Development
Plugin
skillalchemy
From thought to skill. From signal to structure.
Plugin Signal76/100Solid
maintained96
capable81
documented50
adopted52
Install
$ npx -y skills add agentsope/SkillAlchemy --agent claude-code
Run the curl in your terminal, the rest in Claude Code.
In this plugin
- LEAP
- Lens
- agentsop-agent-topology-selection
- agentsop-aider
- agentsop-bio-fraud-forensics
- agentsop-bounded-loop
- agentsop-code-execution-decision
- agentsop-context-scope-discipline
- agentsop-conventions-pinning
- agentsop-cost-tiered-models
- agentsop-crewai
- agentsop-dify
- agentsop-domain-eval-set
- agentsop-dspy
- agentsop-framework-selection
- agentsop-http-tool-wrapping
- agentsop-hybrid-retrieval
- agentsop-idempotent-ingestion
- agentsop-langgraph
- agentsop-llamaindex
- agentsop-llm-artifact-versioning
- agentsop-llm-engine-selection
- agentsop-llm-tool-idempotency
- agentsop-map-reduce-fanout
- agentsop-metric-design
- agentsop-module-shape-selection
- agentsop-multi-tenant-rag
- agentsop-multiscale-chunking
- agentsop-observability-setup
- agentsop-output-format-by-model
- agentsop-per-model-artifacts
- agentsop-prompt-compilation
- agentsop-prompt-history-inspect
- agentsop-query-routing
- agentsop-regression-gate
- agentsop-repo-map
- agentsop-repo-state-gating
- agentsop-reranker-stage
- agentsop-selfhost-decision
- agentsop-session-state-hygiene
- agentsop-signature-design
- agentsop-state-reducer
- agentsop-streaming-output
- agentsop-structured-output-picker
- agentsop-test-fix-loop
- agentsop-tool-scoping
- agentsop-vllm
What's inside
Skills
47/LEAPLEAP โ ่ฝๅฐๆง่กๅผๆใๅ
ๅซไธคๆก็ฎก็บฟ๏ผA ๅๆฏ่ธ้ฆ๏ผไป raw data ๆๅ skill๏ผใ B ๅๆฏ่ๅ๏ผๅค skill ็ผ็ปไธบไธไธช๏ผใ่ขซ SkillAlchemy ็ผๆๅจ่ฐ็จใ Use when ็ผๆๅจๅคๆญ้่ฆ่ธ้ฆๆ่ๅๆถใ/LensLens โ ็ปไฝ ็้ฎ้ขๅ ไธๅฑ่ฎค็ฅ้็ใ่พๅ
ฅไปปๆไปปๅกๆ่ฟฐ๏ผ่พๅบๅขๅผบ็ description๏ผ ๅ็ฐใไฝ ไธ็ฅ้่ชๅทฑไธ็ฅ้ใ็้ๆง็ปดๅบฆใๅ็ฝฎๆกไปถๅ่ฎค็ฅ่ทฏ็บฟใ Use when ็จๆท่ฏดใๅธฎๆๆณๆณใใๅๆไธไธใใ็ๆ skillใใ่ธ้ฆใใ่ๅใ ๆ่พๅ
ฅ็่ตทๆฅๅคช็ฎๅ้่ฆๅฑๅผใ/agentsop-agent-topology-selectionCross-framework enhancement overlay for choosing a multi-agent topology BEFORE writing any agent. A binary-question rubric โ is single-agent + tools enough? do agents need to know about each other? does the output need one voice? โ maps the answer to single-agent / supervisor //agentsop-aiderSOP 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/agentsop-bio-fraud-forensicsScreens 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/agentsop-bounded-loopUniversal discipline for any LM-driven loop โ 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.
