduced bug, trading-algorithm or simulation validation, agent-integration failures, or security; excludes UI and copy changes, unapproved features, coverage-only tests and mock-only proof.
contribute-to-darling-arm64
SlopDotCash
"Raise a real macOS application one verified tier up the arm64 Darling ladder, fix a reproduced defect upstream in darlinghq, or falsify a recorded finding in xchemtina/darling-arm64. Every outcome ships a control, an A/B/A where it claims a fix, and a rerunnable harness. Use for measured arm64 capability, never for x86_64 work, refactors, or cleanup."
/onex:status — Foreground Status Routing
OmniNode-ai
Foreground status snapshot — routes to merge-sweep-lead teammate if present, otherwise spawns a one-shot snapshot agent. Avoids inline repository polling from foreground.
/onex:ship_dirty_canonical — Auto-ship dirty canonical repos
OmniNode-ai
Detect uncommitted files in canonical workspace repo clones and auto-ship each dirty repo to a worktree + PR. Runs node_dirty_canonical_sweep in-process via its module entrypoint (omnimarket).
/onex:shim_audit — one command, one typed result
OmniNode-ai
Scan all OmniNode repos for expired or expiring @shim decorator annotations and create Linear
/onex:session — one command, one typed result
OmniNode-ai
Dispatch-only shim for the unified session orchestrator. All phases (health gate, RSD scoring,
Runner
OmniNode-ai
GitHub Actions runner management — deploy, update, and monitor self-hosted runners
email-bison
ameyadeshmukh10
Integrate with the Email Bison sales-sequencing API to extract and analyze master-inbox replies. Use when the user wants to pull interested replies, conversation threads, leads, campaigns, or other Email Bison data, or extend this skill with new Email Bison use cases.
infographic-syntax
PersonalClaw
Author infographics with the AntV declarative DSL — pick a template, fill a small indented data tree, and save as an artifact (kind=infographic) that renders to crisp SVG and streams as you write it. Load when the user wants an infographic, a visual summary, a comparison/steps/hierarchy/stats graphic, or "make this look like a poster/diagram".
artifacts
PersonalClaw
Persist, version, and iterate on LLM-generated UI (widgets, HTML, markdown). Load when the user wants to save, find, update, or iterate on a previously-rendered widget — anything that should outlive the chat scrollback.
grill
PersonalClaw
Structured questioning to reach shared understanding before action. Walks the decision tree one branch at a time, checks memory for already-answered questions, saves every answer as a lesson. Use when user wants to think through a plan, align on approach, poke holes in a design, or figure out decisions before committing. Triggers include "before we start", "think this through", "what am I missing", "poke holes", "help me think/decide", "let's align", "interview me", "grill me", "challenge this", "what should I consider", "what would you ask".
editorial-document
PersonalClaw
Write long-form editorial documents as clean, semantic HTML saved as an artifact (kind=document) — reports, briefs, explainers, proposals, write-ups. Covers the house style (structure, voice, typography) AND the security contract (the HTML is sanitized fail-closed, so author within the allowlist). Load when the user wants a polished written document, report, brief, or explainer that should read like a publication, not a chat message.
document-authoring
PersonalClaw
Author a real document — a report, proposal, slide deck, spec, or paper — by settling audience, claim, and structure before drafting prose, then writing to that structure. Use when asked to write or draft a document rather than answer a question.
best-of-n
PersonalClaw
Sample several candidate answers in parallel, judge them against stated criteria, and present the winner with the runners-up kept one click away. Confirms the count and the criteria first because each candidate is a separate model call. Use when the user wants options rather than one answer. Triggers include "give me N options", "give me 3 versions", "best of", "try a few versions", "sample and pick", "generate a few and choose", "which of these is best", "draft some variations".
Release Readiness Handshake (RRH) Skill
OmniNode-ai
Opt-in preflight validation via Release Readiness Handshake (RRH) -- runs A1 (collect) -> A2 (validate) -> A3 (store) pipeline before side-effecting phases
Rewind — Conversational Rewind
OmniNode-ai
Query what a named agent was doing at a specific time. Conversational rewind — search the event stream by agent identity and timestamp.
Resume Session
OmniNode-ai
Load projected session state for a task and bind the current session to it
Release
OmniNode-ai
Org-wide coordinated release pipeline (STRUCTURAL PLACEHOLDER — node_release performs no git/gh/PyPI I/O today; full handler implementation is pending). Target design bumps versions, pins cross-repo deps, creates PRs, merges, tags, and triggers PyPI publish across all OmniNode repos in dependency-tier order
refill-sprint Skill
OmniNode-ai
Auto-pull tech debt tickets from Future into Active Sprint when the sprint queue is empty or below capacity threshold
Redeploy
OmniNode-ai
Full post-release runtime redeploy — dispatches to node_redeploy_orchestrator (canonical ORCHESTRATOR; prod-gate COMPUTE + deploy publish-monitor EFFECT + FSM REDUCER over the bus)
Record Friction
OmniNode-ai
Record a friction event for a skill process blocker