Automate Pingdom tasks via Rube MCP (Composio). Always search tools first for current schemas.
Score 70/100
Pinia official Vue state management library, type-safe and extensible. Use when defining stores, working with state/getters/actions, or implementing store patterns in Vue apps.
Score 70/100
Pinia Store Setup - Auto-activating skill for Frontend Development. Triggers on: pinia store setup, pinia store setup Part of the Frontend Development skill category.
Score 70/100
Build a low-latency, Iron Man-inspired tactical voice assistant (F.R.I.D.A.Y.) using Pipecat, Gemini, and OpenAI.
Score 70/100
Composition de pipelines de sous-agents où la sortie d'un agent alimente l'entrée du suivant. Se déclenche avec "pipeline agent", "chaîne d'agents", "agent chain", "agent…
Score 70/100
Interactive LLM inference pipeline design — elicits requirements, recommends pattern, scaffolds production-ready artifacts
Score 70/100
Analyze pipeline health, identify stalled deals, predict close probability, and suggest actions to move deals forward. Improves forecast accuracy and prevents revenue leakage.
Score 70/100
Pipeline Monitoring Setup - Auto-activating skill for Data Pipelines. Triggers on: pipeline monitoring setup, pipeline monitoring setup Part of the Data Pipelines skill category.
Score 70/100
Use when users want to install or set up the atelier-pipeline multi-agent orchestration system in their project.
Score 70/100
Use when users want to remove the atelier-pipeline multi-agent orchestration system from their project.
Score 70/100
Use when the user wants to update deal stages, values, or notes in their CRM pipeline, track pipeline velocity, or manage deal progression.
Score 70/100
Content pipeline visualization — see all content at every stage from idea to published. Track ideas, drafts, in-review, scheduled, and published states.
Score 70/100
Nautical communication style transformer that converts responses into pirate-themed language while preserving technical accuracy.
Score 70/100
Populates investment banking pitch deck templates with data from source files. Use when: user provides a PowerPoint template to fill in, user has source data (Excel/CSV) to…
Score 70/100
Création de pitch decks pour startups et projets avec structure, métriques et appel à l'action. Se déclenche avec "pitch deck", "présentation investisseur", "levée de fonds",…
Score 70/100
Produce an actual launch plan with announcement copy, channel sequence, and day-1 checklist. Use when asked to "plan a launch", "GTM strategy", "how do we announce this", "launch…
Score 70/100
Messaging framework — produce a full headline, subheadline, proof points, and CTA hierarchy for use across all surfaces.
Score 70/100
Blockchain RPC error handling, gas estimation, multi-chain config, and transaction management. Use when interacting with smart contracts, estimating gas, or managing transactions.
Score 70/100
Structure an evidence-based pivot, persevere, or stop decision using Eric Ries's Lean Startup pivot framework — evaluates current metrics against original hypotheses and scores…
Score 70/100
Pivot Table Creator - Auto-activating skill for Data Analytics. Triggers on: pivot table creator, pivot table creator Part of the Data Analytics skill category.
Score 70/100
Faithful reproduction agent that generates pixel-accurate HTML/CSS code from image mockups (PNG/JPG/screenshots) and performs visual verification.
Score 70/100
Guide de création de pixel art pour jeux et interfaces rétro. Se déclenche avec "pixel art", "sprite", "tileset", "pixel", "retro art", "8-bit", "16-bit", "Aseprite", "game art",…
Score 70/100
Specialist in pixel art creation, sprite animation, and limited palette designUse when "pixel art, sprites, sprite sheet, sprite animation, retro game art, 8-bit, 16-bit,…
Score 70/100
PixiJS v8 — fast 2D WebGL/WebGPU rendering engine. Covers Application setup, scene graph, sprites, graphics, text, assets, filters, events, and the ticker system.
Score 70/100
Hotel P&L variance analysis and financial reporting. Use when the user asks about 'P&L variance', 'budget variance', 'flash report', 'CPOR analysis', 'flow-through', 'departmental…
Score 70/100
Automate Placekey tasks via Rube MCP (Composio). Always search tools first for current schemas.
Score 70/100
Automate Placid tasks via Rube MCP (Composio). Always search tools first for current schemas.
Score 70/100
Connects to bank accounts via Plaid Link SDK and retrieves transaction data using the Plaid Transactions API.
Score 70/100
Expert patterns for Plaid API integration including Link token flows, transactions sync, identity verification, Auth for ACH, balance checks, webhook handling, and fintech…
Score 70/100
Automate Plain tasks via Rube MCP (Composio). Always search tools first for current schemas.
