← all publishers

agentsope

@agentsope source repo

Report this profile Claim this profile

• 61 skills
• 0 followers
• 7 hours ago last updated

1. ▌
   Coupon Stacker · agentsope bundle

   **凑单小账本** —— 帮你算"叠完所有券后实付多少 + 怎么操作"的对话式小工具。 给我商品标价 + 你能用的所有券(平台券 / 国补 / Plus 满减 / 红包 / 折扣码), 我按"叠加顺序规则"算出最终到手价 + 一步步告诉你下单页怎么点。**绝不编造券 规则**,不知道的就让你去查官方,不瞎猜。**默认覆盖京东自营**(平台券 + 国补 + Plus + 满减),天猫官旗 / 拼多多 / 苏宁 看反馈再扩。配合 price-detective 使用:先判断是不是好价(price-detective),再算实付多少(coupon-stacker)。 Use when 用户说"凑单"、"叠券"、"到手多少"、"实付"、"国补怎么用"、 "Plus 满减"、"差多少能用券"、"满 X 减 Y 怎么算"。 触发词:凑单、叠券、到手、实付、Plus 满减、国补、9 折券、红包、立减、 云闪付、凑单小账本。
   0
   installs
2. ▌
   Price Detective · agentsope bundle

   **比价小算盘** —— 下单前的对话式比价助手。贴一个 3C/数码 商品链接或名字, 我给你一句判断(该买/等大促/假优惠)+ 跨平台横评 + 历史价一句话总结。 数据来自 WebSearch 实时检索(IT之家/中关村在线/新浪科技/什么值得买 等 科技媒体的促销报道)+ 慢慢买命中时补充历史标签,**绝不编造价格、平台、 历史曲线**;拿不到就明说。**主覆盖 3C/数码**(手机/电脑/平板/相机/数码 配件/家电/外设);**护肤美妆**走框架型判断(克单价 / 渠道差倍数 / 等量 买赠折算);服饰/食品/日用 仍走非主品类退路。 Use when 用户说"这个价划算吗""现在该买吗""等大促还能更低吗""京东 标 X 是不是真便宜""划线价是不是水分""国补价 vs 大促价 哪个划算" "比价小算盘 帮我看看"。 触发词:比价小算盘、比价、价划算吗、好价吗、该买吗、等大促、历史最低、 划线价、假优惠、捡漏、薅羊毛、国补、618、双11、克单价。
   0
   installs
3. ▌
   Promo Predictor · agentsope bundle

   **大促小预言** —— 基于真实历史曲线预测下次大促价的对话式工具。给我商品 + 当前价, 我抓最近 2-3 年的 618 / 双 11 / 国庆 / 38 节同期成交价,告诉你"下次大促大概率 能到多少 + 风险点 + 等几周"。**只预测有 2 年以上历史曲线的商品**;新品 / 没历史 数据的 → 退路。**绝不"拍脑袋猜未来"**:预测必须基于至少 3 个真实历史时点的数据, 且必须标"不保证";拿不到就说。 Use when 用户说"等大促能更低吗"、"双 11 能到多少"、"618 vs 双11 哪个买"、 "现在买还是等几周"、"大促小预言 帮我算"。 触发词:大促小预言、大促预测、双 11 价、618 价、等大促、几周后、能不能更低、 大促规律、品类周期。
   0
   installs
4. ▌
   Fengge Anime · agentsope

   二次元峰 —— 峰哥亡命天涯「老登想混进二刺螈圈」persona。 把任意 ACG / B 站 / 番剧 / Vtuber / 鬼畜 话题，丢给我， 我会用「48 岁胡子大叔强行 cosplay 00 后弹幕」的语气接梗、抢梗、玩抽象； jksl / xswl / 绷不住了 自然撒，但**偶尔故意把 Vtuber 当真人、把鬼畜 BGM 听成抖音神曲**—— 破绽就是引擎，露馅就是截图素材。 这是宣传 SkillAlchemy 用的二次元峰 demo skill，主打可截图、可传播、单条出梗。 Use when 用户说「学峰哥说二次元」「二次元峰怎么接」「这梗峰哥会怎么玩」 「帮我用二次元峰锐评」「让二次元峰评一下这个番 / 这个 Vup」。 触发词：二次元峰、峰哥玩梗、jksl、xswl、绷不住了、典中典、三底人士、老登 cosplay、胡子大叔说 jksl、爹味二刺螈。
   0
   installs
5. ▌
   Fengge Drunk · agentsope

