AI & ML

crisandrews Skill

Run diagnostic checks on the agent workspace. Triggers on /agent:doctor, "diagnóstico", "diagnostico", "doctor", "health check", "agent health", "checkup", "revisar agente", "agent broken", "fix agent", "revisa el agente".

crisandrews Skill

Import an existing OpenClaw agent from its workspace directory into the current project. Triggers on /agent:import, "importar agente", "traer de openclaw", "import agent".

crisandrews Skill

Show agent runtime status — identity, model, context, memory, crons, voice. Works from CLI or messaging. Triggers on /status, /agent:status, "status del agente", "cómo estás técnicamente".

crisandrews Skill

Check for new versions of Claude Code and ClawCode, and print safe update commands. Triggers on /agent:update, /update, "check for updates", "are there updates", "buscar actualizaciones".

crisandrews Skill

Show the sender's info — their ID, the channel they're using, and which agent they're talking to. Triggers on /whoami, /id, /quien, "quién soy", "who am I".

crisandrews Skill

Flush important session context to daily log (manual memory flush). Does NOT invoke native /compact. Triggers on /compact, /agent:compact, /flush, "guarda memoria", "flush".

crisandrews Skill

Run the agent as an always-on background service (launchd on macOS, systemd on Linux). Triggers on /agent:service, /agent:service install, /agent:service status, /agent:service uninstall, /agent:service logs, "always-on", "background service", "correr 24/7", "run as daemon", "launchd", "systemd".

crisandrews Skill

Show messaging channel status (WhatsApp, Telegram, Discord, iMessage, Slack, Fakechat) and the launch command to load them. Triggers on /agent:channels, /agent:channels list, /agent:channels status, /agent:channels launch, "ver canales", "estado de canales", "cómo lanzo con whatsapp", "channel status", "messaging status".

crisandrews Skill

Configure agent settings — memory backend (builtin/QMD), search mode, temporal decay, citations. Triggers on /agent:settings, "configurar agente", "agent settings", "memory settings", "setup QMD", "configurar QMD", "configurar memoria".

crisandrews Skill

Run agent heartbeat — periodic checks, memory consolidation, proactive work. Triggers on /agent:heartbeat, "heartbeat", "heartbeat check", "periodic check", "consolidar memoria".

crisandrews Skill

Set up a messaging channel (WhatsApp, Telegram, Discord, iMessage, Slack) to reach this agent from outside Claude Code. Triggers on /agent:messaging, "configurar whatsapp", "setup messaging", "conectar telegram", "agregar canal".

crisandrews Skill

Install, list, and remove community skills from GitHub or local paths. Triggers on /agent:skill, /agent:skill install, /agent:skill list, /agent:skill remove, "instalar skill", "listar skills", "remover skill", "eliminar skill", "agregar skill", "install skill from github".

cypher0n3 Bundle

Prompt me with questions, one at a time, until we have a shared understanding. Use this skill when a decision, plan, or spec is too ambiguous to act on without guessing.

cypher0n3 Bundle

Quick prompt to indicate that the provided info was produced by another agent for consideration. Invoke only when explicitly called by user.

cypher0n3 Bundle

Update Cursor plan and agent todo items. Invoke only when explicitly called by user.

tiangong-lca Bundle

Execute and troubleshoot Supabase edge function `flow_hybrid_search`, which rewrites flow descriptions and calls `hybrid_search_flows` with optional filters. Use when validating flow query/filter behavior, tuning retrieval prompts, or debugging auth, embedding, and RPC failures.

tiangong-lca Bundle

Use TianGong Foundry to import an external LCA dataset package or develop TIDAS data from source evidence, continue an existing Foundry task, resolve its semantic work items, and complete authorized writes with verified readback.

tiangong-lca Bundle

Execute and troubleshoot Supabase edge function `process_hybrid_search`, which rewrites process descriptions and calls `hybrid_search_processes` with optional filters. Use when validating process query/filter behavior, tuning retrieval prompts, or debugging auth, embedding, and RPC failures.

tiangong-lca Bundle

Orchestrate current-user RLS-scoped TianGong dataset cleanup, delete, retirement, and redo workflows through CLI maintenance plans, explicit approvals, and readback verification.

tiangong-lca Bundle

Execute and troubleshoot Supabase edge function `lifecyclemodel_hybrid_search`, which rewrites lifecycle model descriptions and calls `hybrid_search_lifecyclemodels` with optional filters. Use when validating lifecycle-model query/filter behavior, tuning retrieval prompts, or debugging auth, embedding, and RPC failures.

tiangong-lca Bundle

Review and repair current-account TianGong dataset snapshots across flow, process, and lifecyclemodel rows through public CLI commands only. Use when a task needs local schema validation, deterministic reference rewrites, lifecyclemodel save-draft handoff, lifecyclemodel graph audit, and artifact-first stop rules for account-owned dataset governance.

tiangong-lca Bundle

Orchestrate structured external LCA packages such as BAFU or USLCI into TIDAS candidate rows through CLI conversion, queue state, child skills, deterministic gates, and readback-safe publish handoff.

