Explore skills
Showing 22561–22590 of 32730 skills
Lifecycle SOP for **per-model prompt artifacts** — the compiled prompts, instructions, few-shot demos, edit-format pins, and embedding-bound indices that change behavior when the underlying LM, dataset, or framework version changes. Activate when adopting compiled prompts (DSPy, GEPA, BootstrapFewShot output), when supporting multiple LMs in production, when a provider deprecates a model snapshot, or when a framework deprecates a config surface (LlamaIndex `ServiceContext` → `Settings`, Aider edit-format defaults). Do NOT activate for one-off raw prompt edits or for truly model-agnostic system prompts that have been swap-tested. Search keywords: prompt portability, model swap, recompile prompt, model deprecation, prompt per model, prompt breaks on new model, version compiled prompts.
agentsope/SkillAlchemy
Stars: 483Claude CodeCodexThe compile-readiness gate for prompt auto-optimization. Decide whether you have earned the right to run an optimizer (DSPy MIPROv2 / GEPA / BootstrapFewShot) before spending compute. Two preconditions only — a real metric, and enough examples for the optimizer you picked. Garbage metric in, garbage prompt out. Pick the optimizer by data scale; GEPA inverts the scale assumption (~10 examples + textual feedback).
agentsope/SkillAlchemy
Stars: 483Claude CodeCodexTool skill — the *first move* in any LM-debugging session: dump the actual rendered prompt the framework sent to the model, before changing anything else. Activate when an LM call produced an unexpected output (wrong answer, schema violation, refusal, truncation, cost spike, latency spike, infinite loop, "model got dumber after upgrade"). The skill enforces a 30-second inspect step BEFORE any prompt edit, model swap, retry, or temperature tweak. Cross-framework cheat sheet: DSPy `inspect_history`, LangGraph `get_state_history`, CrewAI `step_callback`, LangChain `set_debug`/`set_verbose`, Aider `/diff`+`--verbose`, raw OpenAI/Anthropic via `OPENAI_LOG=debug`/`ANTHROPIC_LOG=debug` or HTTPX event hooks. Do NOT activate for first-time prompt authoring, exploratory prompt design, or non-LM bugs.
agentsope/SkillAlchemy
Stars: 483Claude CodeCodexRoutes heterogeneous queries to the appropriate index, tool, or answering engine before retrieval. Use when one endpoint serves multiple handlers, such as summary, vector retrieval, text-to-SQL, or tools, and query types require different paths. Covers LLM, semantic, and rule-based routers, confidence thresholds, fallbacks, and framework mappings. Do not use when one handler serves all queries or branching is fixed.
agentsope/SkillAlchemy
Stars: 483Claude CodeCodexBuild a held-out eval set, run it on every prompt/model change, and block regressions in CI. An LM change is a code change — gate it with a test suite (eval set + metric + threshold). Cross-framework SOP not surfaced by any single base skill.
agentsope/SkillAlchemy
Stars: 483Claude CodeCodexSymbol-level code context for LLM coder-agents: tree-sitter extracts symbols, PageRank ranks them over the cross-file reference graph, and the top class/function signatures are fed to the LLM as a token-budgeted read-only map (not RAG, no vector index, human-auditable). Use when an agent must locate the right files in a large/multi-file repo, when builds/refreshes/scopes a repo-map, or when "model edits the wrong file" needs fixing.
agentsope/SkillAlchemy
Stars: 483Claude CodeCodexA 5-minute gate the coder runs at project kickoff (and again whenever the repo shape changes). Classifies the workspace into Greenfield / Brownfield-large / Mid-size-familiar / Library-SDK, then maps the state to an agent strategy (autonomy, context primitive, tool choice). Use BEFORE picking Cursor vs Claude Code vs Aider, BEFORE turning on repo-map, BEFORE writing the first prompt. Skip only if the same repo was gated within the last day and nothing changed. Search keywords: greenfield vs brownfield, new project vs existing codebase, project setup strategy, legacy codebase agent, where to start a coding agent.
agentsope/SkillAlchemy
Stars: 483Claude CodeCodexAdds and tunes a reranker stage for RAG using the retrieve-wide, rerank-narrow pattern. Use when relevant documents appear in the initial top-N but are buried by noise, top-1 precision or MRR is low despite adequate recall, or too many marginal chunks consume context. Covers cross-encoder, API, and local rerankers; N-to-k selection; and latency/cost tradeoffs. Do not use when retrieval recall itself is failing.
agentsope/SkillAlchemy
Stars: 483Claude CodeCodexProject-kickoff rubric for the self-host vs managed-cloud decision — when is running your own inference engine / LLM platform worth the ops cost vs paying per-token for a managed API? Decide on two axes — VOLUME (a cost-crossover slider) and COMPLIANCE (a hard gate). Use at kickoff when choosing where to run inference, or when cost / data-residency pressure forces a re-evaluation.