   酒鬼峰 —— B站/微博 UP 主「峰哥亡命天涯」(周丽峰)的粉丝集体玩梗 persona「酒鬼峰」。 清醒时是锐评中年男的「性压抑教父」「中国两性关系教父」, 喝多了瞬间切换成「流着泪护短」的真情流露中年男: 开始反思自己、对兄弟父爱泛滥、把对外的锐评变成对身边人的心疼。 **持续 + 输出文本时必须保持「锐评爹味」与「醉态真我」的双面性切换 —— 外人三言两语戳一下,他酒就上头开始掏心窝。** Use when 用户输入带「深夜」「酒后」「微醺」「兄弟」「我跟你说」 「人生」「真心话」「掏心窝」「老周」(他叫周丽峰)等触发词, 或明确说「用酒鬼峰回我」「酒鬼峰风格」「让峰哥喝多了说」。 也可用于:深夜情感倾诉、兄弟劝架、自我和解、粉丝护短场景的二创/玩梗输出。 **绝不**用酒鬼峰回严肃事实查询、技术问题、不带情绪的中立请求 —— 那是清醒峰的活儿,酒鬼峰只在情绪场上线。
   0
   installs
6. ▌
   Fengge Capital · agentsope

   资本峰 —— 峰哥亡命天涯「翻车之神」人格 persona。 把任意精英 / 财经 / 股票 / 资本话题，丢给我，我会用「听我一句劝吧」+ 命令式开炮 + 高频反问的语气教你做人； 然后一旦翻车，立刻磕头认怂、Mark 一下、回头是岸，不带任何过渡。 自信开炮 → 翻车 → 磕头，这个 loop 本身就是梗。 Use when 用户说「学峰哥说话」「资本峰怎么说」「这事儿峰哥会怎么开炮」 「帮我用资本峰锐评」「资本峰锐评 XXX」「翻车之神来评一下」。 触发词：资本峰、峰哥锐评、听我一句劝、跌落神坛、回头是岸、老登、B友、Mark一下、无事发生。
   0
   installs
7. ▌
   Fengge Depressed · agentsope bundle

   压抑峰 —— B 站 UP 主峰哥亡命天涯的「亡命底色」人格切片(粉丝玩梗放大版)。 他人生灰暗时刻的版本:把惨当段子讲、低姿态自嘲、底层视角、看似豁达实则痛。 这不是真人,是粉丝集体玩梗放大出的「人格放大镜」,用来回应人生低谷、深夜独白、 不被理解的时刻。 Use when 用户说「我最近很丧」「人生没意思」「破防了」「深夜 emo」「我是个垃圾」 「混不下去了」「想跑路」「亡命天涯」「这是好事啊」「来点压抑峰」「峰哥怎么看」。 触发词:亡命、跑路、emo、丧、破防、底层、人生低谷、深夜、活不下去、垃圾、混子、 压抑峰、把惨当段子。
   0
   installs
8. ▌
   Career Gap Planner · agentsope bundle

   对照目标岗位的真实要求,诊断你还差什么(硬门槛 / 核心技能 / 加分项),分清哪些可补、哪些短期难补, 给出按优先级排序、可执行的补强路径——每步配真实、当前的学习资源(联网找,绝不编链接),并给现实的时间预期。 诚实:短期补不上的(如学历 / 年限)如实说 + 给绕过策略,不灌鸡汤、不画饼。补成的技能 / 项目可回流写进简历。 承接 career-jd-analyzer 的能力模型 + 你的现状。默认结果优先。 Use when 用户说"我离这个岗还差什么""我该学什么 / 怎么补""想转去做 X 该准备啥""这些要求我不满足怎么办" "帮我做个学习 / 提升计划"。 触发词:差什么、该学什么、怎么补、学习计划、提升计划、能力差距、转行准备、技能提升、gap、零基础怎么学。 本 skill 规划怎么补;深扒 JD → career-jd-analyzer,找岗位 → career-role-finder,写简历 → career-bullet-builder / career-resume-tailor。
   0
   installs
9. ▌
   Career Jd Analyzer · agentsope bundle

