This skill should be used when the user asks to "find jobs", "search for jobs matching my expectations", "find the best job matching my expectation", "job hunt", "search job platforms", "match jobs to my profile", "find AI engineer jobs", "find ML engineer jobs", "search for senior software engineer roles", "find jobs with visa sponsorship", or mentions job hunting, job matching, career search, or job platform scraping.
- 📄 agent-job-background.js
- 📄 SKILL.md
Use to spawn or check on long-running background agent jobs (each launches a new Docker agent container that opens a PR when done). Trigger when the user says "create a background job", "spawn an agent", "kick off a job", "run this in the background", "check job status", or asks "what's the status of job <id>".
Streamline session-to-session coordination with pi-intercom. Send messages, delegate tasks, and coordinate work across multiple pi sessions on the same machine. Use for planner-worker workflows, cross-session context sharing, and real-time collaboration between sessions. --- # Pi Intercom Skill Use this skill when you need to coordinate work across multiple pi sessions running on the same machine. Pi-intercom enables direct 1:1 messaging between sessions for delegation, context sharing, and collaborative workflows. When you are supervising `pi-subagents`, delegated child agents can escalate to you via `contact_supervisor` if `pi-subagents` supplied child bridge metadata. This skill covers how to handle those orchestrator-side escalations. ## When to Use - **Task delegation**: Split work between a planner session and worker sessions - **Context handoffs**: Send findings from a research session to an execution session - **Clarification loops**: Worker asks questions, planner answers, work continues - **Multi-session workflows**: Coordinate between specialized sessions (frontend/backend, research/implementation) ## Core Patterns ### Pattern 1: Planner-Worker Delegation The most common pattern. One session holds the big picture, others do hands-on work. **Setup** (in each session): ``` /name planner # Terminal 1 /name worker # Terminal 2 ``` **Planner delegates a task** (fire-and-forget): ```typescript intercom({
- 📁 .claude-plugin/
- 📁 .github/
- 📄 .markdownlint.json
- 📄 INSTALL.md
- 📄 install.sh
Autonomous work mode that lets Claude work continuously while the user is away. Activates pre-flight risk assessment, dangerous-ops approval, and a blocker decision framework. Use "/nonstop" to activate, "/nonstop off" to deactivate. Use this skill whenever the user says things like "go nonstop", "keep working", "don't stop", "I'm going AFK", "work while I sleep", "finish this without me", or wants Claude to work autonomously without interruption.
Apply to a job by URL — auto-routes to the right ATS filler (LinkedIn Easy Apply / Greenhouse / Lever / Jobvite / Ashby), dry-run by default, renders an emoji-tagged result table. Proactively invoke this skill (do NOT answer conversationally) when the user pastes a LinkedIn/Greenhouse/Lever/Jobvite/Ashby job URL (with or without the word "apply"), says "apply to this", "try this one", "fill the form", "run the filler", "can you apply for me", "submit this application", drops a job posting into chat, or invokes /job-apply.
Experimental working-model protocol shipped with memesh v4.1. Status — protocol present + instrumented; effectiveness in real usage is being collected (see `memesh patterns`), not yet proven. Suggests a user-as-CTO / Claude-as-orchestrator / background-agents-as-engineers split. Claude routes work by verifiability, dispatches parallel background agents for high-verifiability technical work, and stays foreground only for strategic/understanding work that the user must own. Use as a default for non-trivial software tasks; report back when it helps or doesn't.
Use lb as the primary task tracker in Linear-backed repos. Use when claiming work, creating dependencies/subissues, updating status, closing work, or avoiding ephemeral built-in todo tools.
- 📁 agents/
- 📁 references/
- 📄 model-policy.json
- 📄 SKILL.md
Handles ambiguous or high-impact coding work where missing artifacts, protected-surface changes, or unresolved implementation branches could materially change the implementation. Use for coding tasks that need artifact recovery, guarded clarification, or post-patch verification. Skip trivial, formatting-only, or already explicit single-path work.
- 📁 agents/
- 📁 references/
- 📄 README.md
- 📄 SKILL.md
Launch and coordinate Codex subagents as deferred tasks. Use when the user wants to start bounded subagent work now, keep the main thread moving without waiting by default, then later join, collect, or redirect that work through a stable task reference.
Read and summarize the user's local work notes from `~/work/notes/` and `~/work/shared/`. Use when the user asks to "summarize notes", "sync notes", "review my notes", "what's in my work notes", or any operation that needs the contents of their personal markdown notebook. Returns the raw markdown contents of all .md files in those folders so the calling assistant can summarize, sync, or paraphrase as the user instructs.
Run interactive, Socratic pre-implementation discovery for medium/large or ambiguous work in a harness-driven repository by clarifying goals, constraints, tradeoffs, and workflow direction before planning or execution. Use this whenever the next move is unclear, the user needs help choosing an approach, or archived work may need to reopen.
Official OpenClaw Zigrix entrypoint. Force Zigrix delegation when a message starts with `/oz`, and semantically route plain-language requests to hand work off, assign it, or have Zigrix take it instead of doing the work directly.
