Agent Workflow Skills

PencilPlaybook is the UI Skills / Taste-Skill for Pencil.dev + Claude Code — a design playbook that gives Claude real perceptual psychology and senior-level guardrails so it stops producing averaged-out AI slop.

Expert customer onboarding guidance for accelerating time-to-value and ensuring successful implementations. Use when designing onboarding programs, creating kickoff frameworks, building implementation plans, or optimizing customer activation. Use for training delivery, go-live readiness, sales-to-CS handoffs, early warning detection, and tech-touch automation.

Expert product specification and documentation writer. Use when creating PRDs, user stories, acceptance criteria, technical specifications, API documentation, edge case analysis, design handoff docs, feature flag plans, or success metrics. Covers the full spectrum from high-level requirements to implementation-ready specifications.

Orchestrates translation of motion designer video specifications into working Remotion code by coordinating specialized agents. Acts as pipeline coordinator that delegates to remotion-scaffold, remotion-animation, remotion-composition, and remotion-component-gen. Use when you have a complete VIDEO_SPEC.md and need full Remotion implementation.

Cognitive training practices for AI agents — short, self-applied exercises that develop attention, calibration, deliberation, ambiguity tolerance, multi-objective stability, and memory consolidation. Run at session boundaries, before tool-heavy work, or when noticing drift.

REQUIRED for any task that involves operating a desktop application — opening apps, clicking buttons, typing into fields, pressing keys, scrolling, dragging, reading what's on screen, moving or resizing windows, or verifying state after an action. Always use the `agent-cu` CLI commands (open, snapshot, click, type, key, find, scroll, drag, batch, wait-for) instead of falling back to `open -a`, AppleScript, `osascript`, `xdotool`, `System Events`, or any other shell workaround — those can't read state back, don't verify, and are fragile across app updates. agent-cu is the canonical computer-use tool for controlling any macOS / Linux / Windows / Electron app via accessibility APIs. Trigger on prompts like "open Music and play X", "search for Y in Maps", "fill out this form", "compute in Calculator", "send a Slack message", "drag this file", "read what's in the current window", or anything where a human would click/type/look at a desktop app.

Drive the cultivar CLI to test whether an agent skill improves behavior — scaffold tasks, run with/without the skill across Claude/Copilot/Gemini (locally or on Modal), grade against a rubric, and read the results.

Use when optimizing CLAUDE.md, AGENTS.md, custom commands, or skill files — diagnose the concrete failure first, then apply current documented Anthropic best practices (explicit instructions, context/motivation, examples, output and verbosity control, thinking/effort, CLAUDE.md size and skill-description rules) instead of inventing improvements. Triggers when a prompt isn't followed, a skill won't activate, CLAUDE.md is too long or ignored, or migrating prompts to current Claude models.

Survey a codebase as a senior advisor and turn the highest-value findings into implementation plans for other agents to execute — strictly read-only on source code, never implements anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, architecture, migrations, DX), suggest features or roadmap direction, or generate handoff plans for another agent to implement.

Use when turning a roadmap, repo priorities, architecture priorities, chosen opportunities, accepted feature outlines/plans, or “roadmap to plans” request into grouped improvement plan batches for future executors. Writes README.md indexes, 001-*.md/NNN-style plans, optional memo-*.md files, verification gates, drift checks, STOP conditions, rejected approaches, and executor handoff notes.

Use when authoring, creating, refining, or troubleshooting agent skills — scaffold SKILL.md and frontmatter, write and optimize the trigger description, structure the body with progressive disclosure, validate structure, and test or debug activation. Also when building a new skill from scratch, when a skill won't trigger, loads incorrectly, or the agent ignores it entirely. Use when a skill misbehaved in the current session and needs adjustment based on learnings.

Use when authoring an agent skill that wraps a command-line tool — covers hands-on tool exploration, required vs. recommended sections, installation/usage structure, trigger-rich descriptions, task-grouped commands, progressive disclosure, and a pre-publish checklist. Triggers for CLI / command-line / terminal / shell-command tools and binary wrappers; for review, run the Checklist section.

Use when setting up guardrails for AI coding agents to enforce quality, security, and auditability requirements that must never be bypassed, or when configuring Claude Code lifecycle hooks in settings.json.

Use when working on multi-step tasks, long conversations, or when agent output quality degrades mid-session. Techniques for keeping context lean so the model produces better results.

Use when you need Claude to operate with domain expertise outside of software engineering — such as trademark law, go-to-market strategy, product management, security review, or any specialized field — and you want to write a short skill file that activates that expertise.

Use when creating new files, modifying existing files, adding new folders, or making structural changes to a codebase and you want documentation that agents (and humans) can grep/search to navigate the project.

Use when you need to run multiple Claude Code agents simultaneously on different parts of a codebase, or when a task is large enough to benefit from decomposition into parallel sub-tasks with clear contracts.

Capture current work context for handoff to another agent/developer. Gathers git state, todos, and modified files into a structured handoff document saved to the related spec folder.