tiangong-lca Bundle

Orchestrate evidence-driven TianGong TIDAS data creation or update from PDFs, Word files, web pages, URLs, APIs, databases, reports, or scientific literature.

tiangong-lca Bundle

Plan and orchestrate recursive LCA assembly across `process-automated-builder`, `lifecyclemodel-automated-builder`, and `lifecyclemodel-resulting-process-builder`, including reuse decisions, submodel builds, resulting-process construction, graph manifests, and lineage manifests. Use when a product system request spans multiple model/process layers and needs a reproducible local orchestration run before any publish handoff.

tiangong-lca Bundle

Build deterministic local resulting-process datasets from an existing lifecycle model, plus lifecyclemodel/resulting-process relation metadata and publish handoff artifacts. Use when a lifecycle model already exists and you need a formal aggregated resulting `processDataSet` without routing through `process-automated-builder`.

is-noname Skill

Compact the current conversation into a handoff document for another agent to pick up.

is-noname Bundle

Prueft Skills und Workflows auf Idiotensicherheit — findet Stellen, an denen ein schwaches Modell abweichen kann, und liefert konkrete Korrekturvorschlaege. Use when ein Skill, ein Prompt oder ein Workflow reproduzierbar und fremdmodell-tauglich werden soll.

is-noname Skill

Checks and updates the global agent conventions (tickets.md, doc-ids.md, design-tokens.md, init_tickets.sh, ticket-mover hook) deployed in agent dirs (~/.claude etc.) and the per-project ticket infrastructure (scripts/tickets.sh, PROTOCOL.md, .counter) against the ai-SKILL-set repo. Use when the user wants to update, refresh, sync, or drift-check their global conventions/tickets/doc-ids setup or their projects' ticket setup.

is-noname Bundle

REST-Client für die AgentMail-API (agentmail.to) — Postfach, Nachrichten und Drafts per Python ansprechen, inkl. Webhook-Empfang und CLI-Review-Flow für Drafts. Nutzen wenn ein Agent E-Mails über AgentMail lesen, ein Draft anlegen, Labels auf Nachrichten setzen oder eingehende Mails per Webhook verarbeiten soll. Kein autonomes Senden — Drafts durchlaufen `draft_review.py` als Human-in-the-loop-Review.

zenithjuno Bundle

Publish any update, addition, repair, rename, or removal of a user-managed Codex/Claude skill from the local `~/.codex/skills` source checkout to its GitHub mirror. Use whenever an agent changes a skill folder or asks to commit, push, install, sync, release, or make a skill available to other sessions. Enforce scoped preflight, verification, commit/push, and clean local-mirror proof through the shared release helper.

zenithjuno Bundle

A rigorous, coding-first design-before-build process for Mode L substantial, high-risk, ambiguous, multi-system, or multi-session work. The agent grills the user with recommendation-backed questions, locks decisions in a live ledger, produces a BLUEPRINT (what) and CONSTRUCTION_PLAN (how and tests), and refuses to build before explicit approval. For coding it establishes bounded-context BUILD-CONTROL, exact path scopes, current contract indexes, AGENTS.md routing, checkpoints, and cold audit logs. Use when task-scoping routes work to L, when costly product decisions remain, or when the user explicitly asks "grill me", "plan this first", "spec this", "grill-to-build", or "deep-grill-to-build". Do not impose the full artifact set on clear one-session S/M coding tasks.

zenithjuno Bundle

Audit an answer key (exam solutions, model answers, a generated question bank) for correctness by BLIND re-solving — an independent solver answers each item WITHOUT seeing the provided key, then diffs against it, marking agreements as pass and disagreements as flags for a human to adjudicate. Use this WHENEVER you need to verify or QA answers/solutions produced by someone else (another AI such as Codex, a textbook, a teacher, an auto-generator) and correctness matters — to catch wrong keys, contradictory questions, no-valid-option items, and duplicate/typo choices before learners or users see them. Triggers include: "ตรวจเฉลย", "audit answer key", "verify these solutions", "blind check", "cross-check the answers", "QA this question bank", "is this answer key correct", and any producer↔checker AI workflow. Roles are swappable — the same process works whether THIS agent produced the answers or is the one checking them. Prefer this over ad-hoc "just re-grade it" because the blind discipline is what prevents anch

iberi22 Skill

Jules is SWAL's autonomous coding agent from Google. Use via Jules CLI, GitHub issues with `jules` label, or EPIC orchestration. Includes Anti-Conflict Protocol, Wave delegation, and auto-merge patterns.

iberi22 Skill

Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (for example spawn/run Codex or Claude Code in a Discord thread; use sessions_spawn with runtime:"acp"), or any work in ~/clawd workspace (never spawn agents here). Claude Code: use --print --permission-mode bypassPermissions (no PTY). Codex/Pi/OpenCode: pty:true required.

nyuway-cybersecurity Skill

Install helper commands for future agent sessions.

polypoint Bundle

Use when the user wants to create Playwright end-to-end tests from an annotated codegen recording. The user records a flow with `npx playwright codegen`, gives the test a descriptive name, adds `// assert that` comments, and this skill enriches it with resilient selectors via Chrome exploration and generates Page Object Model tests.