Show all 47 skillsShow fewer
/agentsop-code-execution-decisionDecision 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/agentsop-context-scope-disciplineCoder-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/agentsop-conventions-pinningSOP 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/agentsop-cost-tiered-modelsSplit 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/agentsop-crewaiSOP for building multi-agent systems with CrewAI โ role-based collaboration, sequential/hierarchical processes, Flows, memory, delegation. Use when modeling agent teams with clear roles and task pipelines./agentsop-difySOP for building LLM applications on Dify โ 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/agentsop-domain-eval-setBuild 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/agentsop-dspyOperating SOP for DSPy (Stanford NLP) โ 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 +/agentsop-framework-selectionNeutral, 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:/agentsop-http-tool-wrappingDecision 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* โ one tool per user intent, not one per endpoint. Activates when a coder agent must expose an/agentsop-hybrid-retrievalEnhancement-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 โ identifiers, error codes, SKUs,/agentsop-idempotent-ingestionRe-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 โ scheduled re-index, incremental updates, CI re-ingest, or a "retrieval has duplicates / shows deleted/agentsop-langgraphDecision 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/agentsop-llamaindexOperating-system distillation of LlamaIndex โ 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,/agentsop-llm-artifact-versioningEnhancement overlay โ 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/agentsop-llm-engine-selectionCross-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 ร workload ร constraint), not "which is fastest". Activates whenever a coder-agent must choose,/agentsop-llm-tool-idempotencyDecision protocol for making side-effectful agent tools idempotent โ 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/agentsop-map-reduce-fanoutDecision protocol for the map-reduce / dynamic fan-out pattern in LM pipelines โ "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/agentsop-metric-designDecomposed, multi-criteria metric design for LLM pipelines. The metric IS the model โ 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,/agentsop-module-shape-selectionENHANCE overlay on [[dspy]] โ 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/agentsop-multi-tenant-ragSecurity-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/agentsop-multiscale-chunkingEnhancement-overlay (C5) for RAG over long documents โ the chunk-paradox resolution. Activate when a single fixed chunk size cannot satisfy both retrieval precision (small chunks) and generation context (large chunks): small chunks lose surrounding context, large chunks dilute/agentsop-observability-setupEnhancement-overlay skill โ 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/agentsop-output-format-by-modelPick 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)./agentsop-per-model-artifactsLifecycle SOP for **per-model prompt artifacts** โ 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,/agentsop-prompt-compilationThe 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 โ a real metric, and enough examples for the optimizer you picked./agentsop-prompt-history-inspectTool skill โ 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,/agentsop-query-routingEnhancement-overlay