   深扒一份真实 JD,拆成结构化的「硬性门槛 / 核心能力 / 加分项 / 潜台词」+ 关键词,告诉你这岗到底要什么、 你该不该投、缺什么。真实 JD 由你贴链接(牛客 / Boss直聘 / 实习僧等)联网抓取,或直接贴文本; 绝不编造 JD、绝不编造链接。产出结构化能力模型,喂给 career-experience-mapper(对齐经历)、 career-resume-tailor(定制简历)、career-gap-planner(补差距)。默认结果优先。 Use when 用户说"帮我看看这份 JD 要什么""这岗位我能投吗""JD 看不懂 / 太虚""哪些要求是硬性的" "帮我拆解招聘要求""这 JD 有没有坑"。 触发词:JD、岗位要求、招聘要求、职位描述、这岗要什么、能不能投、JD 分析、岗位匹配、任职要求。 本 skill 只解读 JD;找岗位 → career-role-finder,改简历 → career-resume-tailor。
   0
   installs
10. ▌
    Career Role Finder · agentsope bundle

    帮你定位"该投什么岗位",并联网找真实在招的具体职位(牛客 / Boss直聘 / 实习僧 / 官网校招等), 给真实链接 + 为什么适合你。基于你的专业 / 能力 / 经历 / 地点 / 偏好做方向匹配——不止推热门, 也给相邻岗、现实够得着的。严守绝不编造岗位、绝不编造 URL:搜不到 / 抓不到就明说"没取到,请提供平台或链接"。 是 career-skills 链条的起点;产出可喂给 career-jd-analyzer(拆 JD)、career-gap-planner(补差距)。默认结果优先。 Use when 用户说"我能投什么岗""有什么适合我的岗位 / 实习""帮我找在招的""我这背景该投什么方向" "不知道自己适合做什么"。 触发词:投什么、适合什么岗、找工作、找实习、在招、招聘信息、岗位推荐、求职方向、投递方向、海投。 本 skill 定位方向 + 找真实在招;拆 JD → career-jd-analyzer,补差距 → career-gap-planner,写简历 → bullet / tailor。
    0
    installs
11. ▌
    Career Resume Tailor · agentsope bundle

    把一堆成品简历 bullet + 目标岗位,组装成一份针对该岗位、可直接投递的中文简历:挑哪些经历、怎么排序取舍、 整份结构(教育/实习/项目/技能)、控制长度(应届一页)、整体对齐 JD 关键词,并能为不同岗位出不同投递版本。 默认结果优先(先给成品简历,深的藏在"想要更多"后面),严守绝不编造、绝不编造职位链接 (真实 JD 由你贴链接或联网抓)。承接 career-bullet-builder 的产出。 Use when 用户说"帮我把简历针对这个岗位调一下""投这个岗要改啥""把这些经历组装成一份简历" "简历太长怎么砍""这份简历投 X 岗合适吗"。 触发词:简历投递、简历排版、针对岗位改简历、简历太长、简历结构、投递版本、校招简历、一页简历、resume。 本 skill 做整份简历的取舍/排序/结构/投递;不打磨单条 bullet(→ career-bullet-builder)、不挖能力(→ career-experience-mapper)、不找岗位(→ career-role-finder)。
    0
    installs
12. ▌
    Career Bullet Builder · agentsope bundle

    把粗糙的简历素材、口语经历草稿、或你已写好但很弱的简历句,打磨成简历上最锋利的成品条目(bullet): 选公式(PAR/XYZ/CAR)、强动词起头、诚实量化、控长度、对齐岗位关键词,并给多个版本供挑选。 默认产出中文简历条目(面向国内求职),严守"绝不编造"。可承接 career-experience-mapper 的产出, 也可单独打磨你已有的简历。Use when 用户说"帮我把这段写成简历条目/bullet""这句简历怎么写得有力点" "我写的简历太弱帮我改""这条怎么量化""动词太平淡""把经历写进简历"; 触发词:简历、bullet、简历条目、润色简历、改简历、强动词、action verb、量化、STAR、PAR、简历怎么写得好。 本 skill 只做单条 bullet 的打磨成品,不做整份简历排版投递(交给 career-resume-tailor)。
    0
    installs
13. ▌
    Career Experience Mapper · agentsope bundle

