agent-harness-orchestration
Coordinate multiple coding agents in shared repos with task packets, worktree or branch isolation, path ownership, verification loops, and PR or CI…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-03 00:11
Agents & models
25,535 results
fogg-behavior-model
Diagnose behavior change with B=MAP motivation, ability, and prompt. Use when users do not take a target action, onboarding stalls, conversion drops, feature…
agent-stop-conditions
Use when designing, reviewing or debugging the limits of an autonomous agent run - a headless claude -p job, an Agent SDK loop, a scheduled or unattended agent…
run-receipt
Use when an agent run completes, fails, or is being audited. A multi-step run is not done until a receipt exists showing what ran, what failed, and what was…
env-capability-discovery
Cross-platform environment capability discovery for workflow skills: scan once at startup for available enhancement skills/agents (debugging, web research,…
stitch-ui-guide
UED guidelines, visual vocabulary, and prompt structure for Stitch. Use when the user asks about layout/style terms, device constraints, or when…
create-plan-flow
Goal-scoped plan write: one plans/NN-slug.md under .agents/temp/goals/<goal-id>/ only after grill shared understanding. Looked up by /goal. Not for…
grill-me-flow
Goal-scoped grill: hard gate before plans under .agents/temp/goals/<goal-id>/. Pulls taste-flow, architecture-flow, and design-flow (if UI) into one batched…
implement-flow
Internal implement: frontier workers from plans/INDEX under .agents/temp/goals/<goal-id>/. Looked up by /goal only. Never for users or auto-invocation.
orchestrate-flow
Internal conductor: Task subagents do the labor, every worker bound to .agents/temp/goals/<goal-id>/ and a specific plans/NN file. Workers return Progress…
split-task-flow
Internal split: turn work into plans/INDEX rows under .agents/temp/goals/<goal-id>/. Looked up by /goal. Never for users or auto-invocation.
finalize
Finalize the current feature branch by running the `simplify`, `strict-quality-review`, and `/okf update` passes in order, each through its own subagent,…
package-automq-green
Provision a three-node AutoMQ cluster with Kafka-compatible brokers backed by Cloudflare R2, AWS S3, Google Cloud Storage, or OCI Object Storage, behind a…
dotagents
Manage agent skill dependencies with dotagents. Use when asked to "add a skill", "install skills", "remove a skill", "update skills", "dotagents init",…
batch-grill-me
A relentless interview that asks every frontier question at once, round by round.
glean-plugin-checklist
Use when creating, adding, or modifying plugins in this Glean Claude Plugins marketplace repository. Triggers on "create plugin", "add plugin", "new plugin",…
agentic-review
Orchestrate repository-aware code review after `setup-agentic-repository` by deriving module specialists from `AGENTS.md` + `CONTEXT.md`/`CONTEXT-MAP.md`,…
github-agentic-workflows
Master GitHub Agentic Workflows (gh-aw) - AI-powered repository automation with safe outputs, sandboxed execution, and multi-engine support
mcp-gateway-security
MCP gateway security patterns, token management, request validation, and audit logging for MCP communications
mcp-server-development
Model Context Protocol server development, MCP tool patterns, MCP configuration best practices, GitHub MCP integration
correct
Use when the human wants the mistakes agents keep repeating fixed for good. Works the KB corrections register: fixes each recurring class at the strongest…
shared-workspace
Use when a workspace has changes from other agents: safe orientation, preserving unfamiliar files.
methodology-skill-creator
Create one focused methodology SKILL.md from a completed methodology-selector contract. Use when a catalog method should become reusable agent instructions for…
deep-solve
Multi-stage problem solving via DeepTutor (plan → reason → write).