SOP for query-type routing โ sending a query to the right index / tool / engine *before* retrieving, not after. Activate when a calling agent owns a retrieval or answering surface that fronts more than one handler (a summary index, a vector index, a/agentsop-regression-gateBuild a held-out eval set, run it on every prompt/model change, and block regressions in CI. An LM change is a code change โ gate it with a test suite (eval set + metric + threshold). Cross-framework SOP not surfaced by any single base skill./agentsop-repo-mapSymbol-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/agentsop-repo-state-gatingA 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/agentsop-reranker-stageEnhancement-overlay SOP for the reranker stage of a RAG pipeline โ the "retrieve wide, rerank narrow" discipline. Activate when a calling agent owns a retrieval pipeline whose answers have plateaued: top-k contains the right document but it is buried below noise, or the context/agentsop-selfhost-decisionProject-kickoff rubric for the self-host vs managed-cloud decision โ 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 โ VOLUME (a cost-crossover slider) and COMPLIANCE (a hard gate). Use at/agentsop-session-state-hygieneDecision 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" โ the failure mode where stale conversation history biases the model against the current task. Surfaces a discipline that Aider/agentsop-signature-designDecision 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 โ it answers the coder-agent decision "when do I stop hand-writing a prompt string and declare it as a/agentsop-state-reducerTool 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/agentsop-streaming-outputEnhancement-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,/agentsop-structured-output-pickerDecide 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/agentsop-test-fix-loopDecision protocol for wiring a verify-then-fix loop around a code-editing LLM agent. The agent edits โ runs lint/test โ reads the output โ fixes โ re-runs, bounded by an iteration cap and an escalation rule. Activates whenever a coder agent has a verifiable success criterion/agentsop-tool-scopingEnhancement 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/agentsop-vllmDecision 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
README
1SkillAlchemy
ไธๅฟต่ฝๅฐ๏ผไธ่ฑกๆๅฝข
ๆไบบ็ฉใๆนๆณๅ็ป้ช่ฝฌๅไธบๅฏๅฎ่ฃ ใๅฏๅค็จ็ Agent Skillใ
้กน็ฎ็ฎไป
ๅๅปบๅฏ้ ็ Skill ไธๅชๆฏๆป็ป่ตๆใ็ณป็ป้่ฆๅ็ฐไปปๅกๆ่ฟฐไธญ้ๆผ็ๆกไปถ๏ผ ไปๅ ฌๅผๆฅๆบไธญๆๅๅฏๆง่กๆญฅ้ชค๏ผๅนถๅคๆญๆฏๆก็ป้ชๅฏไปฅๅค็จๅฐๅคๅคง็่ๅดใ
SkillAlchemy ๆฏๆไธ็ฑปไปปๅก๏ผ
- ่ธ้ฆไบบ็ฉ๏ผไปๅ ฌๅผ่ตๆไธญๆๅๅณ็ญๆนๅผใๅคฑ่ดฅๅค็ใไปทๅผๅ่ๅ่กจ่พพ็น็น๏ผ็ๆ Persona Skillใ
- ่ธ้ฆๆนๆณ๏ผๅฐไนฆ็ฑใๆนๆณ่ฎบใๅผๆบไปๅบๆ่ฎฟ่ฐๆด็ไธบๅ ๅซๆกไปถใๆญฅ้ชคใๅๆฏๅๅคฑ่ดฅๅค็็ๅฏๆง่ก Skillใ
- ่ๅ Skill๏ผ็ปๅๅทฒๆ Skill ็ๅทฅไฝๆต็จไธ้ขๅ่ง่ง๏ผๅฝขๆๆฐ็ๅคๅ่ฝๅใ
ๅฎ่ฃ
ๅฎ่ฃ ๅฎๆด็ SkillAlchemy ๅทฅไฝๆต๏ผ
npx skills add agentsope/SkillAlchemy
ไนๅฏไปฅ็ดๆฅๅ่ฏ Claude Code ๆ Codex๏ผ
่ฏทไป https://github.com/agentsope/SkillAlchemy ๅฎ่ฃ
SkillAlchemy๏ผๅนถๅ่ฏๆๅฆไฝไฝฟ็จใ
ไนๅฏไปฅๅ็ฌๅฎ่ฃ ๆ ธๅฟ็ปไปถ๏ผ
npx skills add agentsope/SkillAlchemy/skills/Lens
npx skills add agentsope/SkillAlchemy/skills/LEAP
ๅฎ่ฃ ไปๅบไธญๅ ถไป Skill๏ผ
npx skills add agentsope/SkillAlchemy/skills/<skill-name>
ๆต่งไปๅบไธญ็ๅ จ้จ Skills
ๅฟซ้ๅผๅง
ๅฎ่ฃ ๅ๏ผ็ดๆฅๅ่ฏ Claude Code ๆ Codex ไฝ ๆณ่ธ้ฆๆ่ๅไปไนใไพๅฆ๏ผ
ไฝฟ็จ SkillAlchemy๏ผไปๅ
ฌๅผๆๆกฃๅ่ฎบๆไธญๅๅปบไธไธช็จไบๅฎกๆฅ RAG ็ณป็ป็ Skillใ
SkillAlchemy ๅ
็จ Lens ่กฅๅ
จไปปๅกไธญ็้ๅซ้ๆฑ๏ผๅ็ฑ LEAP ๆถ้่ฏๆฎใ
ๆด็ๅฏๅค็จๆญฅ้ชคๅนถ็ๆ Skill ๅ
ใ็ๆ็ปๆ้ป่ฎคๅๅ
ฅๅฝๅ้กน็ฎ็ output/ใ
ไปๅบ็ปๆ
.
