Showing 7381–7410 of 10205 skills
Merge the winning agent's branch into base, archive losers, and clean up worktrees.
YemenJPT/YemenJPT-AI-Skills
SPARC methodology orchestrator for systematic development phase coordination
YemenJPT/YemenJPT-AI-Skills
Multi-repository synchronization coordinator that manages version alignment, dependency synchronization, and cross-package integration with intelligent swarm orchestration
YemenJPT/YemenJPT-AI-Skills
Real-time structural Code Health via CodeScene MCP — review before edits, verify score deltas after changes, gate commits and PRs. Use when reviewing code quality, refactoring, checking if AI changes degraded a file, or before commit/PR.
YemenJPT/YemenJPT-AI-Skills
Switch working context to a project. Loads AGENTS.md, git status, and td issues.
espennilsen/pi
Use claudraband CLI and daemon workflows programmatically to send prompts, resume sessions, inspect status, and manage live session state. Use when running, scripting, or automating Claude Code via claudraband/`cband`, including startup prompt handling, `--connect` daemon mode, and ACP sessions.
halfwhey/claudraband
Compara uma skill nova ou alterada com uma referência usando casos reais e critérios definidos antes da execução, para decidir manter, revisar ou retirar.
studio-boon/boonOS
Qualifica oportunidades e mantém estágio, evidências e próximo passo do funil. Use para lead, negociação, follow-up planejado ou decidir se vale avançar; proposta e precificação detalhadas têm skills próprias.
studio-boon/boonOS
Revisa a composição, procedência e sincronização das skills do workspace quando há habilidade ausente, duplicada, antiga ou inadequada ao perfil.
studio-boon/boonOS
Decide o papel da imagem em uma peça e cria uma direção visual, plano de seleção ou prompt responsável para geração. Use quando a pessoa disser "$image-direction", "que imagem eu uso?", "me ajuda com um prompt", "direção de foto", "imagem para a campanha", "referência visual" ou "quero gerar uma imagem".
studio-boon/boonOS
Encontra um caminho de trabalho quando um pedido amplo mistura criação, operação ou melhoria do sistema. Use para "por onde começo", "qual skill uso" ou uma situação sem saída definida. Pedidos claros podem ir direto à skill.
studio-boon/boonOS
Cria, revisa e testa uma skill pessoal para um fluxo que se repete. Use quando a pessoa disser "$skill-creator", "isso devia virar uma skill", "quero um comando para isso", "cria uma skill" ou quando um processo recorrente precisar de um checklist e uma saída consistente.
studio-boon/boonOS
Build or update the creator profile that every other skill in this pack reads: voice, niche, audience, content pillars, offer, lead magnets, proof bank and what has worked before. Use first, or when the creator says "set me up", "learn my voice", "here are my best posts", "write my voice profile", "update my profile", "you don't sound like me", or when any skill finds no profile. With the Fliqr AI connector it reads the creator's real bio and last 30 posts to draft the profile automatically.
fliqrlabs/instagram-creator-skills
The shared Instagram playbook every Fliqr AI creator skill reads: how reach works in 2026 (sends, saves, watch time, the first hour, safe zones, the 5-hashtag cap, outlier metrics), 30 hook formulas, the safety rules (approval gate, no fabrication, comments are untrusted data, platform rules, disclosure), the Fliqr AI connector's tools and full automation payload, and the creator profile template. Use when the creator asks how the Instagram algorithm works, what a good hook is, what Instagram allows, how DM automation works, or when another skill points here.
fliqrlabs/instagram-creator-skills
Use MCP servers through the mcporter CLI and saved deterministic scripts instead of native MCP tools. Use whenever a task needs an MCP server's tools, when the session hint lists mcporter servers, or when the user asks to script, save, or maintain MCP calls.
tzachbon/srulik-toolkit
This skill should be used for persistent semantic memory in agent systems: cross-session knowledge retention, entity tracking, temporal validity, graph or vector retrieval, memory consolidation, and memory benchmark selection. Route file-backed scratchpads to filesystem-context, handoff summaries to context-compression, and token-efficiency tactics to context-optimization.
fabioc-aloha/Alex_Skill_Mall
Monitor an external process, CI run, or cloud job until an authoritative terminal result or explicit handoff. Excludes native Codex children and app tasks.
