Showing 5041–5070 of 10205 skills
Distributed voting and agreement protocols for multi-agent decision making. Use this skill when: 1. Multiple agents need to agree on a value or decision 2. You need Byzantine fault-tolerant consensus in a swarm 3. You want to coordinate distributed transactions or state changes Do NOT use this skill when: - A single leader can make decisions (use pilot-leader-election) - You only need eventual consistency (use pilot-gossip)
TeoSlayer/pilot-skills
Advanced agent discovery by tags and status. Use this skill when: 1. Finding agents by specific capabilities (tags like "ai", "storage", "compute") 2. Looking up detailed agent information and metadata 3. Filtering connected peers by tag substring Do NOT use this skill when: - You need to establish trust (use pilot-trust instead) - You need to connect to a known agent (use pilot-connect instead) - You need to visualize the network (use pilot-network-map instead)
TeoSlayer/pilot-skills
Human-friendly naming with aliases and namespaces. Use this skill when: 1. Setting or changing an agent's hostname 2. Resolving human-readable names to node IDs 3. Managing naming conflicts or namespace collisions Do NOT use this skill when: - You need to discover agents by capability (use pilot-discover instead) - You need to manage trust (use pilot-trust instead) - You need actual DNS resolution (port 53 service is separate)
TeoSlayer/pilot-skills
Shared folder that automatically synchronizes between peers using Pilot Protocol pub/sub. Use this skill when: 1. You need a persistent shared folder that stays in sync across agents 2. You want automatic file synchronization without manual intervention 3. You need multi-peer folder sharing with eventual consistency Do NOT use this skill when: - You only need one-time file transfer (use pilot-share instead) - You need strict consistency guarantees (use pilot-sync with locks) - You need real-time streaming (use pilot-stream-data instead)
TeoSlayer/pilot-skills
Send and receive emails via Pilot Protocol messaging. Use this skill when: 1. You need to send email notifications from Pilot agents 2. You want to receive emails as Pilot events 3. You're integrating agents with email-based workflows Do NOT use this skill when: - You need real-time messaging (use native Pilot instead) - Email server is not configured - The daemon is not running
TeoSlayer/pilot-skills
Multi-agent event aggregation on shared topics for coordinated workflows. Use this skill when: 1. You need to aggregate events from multiple agents on a shared topic 2. You need to broadcast events to all subscribed agents 3. You need to coordinate state changes across a fleet of agents 4. You need to implement fan-out messaging patterns Do NOT use this skill when: - You need point-to-point messaging (use pilot-protocol connect instead) - You need persistent storage (use pilot-event-log instead) - You need filtered or transformed events (use pilot-event-filter instead)
TeoSlayer/pilot-skills
Filter and transform events before delivery using pattern matching and jq transforms. Use this skill when: 1. You need to filter events by content, not just topic wildcards 2. You need to transform event payloads before processing 3. You need to route events conditionally based on content 4. You need to reduce event noise by selective forwarding Do NOT use this skill when: - Topic wildcards alone are sufficient (use pilot-event-bus instead) - You need all events without filtering (subscribe directly) - You need persistent storage (use pilot-event-log instead)
TeoSlayer/pilot-skills
Use when connecting a coding agent — Claude Code, OpenAI Codex, or Cursor — to the zymtrace MCP server so the user can analyze CPU and GPU flamegraphs through natural-language queries. Walks through finding the gateway URL, generating an auth token (if service-token auth is on), adding the server with the right command for the user's client, and verifying the connection. This skill is plumbing only — the analytical workflow lives in `optimize-cpu-workloads` and `optimize-gpu-workloads`. Trigger phrases: "connect zymtrace MCP", "set up zymtrace MCP", "configure zymtrace MCP", "add zymtrace to /mcp", "connect Claude/Codex/Cursor to zymtrace", "/mcp doesn't show zymtrace", "zymtrace MCP token", "Cursor zymtrace integration", "set up the zymtrace AI assistant".
zystem-io/zymtrace-skills
Analyze JVM memory-allocation profiles with zymtrace (Java only): what allocates the most bytes and objects, why GC is busy, and where allocation churn burns CPU (boxing, String churn, collection resizing, buffers). Turns allocation profiling on if it's off, names the allocation sites, and applies the fix in the user's code. Also where a CPU profile turns out allocation- or GC-bound. Non-Java services → optimize-cpu-workloads; GPU memory → optimize-gpu-workloads; OOMKilled or crashes → the troubleshoot skills. Trigger phrases: "what's allocating the most memory", "analyze the JVM allocation profile", "why is GC so busy", "reduce GC pressure", "allocation churn", "what creates the most garbage", "reduce heap churn", "which Java code allocates the most", "enable allocation profiling".