โโโ SKILL.md # SkillAlchemy ไธปๅ
ฅๅฃ
โโโ skills/
โ โโโ Lens/ # ๅ็ฐ้ๅซ้ๆฑ
โ โโโ LEAP/ # ่ธ้ฆใ่ๅๅนถ็ๆ Skill
โ โโโ agentsop-*/ # ๅฏ็ดๆฅๅฎ่ฃ
็ Agent ๅทฅ็จ Skill
โโโ assets/ # README ๅพ็
โโโ package.json
โโโ skill.json
โโโ LICENSE
ๆด่ฏฆ็ป็ๅ ้จๆต็จ่งๆๆฏๆๆกฃใๅไธ่ดก็ฎๅ่ฏท้ ่ฏป CONTRIBUTING.mdใ
่ฎธๅฏ่ฏ
ๆฌ้กน็ฎ้็จ MIT Licenseใ
File tree
261agentsope/SkillAlchemyView on GitHub
.editorconfig
.gitignore
assets/
framework.png
CHANGELOG.md
CONTRIBUTING.md
LICENSE
package.json
README_EN.md
README.md
skill.json
SKILL.md
SkillAlchemy-flow-brief.png
SkillAlchemy.gif
skills/
agentsop-agent-topology-selection/
intermediate/
operation_candidates.json
README.md
references/
R1-source-evidence.md
SKILL.md
agentsop-aider/
intermediate/
operation_candidates.json
README.md
references/
R1-architecture.md
R2-sop-workflow.md
R3-dilemma-cases.md
R4-anti-patterns.md
R5-ecosystem-context.md
SKILL.md
agentsop-bio-fraud-forensics/
examples/
demo_screening.md
README.md
references/
R01-misconduct-taxonomy.md
R02-image-forensics.md
R03-statistical-forensics.md
R04-exposure-sites-method.md
R05-evidence-red-lines.md
R06-screening-workflow.md
R07-paper-mill-signals.md
research_notes.md
sop_models.md
SKILL.md
USAGE.md
agentsop-bounded-loop/
intermediate/
operation_candidates.json
references/
R1-source-evidence.md
R2-cross-framework.md
SKILL.md
agentsop-code-execution-decision/
intermediate/
operation_candidates.json
README.md
references/
R1-source-evidence.md
SKILL.md
agentsop-context-scope-discipline/
intermediate/
operation_candidates.json
README.md
references/
R1-source-evidence.md
SKILL.md
agentsop-conventions-pinning/
intermediate/
operation_candidates.json
README.md
references/
R1-source-evidence.md
R2-tool-equivalents.md
SKILL.md
agentsop-cost-tiered-models/
intermediate/
operation_candidates.json
README.md
references/
R1-source-evidence.md
SKILL.md
agentsop-crewai/
intermediate/
operation_candidates.json
README.md
references/
R1-architecture.md
R2-sop-workflow.md
R3-dilemma-cases.md
R4-anti-patterns.md
R5-ecosystem-context.md
SKILL.md
agentsop-dify/
intermediate/
operation_candidates.json
README.md
references/
R1-architecture.md
R2-sop-workflow.md
R3-dilemma-cases.md
R4-anti-patterns.md
R5-ecosystem-context.md
SKILL.md
agentsop-domain-eval-set/
intermediate/
operation_candidates.json
README.md
references/
R1-source-evidence.md
SKILL.md
agentsop-dspy/
intermediate/
operation_candidates.json
README.md
references/
R1-architecture.md
R2-sop-workflow.md
R3-dilemma-cases.md
R4-anti-patterns.md
R5-ecosystem-context.md
SKILL.md
agentsop-framework-selection/
intermediate/
operation_candidates.json
README.md
references/
R1-decision-tree.md
SKILL.md
agentsop-http-tool-wrapping/
intermediate/
operation_candidates.json
README.md
references/
R1-source-evidence.md
R2-pattern-library.md
SKILL.md
agentsop-hybrid-retrieval/
intermediate/
operation_candidates.json
README.md
references/
R1-source-evidence.md
SKILL.md
agentsop-idempotent-ingestion/
intermediate/
operation_candidates.json
README.md
references/
R1-source-evidence.md
R2-cross-framework.md
SKILL.md
agentsop-langgraph/
intermediate/
operation_candidates.json
README.md
references/
R1-architecture.md
R2-sop-workflow.md
R3-dilemma-cases.md
R4-anti-patterns.md
R5-ecosystem-context.md
SKILL.md
agentsop-llamaindex/
intermediate/
operation_candidates.json
README.md
references/
R1-architecture.md
R2-sop-workflow.md
R3-dilemma-cases.md
R4-anti-patterns.md
R5-ecosystem-context.md
SKILL.md
agentsop-llm-artifact-versioning/
intermediate/
operation_candidates.json
README.md
references/
R1-source-evidence.md
SKILL.md
agentsop-llm-engine-selection/
intermediate/
operation_candidates.json
README.md
references/
R1-source-evidence.md
R2-decision-flowchart.md
SKILL.md
agentsop-llm-tool-idempotency/
intermediate/
operation_candidates.json
README.md
references/
R1-source-evidence.md
R2-pattern-library.md
SKILL.md
agentsop-map-reduce-fanout/
SKILL.md
agentsop-metric-design/
intermediate/
operation_candidates.json