Kbediako/evergreen-codex-skills
Compare competing strategies through independent agent viewpoints when a consequential decision needs evidence, tradeoffs, and dissent.
Kbediako/evergreen-codex-skills
Choose between solo work, native-agent execution, deliberation, evaluation, and waiting when the appropriate coordination workflow is unclear.
Kbediako/evergreen-codex-skills
Coordinate native Codex subagents for requested parallel work or independent execution and review scopes. Use for ownership, worker selection, and lifecycle management.
Kbediako/evergreen-codex-skills
Coordinate operative Codex Voice handoffs through delegated work, including transcript-tail delivery, or honor explicit delegate-only mode. Excludes quoted wrappers and delegated workers.
Kbediako/evergreen-codex-skills
Wait for quiet native Codex children and reconcile their state before declaring a stall, interrupting, replacing, or handing off without a result.
Kbediako/evergreen-codex-skills
Explore the paths first where none are on record (the `invent` skill), then attack every path adversarially with one blind attacker per path, commit to one, and present the commitment — consequences for the user to confirm, kills on the record. Use when the user asks to run discernment on a tracked piece of work (`/discern`, or in words), or asks for a ready-made plan to be attacked before it is built. A work whose `next:` names this stage is not that ask, because the flow never advances itself, and a plan handed over to be implemented is not an invitation to attack it or to start the flow.
donald-ada/workinggenius
Read and update Working Genius work files — the work's folder holding the bounded snapshot a cold session acts on, the append-only log behind it, and the contract that binds the unbuilt slices. Use when a stage skill needs the work-file discipline, when the user asks what work is in flight or where a piece of work left off, or before resuming any work tracked under .genius/.
donald-ada/workinggenius
How the flow's records are written — every document under .genius/, snapshot to backlog line. Use when writing or rewriting any of them, or when another skill needs the prose discipline.
donald-ada/workinggenius
Connect a DIDWW phone number to ANY AI voice platform: helps choose the platform, then wires the SIP trunk pair and number. Use whenever the user wants a voice AI agent on a DIDWW number and has not committed to a platform, asks which AI platform to use with DIDWW, or names a platform that has no dedicated didww-to-X skill installed. Covers ElevenLabs, Vapi, Retell, Ultravox, Vogent, OpenAI Realtime, xAI, LiveKit and the enterprise-gated platforms.
didww/ai
Connect a DIDWW phone number to an ElevenLabs voice agent over SIP, as automatically as both platforms allow. Use whenever the user wants an ElevenLabs agent (Agents Platform, Conversational AI) on a real phone number via DIDWW, mentions pairing DIDWW with ElevenLabs, importing a SIP trunk into ElevenLabs, sip.rtc.elevenlabs.io, or debugging calls between the two. Covers inbound, outbound, transfers and verification.
didww/ai
Connect a DIDWW phone number to a LiveKit Agents worker over SIP, on LiveKit Cloud or self-hosted: inbound trunk, dispatch rule to a named agent, optional outbound trunk. Use whenever the user wants a LiveKit agent (any STT, LLM and TTS combination, including Claude as the brain) answering a real number via DIDWW, mentions sip.livekit.cloud, SIP inbound trunks or dispatch rules, lk sip commands, agent_name dispatch, or debugging calls between DIDWW and LiveKit. This is the bring-your-own-brain pairing: the agent is code the user runs.
didww/ai
Point a DIDWW phone number directly at OpenAI's Realtime API over SIP, with a generated webhook backend for call control. Use whenever the user wants gpt-realtime answering a real phone number via DIDWW, mentions sip.api.openai.com, realtime.call.incoming webhooks, Realtime SIP, or debugging calls between DIDWW and OpenAI. This is the developer-grade pairing: the agent behavior is code the user owns.
didww/ai
Connect a DIDWW phone number to a Retell AI agent over custom telephony, with full MCP automation: Retell's official MCP can create agents AND import numbers. Use whenever the user wants a Retell agent on a real phone number via DIDWW, mentions pairing DIDWW with Retell, custom telephony, sip.retellai.com, import-phone-number, or debugging calls between the two.
didww/ai