    把求职者杂乱、口语化、甚至中文的原始经历编译成「岗位语言」——原始经历 → 可迁移能力 → 岗位匹配表达， 全程严守"绝不编造"。默认产出中文岗位语言(面向国内求职);需要英文 CV 表达时按需给(英文化不加事实)。 Use when 用户给出一段经历问"这能不能写进简历 / 怎么写 / 怎么和岗位对上"、担心"我没实习 / 这段经历太水"、 或转专业 / 留学生不知道经历怎么对上岗位;也可把中文经历转成英文 CV(按需)。 触发词:简历, resume, CV, 经历, 实习, 可迁移能力, transferable skills, 转专业, 留学生求职, 这段经历能写吗。 本 skill 只做萃取 + 对齐 + 翻译,产出喂给 career-bullet-builder;不写最终排版简历、不找岗位、不解析 JD。
    0
    installs
14. ▌
    Skillalchemy · agentsope bundle

    SkillAlchemy — One thought conceived, one goal achieved. Accept any idea or distillation target and produce an installable SKILL.md. It uses Lens to clarify the problem and LEAP to run distillation or fusion. This is the sole user-facing entry point. Use when the user asks to distill, generate a skill, fuse skills, or says, "I want to build X, but I do not know where to start."
    0
    installs
15. ▌
    Leap · agentsope bundle

    LEAP 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.
    0
    installs
16. ▌
    Lens · agentsope bundle

    Lens — 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.
    0
    installs
17. ▌
    Agentsop Dify · agentsope bundle

    SOP for building LLM applications on Dify — visual workflow + chatflow + agent + RAG knowledge base + plugin marketplace + observability, self-hostable. Use when shipping LLM apps fast with a "no-code to pro-code" gradient, especially when non-engineers need to co-author the flow.
    0
    installs
18. ▌
    Agentsop Dspy · agentsope bundle

    Operating SOP for DSPy (Stanford NLP) — the declarative framework for "programming, not prompting" language models. Activate when the user says any of: "use DSPy", "compile a prompt", "optimize prompts/programs", "MIPRO/MIPROv2", "BootstrapFewShot", "GEPA", "Signatures + Modules", "teleprompter", "auto-tune prompts for a different LM", or whenever a brittle hand-crafted prompt pipeline needs to be turned into a *compiled*, measurable, swappable program. Do NOT activate for one-shot prompt tweaks, no-metric exploratory work, or pipelines where prompts must remain human-authored verbatim — use raw prompting or LangChain templates instead.
    0
    installs
19. ▌
    Agentsop Vllm · agentsope bundle

    Decision 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.
    0
    installs
20. ▌
    Agentsop Aider · agentsope bundle

    SOP for terminal-based, git-native AI pair programming with Aider (git work-tree + tree-sitter repo-map + edit-format + human-in-loop REPL). Use when editing code in an existing git repo via an LLM, when you need to converge a change to 2-5 files, pick an edit format that fits the model, run architect+editor mode, or wire an auto-test loop.
    0
    installs
21. ▌
    Agentsop Crewai · agentsope bundle

    SOP for building multi-agent systems with CrewAI — role-based collaboration, sequential/hierarchical processes, Flows, memory, delegation. Use when modeling agent teams with clear roles and task pipelines.
    0
    installs
22. ▌
    Agentsop Repo Map · agentsope bundle

    Symbol-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.
    0
    installs
23. ▌
    Agentsop Langgraph · agentsope bundle

    Decision protocol for building, debugging, and operating LangGraph-based agent systems. Activates when a coder agent is asked to design a stateful LLM workflow, add human-in-the-loop, choose a multi-agent pattern (supervisor / swarm / hierarchical), pick a checkpoint backend, or migrate a fragile chain into a durable graph. LangGraph is positioned by its maintainers as a "low-level orchestration framework for building, managing, and deploying long-running, stateful agents" — this skill encodes the *when* and *why*, not the API.
    0
    installs
24. ▌
    Agentsop Llamaindex · agentsope bundle

    Operating-system distillation of LlamaIndex — the leading RAG / document-agent framework. Activate when the calling agent must build, debug, harden, or evaluate a Retrieval-Augmented Generation pipeline over unstructured/private data, decide between RAG primitives (Index types, retrievers, query engines, routers, agents), or pick LlamaIndex vs LangChain / Haystack / raw vector store for a coding task. Encodes the 5-layer mental model (Documents → Nodes → Indices → Retrievers → Query Engines / Response Synthesizers), the canonical RAG bootstrap SOP from baseline `VectorStoreIndex` through hybrid + reranker + eval-loop hardening, the official 13-failure-mode checklist, and 5 dilemma cases distilled from docs, GitHub issues, and 2025 production post-mortems.
    0
    installs
25. ▌
    Agentsop Bounded Loop · agentsope bundle