zystem-io/zymtrace-skills
Use when the zymtrace profiler agent is misbehaving — pods crash-looping, image pull errors, OOMKilled, CPU profiles working but no GPU profiles, NVML library not found, PC sampling not producing SASS-level data, license errors on the profiler side, or optional GPU features producing nothing (no stragglers / NCCL data, empty Models page, no GPU timeline data). Walks symptom → diagnosis → fix. Focused on the agent itself; for "no data anywhere" use troubleshoot-zymtrace-backend. Trigger phrases: "profiler not working", "profiler pods crashing", "profiler CrashLoopBackOff", "profiler ImagePullBackOff", "agent OOMKilled", "no GPU profiles", "CPU profiles work but GPU doesn't", "NVML library not found", "PC sampling not working", "profiler license rejected", "agent restart cycle", "zymtrace agent unhealthy", "fix the profiler", "no stragglers detected", "GPU Stragglers page empty", "no NCCL metrics", "Models page empty", "no Model Layer frames", "no timeline data", "No high-resolution data in this range".
zystem-io/zymtrace-skills
Create a new agent skill (or Claude Code slash command) from a plain-language description, using live spec fetching, pattern research, and an approval-gated blueprint before any files are written. Use whenever the user wants to build, scaffold, or author a new skill, subagent capability, or slash command, including phrasings like 'make a command for X', 'create a slash command', 'turn this into a reusable skill', or 'package this workflow as a skill'. Not for editing CLAUDE.md/AGENTS.md memory rules (use create-rule) or discovering/installing existing third-party skills (use find-skills).
mgiovani/ai-arsenal
Search, install, update, and remove third-party Agent Skills from skills.sh or any GitHub/GitLab repo via the `npx skills` CLI. Use when the user wants to "find a skill", "install a skill from github", "search skills.sh", or add third-party capabilities to Claude Code/Cursor/other agents. Not for authoring new skills (see create-skill).
mgiovani/ai-arsenal
Run raw ankitpokhrel/jira-cli commands directly against Jira Cloud or on-prem, issue/epic/sprint CRUD, JQL-style filtering, and scripting/CI automation (bulk assign, auto-label, sprint add). Invoke explicitly via /jira-cli, or when the user wants literal `jira` CLI syntax, a filter the curated skills don't expose, or a bash/CI script that drives jira-cli. Manual-invocation skill, does not auto-fire on general mentions of "jira" or "ticket".
mgiovani/ai-arsenal
Turn any task into a model-tiered multi-agent plan, decompose it into subtasks, classify each as research, implementation, planning, or synthesis, map every subtask to the right subagent and model (haiku for research/exploration/finding, opus for planning, sonnet for everything else), then run independent tracks in parallel under strict one-owner-per-file discipline before synthesizing the result yourself. Use for "act as orchestrator", "spawn subagents for this", "delegate this with the right models", "run this in parallel", or any task large enough to fan out across multiple independent workstreams. Not for a single well-scoped feature with a known shape (use implement-feature), and not for pure task breakdown with no execution (use project-planner).
mgiovani/ai-arsenal
Reconstruct what work was actually done on a project by mining Claude Code session transcripts (~/.claude/projects/**/*.jsonl) — streaming grep/jq recipes for files up to 150MB, the CLAUDE.md boilerplate false-positive trap, core/partial/incidental classification, and fork detection. Use when asked "what have we done on X?", when rebuilding a project history, when recovering decisions or work that never reached git, or as the history phase of a footprint inventory.
ever-just/agentskills
Operate the everjust.app custom Appointments app (online booking → calendar event + optional CRM lead + confirmation email) via the Odoo MCP/ORM. Use when the task is to configure a bookable appointment type and its weekly slots, create/confirm/reschedule/cancel a booking as a tenant, inspect a customer's bookings, diagnose why a public /appointment slot isn't offered (min-advance / max-days / staff conflict), or wire a booking to CRM. This is the BESPOKE everjust_appointment stack (appointment.type / appointment.slot / appointment.booking) — NOT Odoo's stock Enterprise appointment.* models, and NOT calendar.event directly. Only some tenants have it installed. Cross-references [[everjust-platform]] and [[everjust-agent-mcp]]; CRM leads flow to native crm.lead; confirmation email goes through a stock mail.template (NOT [[everjust-mail-ops]]).
ever-just/agentskills
Operate the Calendar + Contacts app of an everjust.app tenant over the Odoo MCP/ORM — the shared res.partner contact spine and calendar.event scheduling, with optional Google/Microsoft calendar sync. Use when the task is to create/find/update a contact (person or company), tag/segment contacts with res.partner.category, look up who a partner is before mailing or invoicing them, schedule/reschedule/cancel a calendar.event, add or read attendees and their RSVP state, check a user's free/busy for double-booking, or reason about how a booking became a calendar event. This is STOCK Odoo calendar + contacts with a thin everjust layer (res.partner.is_agent flag, phone/SMS action methods, and everjust_appointment writing events) — NOT a custom webmail or a bespoke scheduler. res.partner is the ONE contact record shared across CRM, mail, projects, invoicing and appointments; edits here ripple everywhere. Cross-references [[everjust-platform]], [[everjust-agent-mcp]], and [[everjust-mail-ops]].