agentsope/SkillAlchemy
Stars: 483Claude CodeCodexDecision protocol for managing the context/session state of an AI coding tool: when to /clear, when to keep context, and how to detect "context bleed" — the failure mode where stale conversation history biases the model against the current task. Surfaces a discipline that Aider (/clear), Claude Code (/clear), CrewAI (memory=False, re-instantiate), and LangGraph (new thread_id, subgraph isolation) all encode separately but none name as a skill.
agentsope/SkillAlchemy
Stars: 483Claude CodeCodexDecision rubric for promoting a prose prompt into a typed DSPy Signature. This is an ENHANCE overlay on top of the [[dspy]] library skill: it does NOT teach DSPy syntax — it answers the coder-agent decision "when do I stop hand-writing a prompt string and declare it as a `dspy.Signature`, and how do I name/describe its fields so the optimizer and the calling code both get a clean contract." Activate when: a prompt string grows past ~50 lines; the LM output is consumed by code (parsed, branched on, stored) rather than read by a human; the same prompt is reused across >1 call site; or a teammate asks "should this be a Signature?". Do NOT activate for one-shot throwaway prompts, or for HOW-TO questions about DSPy modules /optimizers/compile — defer those to the [[dspy]] skill and the [[agentsop-dspy]] workflow skill. Search keywords: typed prompt, structured prompt, DSPy Signature, prompt as a function, prompt contract, when to formalize a prompt.
agentsope/SkillAlchemy
Stars: 483Claude CodeCodexTool skill for declaring reducers on LangGraph state keys so parallel writes merge instead of crashing. Activates whenever a coder agent designs a StateGraph with parallel branches, fan-out via Send, multi-agent topologies, or whenever a run raises `InvalidUpdateError: At key '<k>': Can receive only one value per step`. Encodes the rule "every state key is single-writer or has a reducer — nothing in between."
agentsope/SkillAlchemy
Stars: 483Claude CodeCodexEnhancement-overlay decision protocol for STREAMING the output of long-running LLM / agent runs from the *backend*, not just wiring a typing animation in the UI. Activates when a coder agent must stream final tokens to a chat client, surface intermediate agent steps (which tool, which node, partial reasoning), emit custom tool-progress events, choose a transport (SSE vs WebSocket), or decide what to do when the client disconnects mid-stream. The langchain / langgraph skills mention stream modes but stop at "you can stream"; this skill encodes *what to stream, over what transport, and how to fail safely*.
agentsope/SkillAlchemy
Stars: 483Claude CodeCodexDecide where to enforce structured LM output (constrain at decode time with Outlines vs validate-and-retry with Instructor vs grammar with Guidance) and which failure stance to take (Assert/hard-fail vs Suggest/soft-retry). Use when an LM's output is parsed or typed by downstream code and you must pick one enforcement library plus its failure handling, when malformed output is burning tokens on retries, or when choosing between decode-time vs validation-time constraints for local vs API models.
agentsope/SkillAlchemy
Stars: 483Claude CodeCodexDecision protocol for wiring a verify-then-fix loop around a code-editing LLM agent. The agent edits → runs lint/test → reads the output → fixes → re-runs, bounded by an iteration cap and an escalation rule. Activates whenever a coder agent has a verifiable success criterion (exit code, type-checker output, failing assertion) and the user wants the agent to converge to "green" on its own. Framework-agnostic — wraps Aider's `--auto-lint`/`--auto-test`, an OpenHands SWE-Bench loop, a manual LangGraph cycle, or Claude Code's bash tool just the same.
agentsope/SkillAlchemy
Stars: 483Claude CodeCodexEnhancement overlay for multi-agent / tool-using coder agents. Encodes the per-agent tool- scoping discipline that role-based frameworks (CrewAI, LangChain) document only as a passing best-practice: which agent gets which tool, and why blanket-sharing every tool to every agent is a correctness and blast-radius risk. Activates when an agent system has tools AND there is more than one agent (or one agent holding many tools). Treat a tool as a capability grant; scope by least-privilege. ENHANCE overlay — read alongside [[crewai]], [[agentsop-http-tool-wrapping]], [[agentsop-llm-tool-idempotency]]. Search keywords: which tools per agent, least-privilege agent, agent tool access, tool permissions, limit agent tools, scope tools to roles.overlay_type: enhancement
agentsope/SkillAlchemy
Stars: 483Claude CodeCodexSOP for distilling reusable semantic operators (data-science operation skills) from agent execution trajectories: read action/observation traces, classify per-task failures, bind data-semantic constraints (input semantics / operation decision / output constraints / validation), and feed bounded edits back through an optimizer such as SkillOpt. Use when mining agent runs for cross-task operation knowledge, when a data-science skill keeps failing on the same operation family (join cardinality, group granularity, unit, time alignment), or when wiring trajectory history into a skill optimizer without polluting the skill body.
agentsope/SkillAlchemy
Stars: 483Claude CodeCodexDecision SOP for serving LLMs with vLLM. Covers PagedAttention mental model, quantization/parallelism/batching tradeoffs, OOM triage, and when NOT to use vLLM. Activates when a coder-agent is choosing or tuning an inference engine, debugging vLLM throughput/latency/OOM, or comparing vLLM against TGI/SGLang/TensorRT-LLM/llama.cpp.