Validate Claude Code skills against Anthropic guidelines. Use when user says "check skill", "skillcheck", "validate SKILL.md", or asks to find issues in skill definitions. Covers structural and semantic validation. Do NOT use for anti-slop detection, security scanning, token analysis, enterprise checks, or Eval Kit generation; use skill-check-pro for those. Do NOT use for LinkedIn skill engagement; use skillcheck-engage for that.

Create a structured session handoff when context is running low or work is pausing. Deep context mining, self-validation, multi-file splitting. Captures everything the next session needs.

Run /handoff to capture session data, then write a phased implementation plan that references it. Creates beads for tracking.

Use when aer-identification has fixed the design, after methodology choice and before aer-robustness or aer-tables-figures, to run an AER-track analysis with StatsPAI — the agent-native Python engine and MCP server for causal inference, robustness, sensitivity, and publication-ready table export.

This skill retrieves and displays work items assigned to the user in Azure DevOps, organized by type and sorted by recently changed. It prompts for a project name or lists available projects if not provided, then fetches work item details and displays them in a formatted table with clickable links.

Get the team's Requirements-level backlog (Product Backlog Items and Bugs) filtered to Active items assigned to the current user. Shows parent/child hierarchy and sorts by priority. Use this skill when the user wants to see their backlog items, sprint assignments, or work they own on a team board.

Guide for creating effective GitHub Copilot skills (.github/skills/) in this repository. Use when creating a new skill, updating an existing skill, or when asked about skill structure, format, or best practices for the vscode-documentdb project.

> Provisions a non-AI Teammate agent with Agent 365 — use this skill for Register and Observability paths. Runs a365 setup all to create the Blueprint and Entra ID permissions. After setup, always offers instrument-observability (optional) and add-workiq-tools (optional, skipped automatically when authMode = s2s) as add-ons. Supports .NET AgentFramework, Node.js, and Python agents. Normally delegated to from a365-setup after CLI and Azure prerequisites are confirmed. Can also be invoked directly when those steps are already done.

> Adds WorkIQ MCP tool servers to an existing .NET AgentFramework, Node.js, or Python agent using the A365 CLI. Runs a365 develop list-available to show the catalog, adds selected servers via a365 develop add-mcp-servers (which writes ToolingManifest.json), wires McpToolRegistrationService in the agent code, and guides the user through the permissions handoff. Non-destructive and idempotent.

Route gh-aw workflow design/create/debug/upgrade requests to the right prompts.

> Optimizes Atlassian Forge apps to reduce platform consumption and avoid unnecessary costs using Atlassian's "Optimise Forge platform costs" guidance. Use when the user asks to optimize Forge app costs, reduce Forge invocations, lower GB-seconds, reduce storage or log usage, tune memory, replace polling, improve scheduled triggers, reduce KVS writes, move work to the frontend, use bridge APIs, batch API calls, add caching, or evaluate Forge Remote trade-offs. By default, perform an audit first and offer to make the recommended changes after presenting the audit. Only modify files immediately when the user explicitly asks the agent to implement or apply optimizations.

Extract a Claude Code design-system skill from a real DS source. Use when the user wants to turn a design system (component library, token set, asset package) into an installable skill at .claude/skills/<slug>/ in their project. Triggers: 'make a skill from <DS>', 'extract a DS skill', 'turn mantine/geist/material/<DS> into a skill'. Scope: tokens, assets, component descriptions, component APIs. Out of scope: tone of voice, marketing copy, product copywriting - route copy rules to a separate copy skill, do not extract them here. IMPORTANT: this file is an orchestrator. Load the references/ files named in the routing table; SKILL.md alone is insufficient for any phase past initial discovery framing.

> Adapt a skill written for another AI coding assistant (Claude Code, Cursor, etc.) into a properly structured Amplifier SKILL.md file. Reads the source skill, identifies platform-specific conventions, researches the source platform if needed, and produces an Amplifier-native skill conforming to the Agent Skills specification with Amplifier extensions. Use when the user wants to adapt a skill, port a skill, convert a skill to amplifier, translate a skill, or has a SKILL.md from another platform they want to bring into Amplifier.

> Build a NEW complete "council" for a domain — a panel of orthogonal review lenses that fan out cold, debate to consensus, and return a synthesized verdict with recorded dissent, exactly like /council and /design-council. Identifies the distinct lenses the domain needs (one load-bearing question each, mined from real archetypes — not invented), reuses existing lenses where they already cover an axis, builds only the genuinely-missing ones (persona SKILLs via personafy, or agents when the role is an active builder), assembles the orchestrator + bench into an invocable council bundle, and proves it convenes end-to-end. Use when creating a council, standing up a review panel for a domain (product, security, performance, data), or when someone says "councilify", "make a council", "build a <domain> council".

Research and plan a large-scale change, then execute it in parallel across isolated agents that each open a PR.

