AI & Agents

LLMs, agent workflows, RAG, MCP, prompting, and AI app patterns

skills in category: 299,177
pages available: 12,466

Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.

Open in full browser

Browse ai & agents skills

Showing 217–240 of 299,177 skills

PrototypeAThrowaway code that answers a design question before real implementation — slots between /orc:plan and /orc:start. Use when feeling out whether logic, a state machine, or a data shape holds up, or when comparing radically different UI variants on one route before committing to a design.ai-agentspythongitVotes: 0GitHub stars: 6
Prd WritingAAuthor Product Requirements Documents (PRDs) from scratch — interview-driven, templated, published to docs/prds/NNNN-*.md. Use for "write a PRD for X", an unsettled new feature, or /orc:prd.ai-agentsgogitVotes: 0GitHub stars: 6
Postmortem WritingAAuthor blameless incident postmortems — timeline, root cause(s), contributing factors, action items. Use after a production incident (outage, data loss, security event, regression) or a near-miss.ai-agentsgodebuggingVotes: 0GitHub stars: 6
Postgresql Table DesignADesign or review a PostgreSQL-specific schema: data types, indexing, constraints, partitioning, RLS, performance patterns, and advanced features. Use when modeling or auditing PG tables.ai-agentsgosqlVotes: 0GitHub stars: 6
Postgresql OptimizationAWrite or review PostgreSQL-specific SQL: JSONB, arrays, custom/range/geometric types, indexing, full-text search, window functions, extensions, and RLS. Use for PG-unique features and code review.ai-agentsgosqlVotes: 0GitHub stars: 6
Next Best PracticesANext.js best practices. Use when writing, reviewing, or refactoring Next.js code — App Router routing, RSC/server-client boundaries, data fetching, route handlers, metadata, image/font optimization.ai-agentsgoreactVotes: 0GitHub stars: 6
Nestjs Best PracticesANestJS best practices and architecture patterns for production apps. Use when writing, reviewing, or refactoring NestJS code — modules, dependency injection, security, and performance.ai-agentsgotestingVotes: 0GitHub stars: 6
Mobile Ios DesignAiOS Human Interface Guidelines and SwiftUI patterns for native apps. Use when designing iOS interfaces, building SwiftUI views, or aligning apps with Apple's design principles.ai-agentsswiftperformanceVotes: 0GitHub stars: 6
Jira HierarchyAThe Jira backlog contract — Epic-as-micro-PRD, Stories, concurrency-sliced Tasks, and the mandatory child-ticket template. Use when creating or restructuring Jira epics, stories, or task breakdowns, or when enforcing ticket structure — /orc:jira-breakdown and orc-jira-architect are built on it.ai-agentsVotes: 0GitHub stars: 6
Jira CliAAtlassian CLI (acli) reference for Jira work items — create, sub-task, link, view, JQL search, transition. Use to file/move/link a Jira ticket from the terminal or when /orc:jira is invoked.ai-agentsnodeVotes: 0GitHub stars: 6
Inline ReviewAPost a real GitHub PR review with line-anchored inline comments; invoked by /orc:code-review after findings. For commenting on your OWN diff, prefer the bundled /code-review --comment.ai-agentsrustgoVotes: 0GitHub stars: 6
Improve Codebase ArchitectureAFind architecture-deepening opportunities in a codebase. Use when the user wants to improve architecture, find refactors, consolidate coupled modules, or make a codebase more testable and AI-navigable.ai-agentsgonodeVotes: 0GitHub stars: 6
HandoffACompact the current conversation into a redacted handoff document, saved to the OS temp dir, that a fresh agent in another session or tool can pick up — /orc:resume is the counterpart for resuming in-repo orc state.ai-agentsgitapiVotes: 0GitHub stars: 6
GrillingARound-based interview engine under orc's grill entry points (orc:grill-me, /orc:plan --grill, /orc:rfc --grill, /orc:flow medium+ scope). Use when stress-testing a plan or design decision-by-decision, or when a session must end with nothing left silently assumed.ai-agentstestinggitVotes: 0GitHub stars: 6
Grill With DocsAGrill a plan or design while writing the docs as you go — the interview plus a live glossary (CONTEXT.md) and ADRs captured the moment decisions land.ai-agentsgogitVotes: 0GitHub stars: 6
Grill MeAA relentless decision-by-decision interview to sharpen a plan or design until reaching shared understanding.ai-agentsgitVotes: 0GitHub stars: 6
Git CommitAExecute git commit with conventional-commit analysis, intelligent staging, and message generation from the diff. Use when the user asks to commit changes, create a git commit, or mentions /commit.ai-agentsgobashVotes: 0GitHub stars: 6
Git Advanced WorkflowsAAdvanced Git workflows - rebase, cherry-pick, bisect, worktrees, reflog - for clean history and recovery. Use when managing complex histories, collaborating on branches, or troubleshooting a repo.ai-agentsgitVotes: 0GitHub stars: 6
GatesAThe canonical AskUserQuestion conventions for every orc gate — class-tagged header chips, Recommended-first options, side-by-side `preview` for preview-then-confirm, multiSelect chunking, notes as the rewrite channel, and the --auto ladder. Use when about to render an orc gate.ai-agentsgoVotes: 0GitHub stars: 6
Flow PhasesAPer-phase playbooks for /orc:flow Phases 2–9, loaded one at a time as the flow reaches each phase. Use only from /orc:flow — Read the single references/PHASE-N-*.md for the phase being entered, never all of them.ai-agentsVotes: 0GitHub stars: 6
Finishing A Development BranchAGuide the completion of a development branch by presenting structured options for merge, PR, or cleanup. Use when implementation is complete, all tests pass, and you need to decide how to integrate the work.ai-agentsgobashVotes: 0GitHub stars: 6
ExplainerABuild the narrated what-was-made walkthrough for a QA packet: script from plan + acceptance, demo pass, segments.json, animate graphics, kokoro narration, orc-explain assemble. Use from /orc:explain and the flow explainer gate. Not for QA itself.ai-agentsgogitVotes: 0GitHub stars: 6
Executing PlansAExecute a written implementation plan batch-by-batch — load it, review critically, implement task by task, and stop for review between batches. Use when you have a written implementation plan to execute in a separate session with review checkpoints.ai-agentsgitapiVotes: 0GitHub stars: 6
Evidence PublishADeliver a QA/evidence packet to a tracker or keep it local, behind an always-ask preview gate. Protocol for /orc:qa Phase 6, /orc:evidence, and any evidence-delivery step.ai-agentsgitapiVotes: 0GitHub stars: 6