README.md
references/
R1-source-evidence.md
R2-judge-bias-catalog.md
SKILL.md
agentsop-module-shape-selection/
intermediate/
operation_candidates.json
README.md
references/
R1-source-evidence.md
SKILL.md
agentsop-multi-tenant-rag/
intermediate/
research_notes.md
references/
R1-vendor-filter-cheatsheet.md
R2-cross-tenant-test-recipes.md
SKILL.md
agentsop-multiscale-chunking/
intermediate/
operation_candidates.json
README.md
references/
R1-source-evidence.md
SKILL.md
agentsop-observability-setup/
intermediate/
operation_candidates.json
README.md
references/
R1-source-evidence.md
SKILL.md
agentsop-output-format-by-model/
SKILL.md
agentsop-per-model-artifacts/
intermediate/
operation_candidates.json
README.md
references/
R1-source-evidence.md
R2-versioning-recipes.md
SKILL.md
agentsop-prompt-compilation/
intermediate/
operation_candidates.json
README.md
references/
R1-source-evidence.md
SKILL.md
agentsop-prompt-history-inspect/
intermediate/
operation_candidates.json
README.md
references/
R1-mental-model.md
R2-framework-cheat-sheet.md
SKILL.md
agentsop-query-routing/
intermediate/
operation_candidates.json
README.md
references/
R1-source-evidence.md
SKILL.md
agentsop-regression-gate/
intermediate/
operation_candidates.json
README.md
references/
R1-source-evidence.md
SKILL.md
agentsop-repo-map/
intermediate/
operation_candidates.json
README.md
references/
R1-source-evidence.md
R2-cross-tool-comparison.md
SKILL.md
agentsop-repo-state-gating/
intermediate/
operation_candidates.json
README.md
references/
R1-state-taxonomy.md
R2-gate-questions.md
SKILL.md
agentsop-reranker-stage/
intermediate/
operation_candidates.json
README.md
references/
R1-source-evidence.md
SKILL.md
agentsop-selfhost-decision/
intermediate/
operation_candidates.json
README.md
references/
R1-source-evidence.md
SKILL.md
agentsop-session-state-hygiene/
intermediate/
operation_candidates.json
README.md
references/
R1-source-evidence.md
R2-tool-commands.md
SKILL.md
agentsop-signature-design/
intermediate/
operation_candidates.json
README.md
references/
R1-source-evidence.md
SKILL.md
agentsop-state-reducer/
SKILL.md
agentsop-streaming-output/
intermediate/
operation_candidates.json
README.md
references/
R1-source-evidence.md
SKILL.md
agentsop-structured-output-picker/
intermediate/
operation_candidates.json
README.md
references/
R1-source-evidence.md
SKILL.md
agentsop-test-fix-loop/
intermediate/
operation_candidates.json
README.md
references/
R1-source-material.md
R2-feedback-formatting-recipes.md
SKILL.md
agentsop-tool-scoping/
intermediate/
operation_candidates.json
README.md
references/
R1-source-evidence.md
SKILL.md
agentsop-vllm/
intermediate/
operation_candidates.json
README.md
references/
R1-architecture.md
R2-sop-workflow.md
R3-dilemma-cases.md
R4-anti-patterns.md
R5-ecosystem-context.md
SKILL.md
LEAP/
domains/
cybersecurity/
domain.md
energy/
domain.md
finance/
domain.md
healthcare/
domain.md
manufacturing/
domain.md
mathematics/
domain.md
media-content-production/
domain.md
natural-science/
domain.md
office-white-collar/
domain.md
persona-os/
domain.md
robotics/
domain.md
software-engineering/
domain.md
README_EN.md
README.md
references/
skill-grammar.md
scripts/
build_component_index.py
build_corpus.py
download_subtitles.sh
quality_check.py
score_skill.py
... 9 moreFAQ
skillalchemy is a Claude Code plugin with 47 hand-picked skills for development work, indexed on Flowy. Install it with the command on its page. It includes LEAP, Lens, agentsop-agent-topology-selection. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
- What is skillalchemy?
- From thought to skill. From signal to structure.
- How do I install skillalchemy?
- Run these in Claude Code: npx -y skills add agentsope/SkillAlchemy --agent claude-code. Then prompt normally.
- Does skillalchemy auto-invoke its skills?
- Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
- Is skillalchemy free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.