Skill collection

agentsope/SkillAlchemy

47 agent skills across 12 categories, read straight from the repository tree. The repo holds 48 SKILL.md files — 1 are the same skills republished elsewhere in the tree, and we count things rather than copies.

HengJun Wang255★ across the radarProfile →
47
Skills published
12
Categories
1
Ship scripts
255
Stars on the repo
Tracked on the radar · 255★Repository facts and velocity →
Data & Analytics · 10
All in category →
LEAPLEAP builds skills through two pipelines: Branch A distills a skill from raw data, while Branch B combines…scriptsagentsop-bio-fraud-forensicsScreens biomedical / life-science papers for signs of data fabrication, image manipulation, and statistical…agentsop-llamaindexOperating-system distillation of LlamaIndex — the leading RAG / document-agent framework. Activate when the…agentsop-dspyOperating SOP for DSPy (Stanford NLP) — the declarative framework for "programming, not prompting" language…agentsop-metric-designDecomposed, multi-criteria metric design for LLM pipelines. The metric IS the model — change the metric and…agentsop-per-model-artifactsLifecycle SOP for **per-model prompt artifacts** — the compiled prompts, instructions, few-shot demos…agentsop-selfhost-decisionProject-kickoff rubric for the self-host vs managed-cloud decision — when is running your own inference…agentsop-prompt-compilationThe compile-readiness gate for prompt auto-optimization. Decide whether you have earned the right to run an…agentsop-code-execution-decisionDecision rubric for when an LM agent should write-and-run code (Program-of-Thought / code interpreter) versus…
agentsop-domain-eval-set
AI & Agents · 10
All in category →
agentsop-vllmDecision SOP for serving LLMs with vLLM. Covers PagedAttention mental model…agentsop-llm-engine-selectionCross-engine decision rubric for self-hosting or recommending an LLM serving stack. Picks among vLLM, SGLang…agentsop-prompt-history-inspectTool skill — the *first move* in any LM-debugging session: dump the actual rendered prompt the framework sent…agentsop-repo-mapSymbol-level code context for LLM coder-agents: tree-sitter extracts symbols, PageRank ranks them over the…agentsop-reranker-stageEnhancement-overlay SOP for the reranker stage of a RAG pipeline — the "retrieve wide, rerank narrow"…agentsop-tool-scopingEnhancement overlay for multi-agent / tool-using coder agents. Encodes the per-agent tool- scoping discipline…agentsop-multiscale-chunkingEnhancement-overlay (C5) for RAG over long documents — the chunk-paradox resolution. Activate when a single…agentsop-context-scope-disciplineCoder-agent working-file budget discipline: keep the editable working set (files you /add into writable…agentsop-framework-selectionNeutral, framework-agnostic decision tree for project kickoff: "which agent / RAG / LLM framework should I…
agentsop-state-reducer
Backend & API · 5
All in category →
agentsop-langgraphDecision protocol for building, debugging, and operating LangGraph-based agent systems. Activates when a…agentsop-http-tool-wrappingDecision protocol for wrapping a REST / GraphQL / RPC API as a tool an LLM agent can call. The load-bearing…agentsop-hybrid-retrievalEnhancement-overlay SOP for adding sparse (BM25 / keyword) retrieval alongside dense (embedding) retrieval.…agentsop-structured-output-pickerDecide where to enforce structured LM output (constrain at decode time with Outlines vs validate-and-retry…agentsop-map-reduce-fanoutDecision protocol for the map-reduce / dynamic fan-out pattern in LM pipelines — "given list L, run f(item)…
Workflow & Productivity · 5
All in category →
agentsop-crewaiSOP for building multi-agent systems with CrewAI — role-based collaboration, sequential/hierarchical…agentsop-difySOP for building LLM applications on Dify — visual workflow + chatflow + agent + RAG knowledge base + plugin…agentsop-session-state-hygieneDecision protocol for managing the context/session state of an AI coding tool: when to /clear, when to keep…agentsop-cost-tiered-modelsSplit a multi-call LM workflow by cognitive load, not by accuracy: let one strong model make the few…LensLens — Add a cognitive lens to any problem. It accepts a task description and produces an enhanced…
Documentation · 5
All in category →
agentsop-conventions-pinningSOP for writing, loading, and evolving a project-level convention file (CONVENTIONS.md / CLAUDE.md /…agentsop-idempotent-ingestionRe-ingest-correctness SOP for production RAG. Activate when a calling agent builds, reviews, or debugs an…agentsop-repo-state-gatingA 5-minute gate the coder runs at project kickoff (and again whenever the repo shape changes). Classifies the…agentsop-agent-topology-selectionCross-framework enhancement overlay for choosing a multi-agent topology BEFORE writing any agent. A…agentsop-signature-designDecision rubric for promoting a prose prompt into a typed DSPy Signature. This is an ENHANCE overlay on top…
Testing & QA · 4
All in category →
agentsop-aiderSOP for terminal-based, git-native AI pair programming with Aider (git work-tree + tree-sitter repo-map +…agentsop-test-fix-loopDecision protocol for wiring a verify-then-fix loop around a code-editing LLM agent. The agent edits → runs…agentsop-regression-gateBuild a held-out eval set, run it on every prompt/model change, and block regressions in CI. An LM change is…agentsop-bounded-loopUniversal discipline for any LM-driven loop — agent retries, plan-act-observe, multi-agent handoffs…
DevOps & Cloud · 2
All in category →
agentsop-llm-artifact-versioningEnhancement overlay — version the WHOLE deployable LLM-app artifact as one bundle: prompts + compiled…agentsop-observability-setupEnhancement-overlay skill — the DECISION + WIRING layer for LM observability that the single-backend skills…
Frontend · 2
All in category →
agentsop-streaming-outputEnhancement-overlay decision protocol for STREAMING the output of long-running LLM / agent runs from the…agentsop-module-shape-selectionENHANCE overlay on [[dspy]] — the upfront rubric for choosing a reasoning SHAPE (Predict / ChainOfThought /…
Content & Marketing · 1
All in category →
agentsop-llm-tool-idempotencyDecision protocol for making side-effectful agent tools idempotent — so when an LLM tool call is retried…
Security · 1
All in category →
agentsop-multi-tenant-ragSecurity-first SOP for multi-tenant RAG systems. Activate when a calling agent is building, reviewing, or…
Databases · 1
All in category →
agentsop-query-routingEnhancement-overlay SOP for query-type routing — sending a query to the right index / tool / engine *before*…
Code Review & Quality · 1
All in category →
agentsop-output-format-by-modelPick an LM output format per (task x consumer x model) rather than by reflex: different formats carry…
For maintainers

Maintain agentsope/SkillAlchemy? Drop this in your README — it shows how many of your skills are listed and updates itself.

VibeCrowd Skills badge
[![VibeCrowd Skills](https://vibecrowd.fund/api/skill-badge/agentsope--skillalchemy)](https://vibecrowd.fund/skills/sources/agentsope--skillalchemy)
About this collection
How many skills does agentsope/SkillAlchemy publish?

47 that pass our gate — each has a real description and a SKILL.md we could read. The repository actually contains 48 SKILL.md files, but 1 of them are the same skills republished in other folders, so we count things rather than copies.

How do I install one?

Every skill page carries its own command — `npx skills add agentsope/SkillAlchemy --skill <name> --agent claude-code`. Swap the agent for codex, cursor or copilot.

Keep going
All skills →
The full catalog, by category and by tool.
Open Source Radar →
The repositories these collections come from.
More from agentsope →
Everything this maker publishes.