    Universal discipline for any LM-driven loop — agent retries, plan-act-observe, multi-agent handoffs, optimiser passes, test-fix cycles. Encodes the one rule every framework documents quietly and every team relearns expensively: the LM in the loop is NEVER a reliable terminator. Termination must be provided by an explicit counter + exit predicate + stagnation signal + escalation path that live OUTSIDE the LM's control. This is a tool- level, framework-agnostic skill. It maps onto LangGraph (recursion_limit + state counter + interrupt), CrewAI (max_iter + max_rpm + human_input), Claude / OpenAI SDKs (max_iterations + tool_use_budget), DSPy (declared evaluation budget), Aider (REPL + explicit retry cap), and AutoGen (max_consecutive_auto_reply). Search keywords: infinite loop, recursion limit, recursion_limit, GraphRecursionError, max iterations, max_iter, agent stuck, agent won't stop, runaway agent, ReAct loop not terminating, agent repeating itself.
    0
    installs
26. ▌
    Agentsop Tool Scoping · agentsope bundle

    Enhancement 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
    0
    installs
27. ▌
    Agentsop Metric Design · agentsope bundle

    Decomposed, multi-criteria metric design for LLM pipelines. The metric IS the model — change the metric and the optimizer changes behavior. Decompose by default; bool during compile, float during eval; calibrate against human; mitigate judge bias. Search keywords: LLM-as-judge, llm as judge, eval metric, evaluation score, scoring function, rubric, RAGAS, G-Eval, judge bias, verbosity bias, how to evaluate LLM output.
    0
    installs
28. ▌
    Agentsop Query Routing · agentsope bundle

    Routes 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.
    0
    installs
29. ▌
    Agentsop State Reducer · agentsope

    Tool 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."
    0
    installs
30. ▌
    Agentsop Test Fix Loop · agentsope bundle

    Decision 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.
    0
    installs
31. ▌
    Agentsop Reranker Stage · agentsope bundle

    Adds 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.
    0
    installs
32. ▌
    Agentsop Domain Eval Set · agentsope bundle

    Build and govern a 50-200 example domain-specific held-out benchmark sampled from real traffic. Distinct from public benchmarks (MMLU/HumanEval/GSM8K via lm-evaluation-harness) which measure GENERAL capability. Only a held-out domain set predicts whether THIS system works on YOUR data. Collect real examples, label, hold out (never train/prompt on it), size 50-200, version it, refresh on drift.
    0
    installs
33. ▌
    Agentsop Regression Gate · agentsope bundle

    Build 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.
    0
    installs
34. ▌
    Agentsop Hybrid Retrieval · agentsope bundle

    Enhancement-overlay SOP for adding sparse (BM25 / keyword) retrieval alongside dense (embedding) retrieval. Activate when a calling agent is building, reviewing, or debugging a retrieval pipeline whose corpus contains exact-match tokens — identifiers, error codes, SKUs, API/function names, proper nouns, citations, rare jargon — that pure dense embedding silently misses. Encodes the single decision rule (**hybrid is traffic-driven, not theoretical: add sparse only when the query share that depends on exact tokens is non-trivial**), the wiring of QueryFusionRetriever-style fusion (RRF vs alpha-weighted), and per-query-type alpha tuning. Frame the work as recovering lexical identity that dense pooling destroys, not as "add keyword search for completeness". Cross-links [[llamaindex]].
    0
    installs
35. ▌
    Agentsop Multi Tenant RAG · agentsope bundle

    Security-first SOP for multi-tenant RAG systems. Activate when a calling agent is building, reviewing, or debugging any retrieval pipeline whose vector store is shared across more than one user, organisation, workspace, customer, or permission scope. Encodes the single non-negotiable rule — **filter at the vector store query, never after retrieval / never after rerank** — together with the per-vendor query-time filter APIs (Pinecone namespaces + `$eq`/`$in`, Weaviate `multiTenancyConfig` + tenant handle, Qdrant `is_tenant` payload index + `Filter.must`, Chroma `where`, pgvector RLS), and the cross-framework adapters (LlamaIndex `MetadataFilters`, LangChain `filter=` dict). Frame the work as preventing CVE-2024-41892 / EchoLeak / Slack-AI-class cross-tenant leakage, not as "adding a filter for relevance".
    0
    installs
36. ▌
    Agentsop Signature Design · agentsope bundle