agentsope/SkillAlchemy
Stars: 483Claude CodeCodexDirect and implement programmatic videos from a natural-language sentence: brief, shots, style, timeline, assets, engine-specific coding prompts, draft, review and repair. Use when asked to make a video, product launch, explainer, Reel/Short, kinetic typography or docs-to-video with HyperFrames, Remotion or Motion Canvas, or to improve an existing code-video project. 一句话视频制作与导演工作流。
agentsope/SkillAlchemy
Stars: 483Claude CodeCodexLEAP builds skills through two pipelines: Branch A distills a skill from raw data, while Branch B combines multiple skills into one. It is called by the main SkillAlchemy workflow. Use when SkillAlchemy requires distillation or fusion.
agentsope/SkillAlchemy
Stars: 483Claude CodeCodexLens — Add a cognitive lens to any problem. It accepts a task description and produces an enhanced description that surfaces hidden dimensions, prerequisites, and lines of inquiry—the things you do not know you do not know. Use when the user asks to brainstorm, analyze, generate a skill, distill, or fuse, or when the input is too simple and needs to be expanded.
agentsope/SkillAlchemy
Stars: 483Claude CodeCodexRead a real .pptx using text extraction, OOXML inspection, slide rendering, OCR, visual inventory, and vision-capable screenshot review; then write academic speaker notes grounded in every visible slide element, generate a complete display-version document, and inject clean notes into the PowerPoint notes pane. Use when the user wants speaker notes, presenter notes, a speech script, narration, or annotated notes for an existing PowerPoint deck, especially when slides contain images, charts, tables, SmartArt, axes, legends, or screenshot text.
AI272/speaker
Stars: 480Claude CodeCodexUse when asked to make a launch video, product film, motion design piece, UI motion reel, Dribbble-style UI animation or animated brand/logo sting — anything rendered to MP4 from HTML with a cursor, morphing UI, springs, beat-synced music and SFX. Carries Chan's full creative direction (one shape never cut, blur content swaps, springs, real data, logo slams, no creative limits) and the proven build/render pipeline (pure seek(t), closed-form springs, Playwright subframes, ffmpeg tmix, numpy beat grid).
AbubakrChan/product-launch-motion
Stars: 479Claude CodeCodexLegacy v1 (voiceover-led, GSAP + HyperFrames). Use when making, directing or rescuing a product launch video, promo, teaser, demo reel, sizzle, feature-announcement film or animated product explainer built from code — and when an existing one looks basic, reads as a slideshow, has reveals that miss the voiceover, an invisible cursor, an inaudible sound effect, a clipped or too-quiet mix, or every video coming out looking the same. Covers SaaS, apps, hardware, e-commerce, dev tools, services. Keywords include motion design, storyboard, voiceover sync, kinetic typography, GSAP, HyperFrames, Remotion, film grain, LUFS, ffmpeg.
AbubakrChan/product-launch-motion
Stars: 479Claude CodeCodex网感口播精剪(v3.4):口播视频加动效,自动剪成"网感口播精剪风格"竖版/横版样片,交付渲染成片+分层工程包(装了剪映引擎则再出剪映分层草稿,音效放草稿;没装则音效混进成片)。当用户给了口播粗剪(+B-roll/截图/录屏)并想要"口播动效/加卡片弹字/剪成短视频/做动效样片/网感口播精剪"时用。自循环:预检→素材理解→找真证据→编排→HyperFrames构建→硬门+两两对比自迭代(≤3版)→配音效→交付→用户终审。不做:纯字幕/纯配音/纯生图/BGM。
YeJe-cpu/SeeCut
Stars: 464Claude CodeCodex后端开发 Agent — API 设计、数据库优化、服务器端逻辑、认证授权、性能优化
peterfei/ai-agent-team
Stars: 452Claude CodeCodex智能变更日志生成器 - 自动分析Git提交历史,生成符合规范的CHANGELOG.md。支持语义化版本管理、多种输出格式、增量更新和GitHub/GitLab集成。
peterfei/ai-agent-team
Stars: 452Claude CodeCodexDevOps 工程师 Agent — CI/CD 流水线、容器化与 K8s、基础设施即代码、可观测性
peterfei/ai-agent-team
Stars: 452Claude CodeCodex智能笔记与流程图绘制工具(优化版-无权限读取)。根据用户提供的内容,自动生成精美的可视化笔记和流程图,支持多种风格(手写笔记、思维导图、流程图等),并导出为图片。使用内置模板,无需读取文件权限。适用于:(1) 学习笔记可视化,(2) 知识梳理与总结,(3) 流程图绘制,(4) 概念解释图表
peterfei/ai-agent-team
Stars: 452Claude CodeCodex前端开发 Agent — UI 实现、组件构建、交互设计、性能优化、可访问性
peterfei/ai-agent-team
Stars: 452Claude CodeCodex