ever-just/agentskills
Operate the "Documents" app of an everjust.app Odoo 19 tenant (browse/create/move folders and files, upload, download, tag, migrate storage, point Documents at the tenant's private cloud) via the Odoo MCP/ORM. Use to read or mutate a tenant's documents — create a folder (dms.directory) or file (dms.file), fetch a file's bytes, move/archive/lock/tag a file, or wire the app to Nextcloud-over-WebDAV. This is the OCA dms stack (dms.file / dms.directory / dms.storage) plus the bespoke everjust_documents layer that stores every file PHYSICALLY in the tenant's Nextcloud over WebDAV (fs_storage + fs_attachment) — NOT Odoo Enterprise "documents.document" (that model does not exist here), NOT raw ir.attachment. Only some tenants have it installed (tcstartupweek + headsup as of 2026-07, NOT connectdomain) — check first. Files depend on live Nextcloud connectivity and a webdav4 monkeypatch. Cross-refs [[everjust-platform]], [[everjust-agent-mcp]], [[everjust-mail-ops]], [[everjust-sms]].
ever-just/agentskills
Operate the Events app of a live everjust.app tenant (create/publish an event, take & manage attendee registrations, wire registrations to CRM leads, schedule attendee email/SMS reminders, inspect seats/registration state) via the Odoo MCP/ORM. Use when the task is to set up or edit an event on an everjust.app workspace, register/confirm/cancel an attendee, turn registrations into crm.leads, add or diagnose a registration confirmation/reminder email or SMS, check seat availability, or reason about which event modules are installed on a tenant. This is STOCK Odoo event/website_event/event_crm/event_sms — NO custom everjust event addon — but website_event_track (event.track / speakers / agenda) is installed on ONLY some tenants, and event_sms reminders ride the per-company everjust SMS gateway swap. Cross-references [[everjust-platform]], [[everjust-agent-mcp]]; SMS via [[everjust-sms]], leads via native CRM, event mail is stock event.mail (NOT the [[everjust-mail-ops]] webmail stack).
ever-just/agentskills
Operate the SMS app of an everjust.app tenant (send an SMS to a number, send SMS as chatter on a partner/lead, use an SMS template, mass-SMS a set of records, inspect delivery state, and reason about which gateway a send actually took) via the Odoo MCP/ORM. Use when the task is to text someone from an everjust.app workspace, diagnose why an SMS failed, check an sms.sms row's status, or confirm which provider (TextBee / Ringover / Twilio / Odoo IAP) the tenant is on. This is the everjust_sms_gateway stack — the transport under sms.sms is provider-SWAPPED per company via res.company.sms_provider, NOT necessarily Odoo IAP. Do NOT hand-POST TextBee/Ringover; drive sms.sms/sms.composer and let _get_sms_api_class route it. Cross-references [[everjust-platform]] and [[everjust-agent-mcp]]; sibling of [[everjust-mail-ops]].
ever-just/agentskills
Use when writing, fixing, or refactoring code in a software repository, as the baseline discipline alongside more specific skills. Ground every edit in the real code path, do only the requested work and what it necessarily implies, avoid speculative abstraction and drive-by edits, apply the risk gate to changes touching money, auth, data, interfaces, or other high-risk areas, and close with verification. Do not use alone for review-only, diagnosis-only, or question-answering requests.
rumoii/rumo-engineering-skills
Use when the user asks to wrap up ("收尾"), hand off, pause, or package a task so another session, agent, or client can continue it, or when a new session must pick up earlier work, such as asking for current progress, the next step, or where a topic stands ("汇报一下当前进度", "下一步做什么", "接着上次做", "回忆一下 X 做到哪了") or to continue another agent's session. Writes a handoff document when asked or when wrapping up leaves work open; picks up from this project's recent Claude Code, Codex, and Kimi Code sessions, checked against the repository. Do not use for a plain end-of-task summary.
rumoii/rumo-engineering-skills
Use when the user runs rumo-setup, asks to configure or change which agent CLIs, models, and reasoning efforts the Rumo skills use for multi-model review or default delegation ("配置 agent", "把评审换成 grok", "思考强度改成 high"), or when a Rumo script reports that agents are not configured. Probes every chosen lane with one tiny read-only turn before saving. Do not use to delegate a task now (use rumo-agent-collaboration) or to configure project profiles (use rumo-project-profile).
rumoii/rumo-engineering-skills
Use when reviewing current branch for bugs before pushing or merging, when wanting a thorough multi-agent review of local changes, or when preparing work for human review. Not for codebase structure, not for code style, and not for fixing what it finds.
Ovid/paad
Use when reviewing current branch for bugs before pushing or merging, when wanting a thorough multi-agent review of local changes, or when preparing work for human review. Not for codebase structure, not for code style, and not for fixing what it finds.
Ovid/paad
Use when reviewing current branch for bugs before pushing or merging, when wanting a thorough multi-agent review of local changes, or when preparing work for human review. Not for codebase structure, not for code style, and not for fixing what it finds.
Ovid/paad
Drive and script tldraw offline canvases with an agent.
openamer/openamer
Give the agent its own inbox: send and receive email.
openamer/openamer
Manual OAuth for remote MCP servers on headless gateways.
openamer/openamer
List, auth, and call MCP servers/tools from the terminal.
openamer/openamer