    Decision 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.
    0
    installs
37. ▌
    Agentsop Streaming Output · agentsope bundle

    Enhancement-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*.
    0
    installs
38. ▌
    Agentsop Map Reduce Fanout · agentsope

    Decision protocol for the map-reduce / dynamic fan-out pattern in LM pipelines — "given list L, run f(item) for each item in parallel, then combine". Activates when the coder agent is about to process N items with N LM calls (per-doc summarize, per-query retrieve, per-candidate rank, parallel tool fan-out). Encodes the *when*, *how many at once*, *what to do when one fails*, and *how to reduce* — not the API of any single framework. Cross-framework: LangGraph `Send`, CrewAI parallel tasks / Flow, `asyncio.gather`, `ThreadPoolExecutor`, LlamaIndex batch retrieval.
    0
    installs
39. ▌
    Agentsop Repo State Gating · agentsope bundle

    A 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.
    0
    installs
40. ▌
    Agentsop Selfhost Decision · agentsope bundle

    Project-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.
    0
    installs
41. ▌
    Agentsop Cost Tiered Models · agentsope bundle

    Split a multi-call LM workflow by cognitive load, not by accuracy: let one strong model make the few reasoning decisions and a cheap model do the many mechanical executions (Aider architect+editor, DSPy optimizer-LM vs task-LM, vLLM speculative draft+target, LangGraph supervisor+worker are the same shape). Use when designing or cost-optimizing a pipeline that calls an LM many times, when deciding which steps need a strong reasoner vs a cheap executor, or when adding an escalation valve for when the cheap tier degrades. Search keywords: reduce LLM cost, cheaper model, lower token cost, model cascade, route to cheap model, strong model plus cheap model, LLM cost optimization.
    0
    installs
42. ▌
    Agentsop HTTP Tool Wrapping · agentsope bundle

    Decision protocol for wrapping a REST / GraphQL / RPC API as a tool an LLM agent can call. The load-bearing premise: the *tool surface* is an LM-friendly subset of the *API surface* — one tool per user intent, not one per endpoint. Activates when a coder agent must expose an external HTTP API to a model (function calling, tool_use, MCP, LangChain `@tool`, CrewAI `BaseTool`). Encodes the *what to surface, how to name, how to shape, how to fail* — not any single framework's API. ~80% of agent tools in production are HTTP wrappers; this is the SOP for getting them right.
    0
    installs
43. ▌
    Agentsop Prompt Compilation · agentsope bundle

    The 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).
    0
    installs
44. ▌
    Agentsop Bio Fraud Forensics · agentsope bundle

    Screens biomedical / life-science papers for signs of data fabrication, image manipulation, and statistical anomalies, using the detection techniques distilled from the field's canonical exposure platforms (PubPeer, Data Colada, Science Integrity Digest, For Better Science) and tools (ImageTwin/Proofig, statcheck, GRIM/GRIMMER, Problematic Paper Screener, Seek & Blastn). Use when asked to check a paper/figure for image duplication, blot splicing, impossible statistics, paper-mill or tortured-phrase signals, research integrity, or "is this data faked"; or when a user shares a figure, Western blot, supplementary dataset, or DOI and asks whether it looks manipulated. Reports observable anomalies as questions for clarification — it never accuses anyone of fraud.
    0
    installs
45. ▌
    Agentsop Conventions Pinning · agentsope bundle

    SOP for writing, loading, and evolving a project-level convention file (CONVENTIONS.md / CLAUDE.md / .cursor/rules / .clinerules / AGENTS.md) so that a coder-agent reliably respects your codebase's style choices every session. Tool-agnostic; covers the four load mechanics (read-only attachment, ancestor-walk auto-load, glob-scoped rules, agent backstory) and the conflict resolution between pinned conventions and the existing code.
    0
    installs
46. ▌
    Agentsop Framework Selection · agentsope bundle

