Loading...
Loading...
Found 6,710 Skills
How to write effective agent skills — what to do, what not to do, anatomy, progressive disclosure, design patterns, anti-patterns, testing, security. Read this whenever a skill (Claude Skill, Agent Skill, SKILL.md) is being created, edited, reviewed, or debugged. Use when the user says "create a skill", "new skill", "update this skill", "improve a skill", "why isn't my skill triggering", or anything else involving authoring or editing SKILL.md files.
Implement a whole backlog of tickets overnight, unattended. Give it the spec or parent issue whose build tickets you want built (or a local backlog folder); it pulls the linked tickets from the issue tracker, reads the spec and completed tickets for context, orders the open tickets by dependency, then runs one agent per ticket — each using /implement in its own git worktree, on a model matched to the ticket's difficulty, at high reasoning effort — and leaves you your chosen deliverable in the morning — a stack of reviewed branches, one integration branch, or a ready-to-review PR.
Use when asked to watch, babysit, audit, review, compare, or fix another agent's work from a Codex session ID, Claude Code session/transcript, chat/thread link, PR, branch, log, or pasted run summary. Monitor until the other agent is done or blocked, reconstruct what the user asked, inspect what the agent actually changed and verified, report gaps, and optionally make scoped fixes when the user authorizes repair.
This skill is used when users want to review an existing code segment with an Agent — examining code rationality and identifying refactoring opportunities. It is language-neutral and focuses on design-level judgments (rather than correctness/mechanical checks). By default, it provides conversational conclusions and does not modify files proactively; hierarchical reports can be generated for archiving or large-scale code inspections, and findings can be reviewed item by item if there are multiple ones. Trigger: Users say "review / refactor / check if this code is reasonable / review with me / is there any problem with this design"; after writing a batch of code continuously, users or Agents can actively ask if inspection is needed. Not applicable: Executing single-point modifications with clear instructions from users (e.g., "change data1 to user_data"), adding new features, fixing bugs, performance tuning (profile/benchmark special projects), security audits, deterministic mechanical checks like lint, rewriting, or step-by-step inquiries (explaining code).
Drive iOS Simulator and Android emulator/device screens for AI agents. Use when asked to automate a simulator or emulator, tap/swipe/type on a device, describe UI, take a screenshot, or interact with a mobile app.
Read, search, summarize, and triage AgentMail inboxes through the connected MCP server. Use for ANY request to look at, search, or process mail — even a simple 'search my inbox for X' or 'any new mail?'; the read workflow applies regardless of task size. Also use to summarize conversations, inspect attachments, manage read/unread labels, or find messages needing a reply; do not use for sending or drafting (agentmail-send-email), inbox administration (agentmail-manage-inboxes), or MCP connection setup (agentmail-mcp).
Use when explicitly invoked or when a concrete latency constraint requires minimizing wall-clock agent time without reducing accuracy.
Salesforce Data 360 metadata API mastery for production agentic use cases: metadata retrieval, semantic descriptions, field/object documentation, relationship semantics, data graph readiness, prompt/action grounding, and metadata quality scoring. TRIGGER when: the user prepares Data 360 metadata for Agentforce, AI agents, semantic search, dashboards, prompt grounding, or wants metadata descriptions and semantics improved programmatically.
Render independent questions in an Agent workflow into a local interactive form, mark recommended answers, collect optional supplementary notes for each question, save responses as portable JSON, and return the submitted results directly to the waiting Agent command. Suitable for grill-me, grill-with-docs, brainstorming, requirement clarification, configuration, planning, and any workflow requiring user confirmation or question collection; explicitly call Ask UI when a round contains more than two questions. When a user says "submitted", "done submitting", or "finished answering" during an Ask UI round, follow this skill's manual recovery path.
Guides agents through creating and safely sizing a Replay Vision scanner: choosing the scanner type (monitor/classifier/scorer/summarizer), shaping the RecordingsQuery that selects sessions, and — crucially — estimating observation volume and checking the org's monthly quota before creating, so a broad scanner doesn't exhaust the budget on its first scheduled sweep. TRIGGER when: user asks to create, set up, or configure a Replay Vision scanner, OR when you are about to call vision-scanners-create, OR when widening an existing scanner's query or sampling_rate via vision-scanners-update. DO NOT TRIGGER when: only reading scanners or observations, deleting a scanner, or running an existing scanner against a single session on demand (vision-scanners-scan-session).
Design agent-native applications where agents replace UI users as the primary actor. Use when designing MCP tools, agent-loop architectures, system prompt design, hooks policy, shared-workspace file patterns, or self-modifying agent systems.
Scan how you actually work with your coding agent and surface what to encode next. Point it at ONE run's artifacts to find what would have prevented a specific failure (the reactive loop — 'that went wrong, what should change in the AI layer?'), or at a window of session logs to find recurring patterns worth building (the proactive scan). Agent-agnostic. Outputs a shape-only HTML report. Use to evolve your system from real usage.