智能体
Agent 规划、多步流程与编排
RedTeam
danielmiessler
Adversarial analysis with 32 agents. USE WHEN red team, attack idea, counterarguments, critique, stress test. SkillSearch('redteam') for docs.
FirstPrinciples
danielmiessler
First principles analysis. USE WHEN first principles, fundamental, root cause, decompose. SkillSearch('firstprinciples') for docs.
USMetrics
danielmiessler
US economic indicators. USE WHEN GDP, inflation, unemployment, economic metrics, gas prices. SkillSearch('usmetrics') for docs.
PAIUpgrade
danielmiessler
Extract system improvements from content AND monitor external sources (Anthropic ecosystem, YouTube). USE WHEN upgrade, improve system, system upgrade, analyze for improvements, check Anthropic, Anthropic changes, new Claude features, check YouTube, new videos. SkillSearch('upgrade') for docs.
Documents
danielmiessler
Document processing. USE WHEN document, process file. SkillSearch('documents') for docs.
BeCreative
danielmiessler
Extended thinking mode. USE WHEN be creative, deep thinking, deep thinking, extended reasoning. SkillSearch('becreative') for docs.
Evals
danielmiessler
Agent evaluation framework based on Anthropic's best practices. USE WHEN eval, evaluate, test agent, benchmark, verify behavior, regression test, capability test. Includes three grader types (code-based, model-based, human), transcript capture, pass@k/pass^k metrics, and ALGORITHM integration.
Prompting
danielmiessler
Meta-prompting system for dynamic prompt generation using templates, standards, and patterns. USE WHEN meta-prompting, template generation, prompt optimization, or programmatic prompt composition.
Agents
danielmiessler
Dynamic agent composition and management system. USE WHEN user says create custom agents, spin up custom agents, specialized agents, OR asks for agent personalities, available traits, agent voices. Handles custom agent creation, personality assignment, voice mapping, and parallel agent orchestration.
Science
danielmiessler
Universal thinking and iteration engine based on the scientific method. USE WHEN user says "think about", "figure out", "try approaches", "experiment with", "test this idea", "iterate on", "improve", "optimize", OR any problem-solving that benefits from structured hypothesis-test-analyze cycles. THE meta-skill that other workflows implement.
IterativeDepth
danielmiessler
Multi-angle iterative exploration for deeper ISC extraction. USE WHEN iterative depth, deep exploration, multi-angle analysis, explore deeper, multiple perspectives on problem, examine from angles, OR when the Algorithm's OBSERVE phase needs enhanced ISC extraction.
Remotion
danielmiessler
Programmatic video creation with React. USE WHEN video, animation, motion graphics, video rendering, React video, intro video, YouTube video, TikTok video, video production, render video.
WriteStory
danielmiessler
Layered fiction writing system using Will Storr's storytelling science and rhetorical figures. USE WHEN write story, fiction, novel, short story, book, chapter, story bible, character arc, plot outline, creative writing, worldbuilding, narrative, mystery writing, dialogue, prose, series planning.
OSINT
danielmiessler
Open source intelligence gathering. USE WHEN OSINT, due diligence, background check, research person, company intel, investigate. SkillSearch('osint') for docs.
skill-authoring
knoopx
Writes effective pi skills with proper structure, concise content, and progressive disclosure. Use when creating new skills, improving existing skills, or reviewing skill quality.
daily-standup
knoopx
Generates daily standup updates from session activity and commits. Use when preparing standups, reviewing daily progress, or aggregating work across projects.
pi
knoopx
Configures pi coding agent with skills, templates, extensions, packages, and models. Use for composable development workflows, custom agents, and project-specific configurations.
self-reflect
knoopx
Reflects on the current session to identify failures, inefficiencies, and improvement opportunities. Use at session end to extract learnings.
self-improve
knoopx
Analyzes Pi sessions to discover repeating patterns and tool failures, then improves agent behavior through skills, templates, guardrails, and hooks.
create-workflow
VapiAI
Build visual conversation workflows in Vapi with nodes for conversation steps, tool execution, conditional branching, and handoffs. Use when creating structured multi-step voice interactions that need deterministic flow control beyond what a single assistant prompt provides.
dyad:multi-pr-review
CoWork-OS
Multi-agent code review system that spawns three independent Claude sub-agents to review PR diffs. Each agent receives files in different randomized order to reduce ordering bias. One agent focuses specifically on code health and maintainability. Issues are classified as high/medium/low severity (sloppy code that hurts maintainability is MEDIUM). Results are aggregated using consensus voting - only issues identified by 2+ agents where at least one rated it medium or higher severity are reported. Automatically deduplicates against existing PR comments. Always posts a summary (even if no new issues), with low priority issues mentioned in a collapsible section.
tmux-cli
pchalasani
CLI utility to communicate with other CLI Agents or Scripts in other tmux panes; use it only when user asks you to communicate with other CLI Agents or Scripts in other tmux panes.
review
ballred
Smart review router. Detects context (morning, Sunday, end of month) and launches the appropriate review workflow. Use anytime for the right review at the right time.
agent-md-refactor
pedronauck
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.