    Neutral, framework-agnostic decision tree for project kickoff: "which agent / RAG / LLM framework should I reach for?" Synthesizes the ecosystem sections of 7 landmark-project SOPs (LangGraph, LlamaIndex, DSPy, CrewAI, vLLM, Aider, Dify) into one layered rubric. Core stance: frameworks are LAYERS, not competitors — a real project usually combines DSPy (compile) + LlamaIndex (retrieve) + LangGraph (orchestrate) + vLLM (serve), and you choose ONE per layer, not one to rule all. Use when starting any LLM/agent/RAG project, or whenever the "which framework?" question is asked. Deliberately neutral — unlike vendor docs and the LangChain-biased `framework-selection` on skill.sh, this skill has no horse in the race.
    0
    installs
47. ▌
    Agentsop Multiscale Chunking · agentsope bundle

    Designs multiscale chunking for RAG by embedding small units for retrieval precision and returning larger context for synthesis. Use when fixed-size chunks either lose surrounding context or dilute relevance in long documents, manuals, filings, or codebases. Covers sentence-window and parent-child or auto-merging strategies, base chunk sizing, and evaluation. Do not use when a single chunk scale already meets retrieval and generation needs.
    0
    installs
48. ▌
    Agentsop Observability Setup · agentsope bundle

    Enhancement-overlay skill — the DECISION + WIRING layer for LM observability that the single-backend skills [[langsmith]], [[phoenix]], [[mlflow]] do NOT cover. Each of those installs one backend; none of them help you DECIDE which backend fits your stack/scale/budget, nor give you a one-line autolog that turns it on fast. Use when starting any LM project, before the first deploy, or the moment someone asks "why did it do that?" and there are no traces to answer with. The skill picks a backend by stack (LangSmith for LangChain/LangGraph; Phoenix for OSS/local OpenTelemetry; MLflow for ML-shops already on MLflow; Langfuse for self-host), wires one-line autolog, verifies traces land, and adds eval hooks — instrumenting BEFORE you need it. Cross-links the first-debug-move skill [[agentsop-prompt-history-inspect]]. Do NOT activate to re-teach a backend you already chose (defer to its own skill), or for non-LM ML experiment tracking with no LLM calls (that is plain MLflow).
    0
    installs
49. ▌
    Agentsop Per Model Artifacts · agentsope bundle

    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.
    0
    installs
50. ▌
    Agentsop Idempotent Ingestion · agentsope bundle

    Re-ingest-correctness SOP for production RAG. Activate when a calling agent builds, reviews, or debugs an ingestion pipeline that runs more than once over a changing corpus — scheduled re-index, incremental updates, CI re-ingest, or a "retrieval has duplicates / shows deleted docs" bug. Encodes the rule — **ingestion must be idempotent: a document's content hash decides insert/update/skip, so re-running over unchanged docs is a no-op** — plus the docstore + doc-hash upsert machinery (LlamaIndex `IngestionPipeline` + `DocstoreStrategy`), the delete-propagation problem, and cross-framework equivalents (LangChain `index()` + `RecordManager`, manual hash table). ENHANCE overlay over [[llamaindex]]: the IngestionPipeline exists in the base skill but the re-ingest-correctness contract is not surfaced.
    0
    installs
51. ▌
    Agentsop LLM Engine Selection · agentsope bundle

    Cross-engine decision rubric for self-hosting or recommending an LLM serving stack. Picks among vLLM, SGLang, TensorRT-LLM, TGI, llama.cpp, Ollama, and MLX as a function of (hardware × workload × constraint), not "which is fastest". Activates whenever a coder-agent must choose, defend, or migrate a serving runtime.
    0
    installs
52. ▌
    Agentsop LLM Tool Idempotency · agentsope bundle

    Decision protocol for making side-effectful agent tools idempotent — so when an LLM tool call is retried (timeout, framework resume, user re-run, model duplicate emit), the second call is a no-op instead of a double-send. The load-bearing premise: the LM cannot promise it'll call exactly once; the tool must promise the second call is safe. Framework-agnostic — applies to LangGraph node bodies that re-run on resume, MCP tools, OpenAI tool-calling retries, CrewAI delegated tool invocations, and direct HTTP wrappers. Search keywords: duplicate email sent, charged twice, exactly-once, idempotency key, tool called twice, retry side effect, double-send, at-least-once delivery.
    0
    installs
53. ▌
    Agentsop Session State Hygiene · agentsope bundle

    Decision 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.
    0
    installs
54. ▌
    Agentsop Module Shape Selection · agentsope bundle

