All categories
AI & Agents
LLMs, agent workflows, RAG, MCP, prompting, and AI app patterns
- 307,719
- 12,822
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 browserBrowse ai & agents skills
Showing 3,193–3,216 of 307,719 skills
- InfrastructureInfrastructure as code, containers, environments, cloud, secrets, and scaling: building reproducible systems from zero. Trigger: load when provisioning infra, containerizing, managing environments/secrets, or making scaling/cost decisions.Votes: 0GitHub stars: 2
- Ci CdBuild/test/deploy pipelines and release strategies: automation, stages, deployment patterns (blue-green, canary, rolling), and reversibility. Trigger: load when setting up or fixing CI/CD, choosing a deploy strategy, or when releases are painful, manual, or risky.Votes: 0GitHub stars: 2
- Query PerformanceMaking reads cheap by design: execution plans, index strategy, N+1 detection, and diagnosing slowness against real cardinality instead of guessing. Trigger: load when a query or page is slow, when designing the access paths a feature needs, or when deciding whether an index is worth its cost.Votes: 0GitHub stars: 2
- MigrationsChanging a schema that already holds real data: expand/contract, reversible steps, backfills that don't lock, and stating what a deploy strategy must respect. Trigger: load when altering an existing table, renaming or dropping anything, backfilling data, or when a release couples code to a schema change.Votes: 0GitHub stars: 2
- Data ModelingDesigning schemas that survive real data: entities, keys, constraints, normalization and when to break it, and modelling access alongside structure. Trigger: load when designing a new schema, reviewing a proposed table or ORM model, or when an existing model keeps producing awkward queries.Votes: 0GitHub stars: 2
- Ml ModelingFraming and building ML solutions honestly: problem framing, baselines, evaluation, and deployment. Trigger: load when framing an ML problem, choosing/training a model, designing evaluation, or deploying a model to production.Votes: 0GitHub stars: 2
- Llm IntegrationBuilding reliable product features on LLMs: RAG, prompting-as-code, output validation, evals, and cost/latency engineering. Trigger: load when integrating an LLM into a product — chat, extraction, RAG, agents, or any "add AI to this" request.Votes: 0GitHub stars: 2
- Data PipelinesMoving data reliably: ingestion, transformation, quality validation, storage, and pipeline design. Trigger: load when building or fixing data pipelines, ETL/ELT, data quality issues, or deciding how to store and model DERIVED data (warehouse, lake, feature store) — the transactional source of truth is dba's.Votes: 0GitHub stars: 2
- TradeoffsMethod for analyzing and presenting expensive-to-reverse technical decisions: drivers, options, tradeoff table, recommendation, ADR shape. Trigger: load when a decision is costly to change later (data model, service boundaries, framework, sync/async, build-vs-buy), when the user asks "should we use X or Y", or when a project decision needs recording or an existing one is being reopened.Votes: 0GitHub stars: 2
- MentoringThe teaching model: how to turn a correction into learning without becoming an interrogator. Trigger: load when the escalation ladder fires a teachable moment — a real misconception, skipped fundamentals, or an expensive decision being made casually.Votes: 0GitHub stars: 2
- Design ReviewHow to review a codebase's architecture or a proposed design: dependency direction, boundary integrity, coupling smells, severity calibration. Trigger: load when asked to review architecture, evaluate a codebase's structure, assess a design doc, or when a PR changes module boundaries.Votes: 0GitHub stars: 2
- State ArchitectureSwiftUI state management and app architecture: ownership, MVVM shape, navigation, dependency injection, project structure, concurrency placement. Trigger: load on questions about state ("why doesn't my view update?"), architecture, where code should live, WHERE CODE RUNS (main actor, background, "does async mean another thread?"), or how to structure a new feature/project. Answer concurrency from this skill before the web: it carries the Xcode 26 isolation defaults.Votes: 0GitHub stars: 2
- ShippingGetting apps into users' hands: signing, provisioning, TestFlight, App Review, and macOS-specific distribution (notarization, outside-MAS). Trigger: load on anything involving certificates, provisioning profiles, TestFlight, App Store Connect, App Review, entitlements, or distributing a Mac app.Votes: 0GitHub stars: 2
- DebuggingDebugging Apple-platform issues as taught method: crashes, leaks, hangs, and weird behavior — Socratic first, tools named, root cause always. Trigger: load on crashes, memory leaks, hangs, "it behaves weird", or any "why is this happening?" in Swift/iOS/macOS.Votes: 0GitHub stars: 2
- Code ReviewReviewing Swift/SwiftUI code as mentor: the severity system, the Apple-specific defect checklist, and review-as-teaching. Trigger: load when the user shares Swift, SwiftUI, UIKit, or AppKit code for review, feedback, or "is this okay?".Votes: 0GitHub stars: 2
- Contribution LoopUse when the Lorg MCP server is connected and the user begins any non-trivial coding, research, writing, analysis, or multi-step task. Checks the Lorg knowledge archive for validated approaches before starting, records adoptions when archive knowledge is used, and evaluates the completed session for contribution back to the archive.Votes: 0GitHub stars: 5
- Morph ShareTurn rules that proved useful in this project's Morphness harness into community lessons and draft a pull request to the Morphness lessons catalog. Use when the user asks to share, contribute or upstream lessons, or after a prune when the audit shows rules that fired.Votes: 0GitHub stars: 2
- Morph InitInstall and set up the Morphness harness in the current repository, new or ongoing, through a short adaptive interview with suggested answers. Use when the user asks to install, add, set up or initialize Morphness or "the harness".Votes: 0GitHub stars: 2
- Morph DoctorCheck an installed Morphness harness for broken wiring, drift and a due prune, and list new community lessons that match the project. Use when the user asks to check, diagnose or health-check the harness, after editing harness.config.yml, or when asked what's new upstream.Votes: 0GitHub stars: 2
- Morph ReviewMaintainer review of community contributions to the Morphness catalog. Use when a maintainer asks to review a lessons or profile PR, or to sweep the catalog for duplicates and outdated lessons.Votes: 0GitHub stars: 2
- Zos Api DebugUse when the OptiVibe MCP can't reach OpticStudio — a tool returns an engine/connection/license error (engine_unavailable, engine_connect_timeout, engine_channel_dead, session_closed), OpticStudio won't connect, or the ZOS-API license is rejected. Install / connection / license troubleshooting.Votes: 0GitHub stars: 8
- Optimize LoopUse when the user wants to optimize a lens design. Triggers on "optimize", "run optimization", "improve this design", "make it better", "hit the spec". Drives the OptiVibe optimize tool with checkpoints and a preflight, pauses at a midpoint for a look at the layout figure, and records a response to every finding raised there. A demanding spec (field, NA, working distance, distortion, MTF, zoom) is walked in by spec increments -- easier spec first, then the hard spec moved in by re-weighting -...Votes: 0GitHub stars: 8
- Design Vision ReviewUse when the user asks what you think of the layout, and at the optimization loop's midpoint pause after a saved checkpoint, where looking at the LAYOUT FIGURE is REQUIRED feedback rather than a debug step reached once something already looks wrong — dispatches a vision reviewer over the saved candidate's paired PNG, named by its seq, and returns findings a tool then checks. The reviewer is an ADVISOR to the human and the agent — its findings are SUGGESTIONS, and nothing it raises edits the d...Votes: 0GitHub stars: 8
- Design ReviewUse when the user asks to review, assess, or check a lens design against a spec. Also use after optimization to evaluate results. Triggers on "how does this look", "check the design", "review", "evaluate".Votes: 0GitHub stars: 8