Score 70/100
Translates every clause of a contract into plain language at an 8th-grade reading level and flags deliberately confusing language patterns.
Score 70/100
Compare SQL model changes, preview backfills and downstream impact, and stage safer warehouse rollouts before execution.
Score 70/100
Plan-approval workflow patterns for user control over AI actions in Claude Code Waypoint Plugin. Use when planning complex changes, need user approval before execution, want to…
Score 70/100
Plan B framework — 6 environmental forces monitoring, pre-mortem 5-step process, scenario planning with auto-trigger points, Devil's Advocate on every proposal, 100-day gate…
Score 70/100
Validates implementation plans before execution — checks requirement coverage, file paths, dependencies, scope, factual accuracy
Score 70/100
Resume work from an existing plan document with full context reload. Use when the user asks to continue, resume, pick up, or keep going on a plan.
Score 70/100
Generate a structured engineering plan markdown for an idea, pre-filled with codebase facts (stack, dependencies, current critique score) from dragoon.json.
Score 70/100
Batch execution with checkpoints. Trigger: When executing plans with batched tasks.
Score 70/100
Plan a new feature with analysis, design, and implementation steps. Use when the user asks to plan a feature or run /plan-feature.
Score 70/100
计划锁定器。把修复计划、实现方案和 WP 规格锻造成 decision-complete 的可执行上游文档：真相先验、决策关死、接口对齐、测试层级一致、时序稳定。在 lead 的 Gate 1 与 Gate 2 之间，以及 task-arch 拆 WP 之前必须使用。
Score 70/100
Gate plan mode entry with permission updates so complex tasks run in a controlled, reviewable state.
Score 70/100
Plan-only mode that replicates Claude Code's built-in plan mode workflow but stops after the user approves the plan — no auto-execution.
Score 70/100
Process user annotations in a plan document and refine iteratively until approved. Use when the user asks to refine, revise, iterate on, or address comments in a plan.
Score 70/100
Have multiple specialized agents review a plan in parallel. Spawns DHH, Kieran, and code simplicity reviewers to provide diverse feedback on implementation plans.
Score 70/100
Adversarial plan review by 3 independent reviewers (Feasibility, Completeness, Scope & Alignment) before presenting to user.
Score 70/100
Verifies each critique finding from `/forge:critic-review`, then folds the verified ones back into the master plan in conversation context.
Score 70/100
Generate detailed subplans from an approved parent plan, flagging steps that can run in parallel. Use when the user asks to break down, expand, or generate subplans from a plan.
Score 70/100
Create a plan collaboratively with the user, then convert the approved plan into a GitHub issue.
Score 70/100
Update a plan document with the latest implementation status, test results, and completed steps. Use when the user asks to update, sync, mark progress on, or refresh a plan.
Score 70/100
Verify a plan or in-progress work has been fully achieved against its acceptance criteria. Use when the user asks to validate, verify, check completion, or confirm a plan is done.
Score 70/100
Read finalized specs and generate a detailed implementation plan. Updates the plans markdown with actionable steps.
Score 70/100
Plan multi-step implementation tasks to minimize context usage and maximize parallelism. Automatically applies whenever plan mode is active.
Score 70/100
Document and abandon a feature worktree with reason and lessons learned. Use when the user asks to abandon, drop, give up on, or shelve a feature/branch/worktree.
Score 70/100
Create a new git worktree for a feature branch. Use when the user asks to create a worktree, start a feature in a worktree, or branch into an isolated workspace.
Score 70/100
Merge a feature worktree back into the source worktree or branch. Use when the user asks to merge a worktree, integrate worktree changes, or land a feature back home.
Score 70/100
Plandex is an open-source terminal-based AI coding agent designed for large projects and complex tasks.
Score 70/100
À utiliser lorsque tu disposes d'une spécification ou des exigences pour une tâche complexe en plusieurs étapes, AVANT de toucher au moindre code ou fichier.
Score 70/100
中文优先：用于Plankton代码质量相关任务，帮助识别、设计、实现或验证对应工作流。English keywords: Write-time code quality enforcement using Plankton — auto-formatting, linting, and Claude-powered fixes on every file…
Score 70/100
Create comprehensive, phased implementation plans with sprints and atomic tasks. Use when user says: "make a plan", "create a plan", "plan this out", "plan the implementation",…
Score 70/100
Create, update, revise, reopen, or rescope a plan or ExecPlan using `docs/PLANS.md`. Use when an agent needs to create a plan, plan a change, update the plan with new…
Score 70/100