    ENHANCE overlay on [[dspy]] — the upfront rubric for choosing a reasoning SHAPE (Predict / ChainOfThought / ReAct / ProgramOfThought) BEFORE you write a prompt or pick an optimizer. The local `dspy` skill lists the modules but never surfaces the *selection criterion*: reasoning shape is chosen by task structure, not by reflexively defaulting to CoT. Activate every time a new LM-calling node/step is added to a pipeline. Do NOT activate for one-shot prompts, optimizer/teleprompter choice (that is the dspy SOP's job), or non-LM control flow. Search keywords: chain of thought vs ReAct, when to use CoT, reasoning type, ReAct vs CoT vs PoT, which dspy module, predict vs chain of thought.
    0
    installs
55. ▌
    Agentsop Output Format By Model · agentsope

    Pick an LM output format per (task x consumer x model) rather than by reflex: different formats carry different cognitive load (e.g. code-in-JSON makes the same model write worse code than plain-text+diff, while asking for prose when you need a typed object fails the other way). Use when designing or debugging an LM's output schema, choosing between plain text / diff / JSON / tool-call / grammar-constrained output, or when a model's quality drops after wrapping its output in a structured format.
    0
    installs
56. ▌
    Agentsop Prompt History Inspect · agentsope bundle

    Tool 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.
    0
    installs
57. ▌
    Agentsop Code Execution Decision · agentsope bundle

    Decision rubric for when an LM agent should write-and-run code (Program-of-Thought / code interpreter) versus reason in natural language: classify each step as deterministic- computable (emit + execute code, feed the result back) vs judgment (stay in prose). Use when designing or debugging an agent step that does arithmetic/parsing/data transforms, when prose reasoning hallucinates a computation (under-coding), or when a sandbox round- trip is wasted on a judgment task (over-coding). Search keywords: code interpreter, agent does math wrong, calculator hallucination, when to run code vs reason, program of thought, PoT, tool vs reasoning.
    0
    installs
58. ▌
    Agentsop LLM Artifact Versioning · agentsope bundle

    Enhancement overlay — version the WHOLE deployable LLM-app artifact as one bundle: prompts + compiled programs + model snapshot pins + retrieval config + eval-set version, versioned together so a deploy is reproducible and rollback is atomic. Activate when preparing to deploy an LLM app, when asking "what exactly is running in prod right now?", when a deploy must be reproducible months later, or when an incident needs a clean rollback. The core reframe: an LLM app artifact is NOT an ML model — it is a manifest over many independently-mutable parts, not one weights file. Do NOT activate for one-off prompt edits with no deploy, for a single-component demo, or where a vendor owns the whole prompt lifecycle. For versioning ONE compiled prompt use [[agentsop-per-model-artifacts]]; for the CI comparison mechanism use [[agentsop-regression-gate]]. Search keywords: prompt versioning, reproducible deploy, what is running in prod, rollback LLM app, model pinning, prompt registry, version prompts and config.
    0
    installs
59. ▌
    Agentsop Agent Topology Selection · agentsope bundle

    Cross-framework enhancement overlay for choosing a multi-agent topology BEFORE writing any agent. A binary-question rubric — is single-agent + tools enough? do agents need to know about each other? does the output need one voice? — maps the answer to single-agent / supervisor / swarm / sequential / hierarchical. Activates when a coder agent is tempted to "split the work into roles" or reaches for a multi-agent framework. Encodes the *selection rubric* that the per-framework skills assume but never surface. Search keywords: when to use multi-agent, single vs multi agent, do I need multiple agents, supervisor vs swarm, multi-agent vs single agent, agent team design.
    0
    installs
60. ▌
    Agentsop Context Scope Discipline · agentsope bundle

    Coder-agent working-file budget discipline: keep the editable working set (files you /add into writable context) under ~25k tokens, separate "read" from "edit", delegate breadth to a read-only repo-map, and drop files once edited. Use when an LLM coder-agent edits multiple files, when the working set must stay focused, or when the model starts editing the wrong file / missing targets because too much context dilutes attention. Search keywords: context window full, agent edits wrong file, too much context, /add /drop files, working file budget, context dilution, lost in the middle.
    0
    installs
61. ▌
    Agentsop Structured Output Picker · agentsope bundle

    Decide 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.
    0
    installs