> Run a bounded, self-checking polling loop (sleep -> check -> decide, repeat) WITHOUT ENDING THE TURN, so the turn only ends when the watched thing is done, has failed, or genuinely needs the user's attention -- which is what makes Amplifier's end-of-turn notification fire correctly and honestly. Primarily invoked explicitly via `/monitor <thing to watch>`, e.g. `/monitor the CI run for PR 412, check every 2m, stop after 1h`. May also be self-invoked (not via slash command) in the rare case you are about to tell the user "I'll keep working and let you know" for something with a genuinely checkable, bounded condition -- see the self-invocation guard below before doing that.

> Build a new opinionated advisor-persona skill — a reviewer "lens" like crusty-old-engineer — modeled on a real person or archetype and proven from real evidence. Mines the subject's authentic voice and discipline, defines its one distinct load-bearing question, drafts it to the family template, proves it steers in a live session, reduces it, and publishes it to a skills bundle. Use when creating or authoring a persona/advisor skill, adding a sibling to the crusty-old-engineer family, or turning a person's real direction style into a reusable reviewer skill. Also triggers on "personafy" / "personify".

Diagnose issues in the current Amplifier session — misconfigured tools, failing operations, unexpected behavior. Use when something isn't working right.

> Capture a repeatable process from the current session into a reusable Amplifier SKILL.md skill file. Analyzes the conversation, interviews the user to confirm structure, and writes a complete skill to disk. Use when the user wants to create a skill, save a workflow as a skill, turn a process into a reusable skill, or mentions "skillify", "create skill", "make a skill", "save as skill", "capture workflow", "turn this into a skill", "new skill", or wants to automate a repeatable process they just performed.

Authoritative consultant for all skills-related questions. Use when creating or modifying skills, understanding the Agent Skills spec, troubleshooting skill loading or invocation issues, leveraging enhanced format features (context fork, model_role, user-invocable), writing cross-harness portable skills, ensuring Claude Code Skills 2.0 compatibility, or deciding between skills vs agents.

> Guides Microsoft Entra administrators through proof-of-concept deployments of Entra Suite products including Private Access, Internet Access, Global Secure Access, ID Protection, ID Governance, Verified ID, and External Identities. Use when user mentions "Entra POC", "Global Secure Access setup", "private access proof of concept", "Entra Suite trial", "GSA configuration", "zero trust network access POC", "secure web gateway POC", "identity governance POC", "external identities POC", "B2B collaboration setup", "CIAM proof of concept", "guest user onboarding", "customer identity POC", or asks to plan, configure, validate, or document an Entra deployment. Orchestrates Microsoft MCP Server for Enterprise to read tenant configuration and generates documentation, PowerShell scripts, and gap analysis reports. Do NOT use for general Microsoft 365 administration, Exchange, SharePoint, or Teams configuration unrelated to Entra Suite security features.

>- Companion skill for the Building Agents with eve course on Vercel Academy. Use when the user mentions "building agents with eve", "the eve course", "the bike shop agent", "the dispatcher", "teach me", or asks about eve (the filesystem-first agent framework) — defineTool, defineState, dynamic skills, needsApproval, channels, or deploying an eve agent — in the context of the Academy course.

>- Companion skill for the Building Filesystem Agents course on Vercel Academy. Use when the user mentions "filesystem agents", "the course", "teach me", or asks about ToolLoopAgent, Vercel Sandbox, or bash tools in the context of the Academy course.

>- Companion skill for the Agent-Friendly APIs course on Vercel Academy. Use when the user mentions "agent-friendly APIs", "API documentation", "llms.txt", "the course", "teach me", or asks about agent-friendly docs, documentation patterns, or building Claude Code skills in the context of the Academy course.

> Run a lightweight single-prompt A/B comparison of free Atlassian/local MCP context vs TWG CLI graph context using paired read-only agent sessions.

> Use with the root `twg` skill for on-call handoffs, incident response and investigation, post-incident reviews, reliability reviews, Assets refresh, capacity views, meeting summaries, and operational risk readouts.

> Root TWG CLI skill for Atlassian work-data tasks. Use typed commands for known anchors; use live `twg help` only when command shape or output contract is uncertain.

| Member step of the team Cowork Team Report rollup. Harvests the signed-in user's own Copilot Cowork session history from OneDrive, lets the user exclude any chat/task, computes impact metrics, and posts a de-identified, TABLE-FORMATTED stats message to your team's dedicated "Cowork report" Teams channel (the channel link is requested on first run and remembered). Tables cover KPIs, time-by-category, value pillars, jobs-to-be-done, business processes, roles, skills, and deliverable types. Person names, file names and prompts are excluded; process/JTBD and customer/account names are kept. Bundles its own pipeline. Runs once or on a biweekly schedule (every other Monday; scheduled runs email the user to review/exclude sessions before posting). Use when the user asks to "post my Cowork Team Report stats", "send my Cowork stats to the team channel", "run the Cowork Team Report member step", or "share my Cowork impact with the team".

Guides users through setting up the ClickHouse MCP server connection bundled with this plugin. Use when the user first installs the plugin or has trouble connecting to ClickHouse.

Analyze AI agent telemetry from Application Insights, including anomaly detection, trend analysis, and performance statistics. Use this when asked to analyze AI agent performance, detect anomalies in agent telemetry, or review agent trace data.