sharpen
Use when a Pstack task needs a stronger outcome or approach before execution while preserving an independent correctness check.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-02 00:09
Agents & models
25,477 results
show-me-your-work
Use for Pstack decision trails, unattended runs, transcript audits, or review of evidence behind completed work.
graph-engineering
Compose installed agent skills into one orchestrated multi-agent run: an agent graph where each node is a sub-agent that loads exactly one skill, edges carry structured data, and stages fan work out, adversarially verify it, and synthesize one deliverable. Claude Code calls the executable form a dynamic workflow; the pattern is Anthropic's orchestrator-workers. Use when a task needs several skills applied in parallel (multi-lens review, multi-angle audit or research, migration sweeps), when the user says graph engineering, agent graph, fan out sub-agents, or orchestrate skills, or when designing any workflow where sub-agents each own one skill. For PR review specifically use panel-review (an instance of this skill); for a single second opinion on finished work use double-check; do not use for tasks one skill handles in one context.
spec
Drives interactive requirement discovery to produce spec files. Use when the user says "spec this", "write specs", "create specs", or "run the spec skill".
aggregate-boundaries
Determine and enforce aggregate boundaries when domain entities relate to other domain entities. Use when an agent needs to create, modify, review, or…
business-logic-entry-point-repository-operations
Require repository interfaces to expose a standard set of operations with specific signatures, naming conventions, and a strict error model. Use when an agent…
domain-entity
Identify, interpret, review, or write domain entities in code. Use when an agent needs to decide whether a domain entity is defined by a stable identity that…
iso8601-millisecond-precision
Require ISO 8601 textual representations for temporal values. Use when an agent needs to format, serialize, parse, document, review, or define textual date,…
openclaw-guide
Reference and consulting skill for OpenClaw — a messaging gateway that connects AI agents to multiple communication platforms (Telegram, Discord, Slack,…
tb-best-practices
tb-best-practices — an installable skill for AI agents, published by codejunkie99/gateflow-plugin.
publish
This skill should be used when the user asks to "send message to agent X", "publish to topic", "broadcast to all agents", "notify other sessions", "tell agent…
wait
This skill should be used when the user asks to "wait for message from agent X", "block until response", "wait for handoff", "synchronize with other agents",…
three-layer-agent-stack
Use when building AI-powered products or agents, when raw model intelligence isn't enough to solve user problems, or when designing the architecture for…
google-continuous-fuzzing
Apply Google's continuous fuzzing methodology using OSS-Fuzz and ClusterFuzz. Emphasizes coverage-guided fuzzing, automated bug triage, and integration into…
notion
Read, search, update or organize Notion pages and databases using available Notion MCP tools. Use ntn for requested scripts or capabilities missing from the…
intent
Use it to establish common understanding with the user on a request.
port-daddy-cli
Multi-agent coordination via Port Daddy. Use when starting dev servers, coordinating with other agents, preventing file conflicts, salvaging dead agents' work,…
theboardroom
Convene an AI executive board of directors (CEO, CFO, COO, CLO, CISO sub-agent personas) to vet a business idea, product concept, new service offering, M&A…
prompt-engineering-patterns
Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability.
plugin-creator
Creates plugins (skills and MCPs) by guiding through the authoring process. Use when users want to create or update (1) skills that extend Claude's…
factory-conductor
Run an approved task plan unattended, from its first task to an open pull request, inside a user-approved autonomy grant. Use when the user says "run the…
retail-media-networks
This skill enables Claude to act as a specialist in Retail Media Networks. Use when a user asks for help with advertising on platforms like Amazon Advertising,…
webinars-virtual-events
This skill transforms Claude into a webinar marketing specialist following Jason Fladlien's One to Many selling methodology and Russell Brunson's Perfect…
promote-on-x
Promote a product by finding high-signal posts on X and crafting value-first replies. Uses Claude in Chrome for browser interaction and writing plugin for…