← all publishers

closedloop-technologies

@closedloop-technologies source repo

31 published skills

  1. Evolving Solutions · closedloop-technologies
    Recombine proven parts of multiple evaluated attempts into a coherent follow-up attempt. Use when ClimbHill attempt comparison reveals complementary partial wins.
    1 install
  2. Deep Research Custom Data · closedloop-technologies bundle
    Build and validate custom-corpus inputs for deep research from Google Docs, YouTube, local files, S3, arXiv, databases, Slack, email, tickets, and similar non-web sources. Use when preparing private or domain-specific source manifests, validating source safety, or turning custom data into cited research inputs.
    1 install
  3. Deep Research Okf Normalize · closedloop-technologies bundle
    Normalize raw deep research outputs into a compact Open Knowledge Format bundle with source, finding, uncertainty, method, index, and log concepts. Use after provider runs when reports need portable structured markdown and citation-preserving validation.
    1 install
  4. Deep Research Gpt Researcher · closedloop-technologies bundle
    Run GPT Researcher as a self-hosted open-source deep research framework using an LLM plus a search provider. Use when a task needs inspectable local report generation, configurable retrievers, or comparison against commercial research APIs.
    1 install
  5. Deep Research Stanford Storm · closedloop-technologies bundle
    Run Stanford STORM for perspective-driven, article-style deep research reports with retriever-backed citations. Use when a task needs Wikipedia-like synthesis, outline-driven research, or comparison against heavier open-source research frameworks.
    1 install
  6. Experiment Tree Analysis · closedloop-technologies
    Analyze ClimbHill runs, attempts, lineage, costs, failures, and recurring constraints. Use for experiment-history diagnosis and evidence-backed follow-up proposals.
    1 install
  7. Resource Grounded Coding · closedloop-technologies
    Ground implementation decisions in recorded ClimbHill resources and cited prior work. Use when code changes should trace back to research, guidance, postmortems, or experiment evidence.
    1 install
  8. Protected Surface Editing · closedloop-technologies
    Classify proposed paths and enforce denied or approval-required ClimbHill policy before edits. Use when work may touch tests, CI, infrastructure, secrets, or other protected surfaces.
    1 install
  9. Parallel Coding Agent Loop · closedloop-technologies
    Coordinate independent, bounded coding attempts against one goal and compare them after policy and evaluation checks. Use for parallel ClimbHill improvement attempts.
    1 install
  10. Progressive Fidelity Tool Routing · closedloop-technologies
    Choose between exact rules, cached results, Tool Shadows, reduced tools, authoritative tools, and physical tests using cost, latency, uncertainty, decision stakes, and evidence freshness.
    1 install
  11. Cost And Progress Reporting · closedloop-technologies
    Produce evidence-backed run and attempt reports with evaluations, costs, risks, and promotion recommendations. Use at the end of a ClimbHill run or attempt attempt.
    1 install
  12. Historical Attempt Sampling · closedloop-technologies
    Sample successful and failed historical ClimbHill Attempts before planning new work. Use when prior Runs may contain reusable approaches or known failure modes.
    1 install
  13. Human In The Loop Promotion · closedloop-technologies
    Review policy, evaluations, cost, lineage, and risk before recording a human promotion or rejection decision. Use when a ClimbHill attempt is ready for disposition.
    1 install
  14. Meta Analysis To Github Issues · closedloop-technologies
    Convert evidence-backed ClimbHill experiment findings into reviewable GitHub issue proposals. Use after experiment-tree analysis identifies actionable repository improvements.
    1 install
  15. Prepare Codebase For Recursive Optimization · closedloop-technologies
    Prepare a repository for controlled recursive optimization by defining goals, agent guidance, policies, evaluations, resources, and protected surfaces. Use when a codebase lacks ClimbHill support files.
    1 install
  16. Climbhill Repository Preparedness · closedloop-technologies
    Prepare a repository with goals, agent guidance, policies, evaluations, resources, and protected surfaces for controlled optimization. Use when setting up or auditing ClimbHill support files.
    1 install
  17. Tool Shadow · closedloop-technologies
    Design an explicit, uncertainty-aware approximation of an expensive or long-running tool so agents can explore and reason quickly without confusing prediction with verification.
    1 install
  18. Reasoning · closedloop-technologies bundle
    Resolve important uncertainty with a small set of evidence-oriented reasoning primitives and reusable workflows. Use when a decision should be driven by research, experiments, observations, or explicit falsification rather than more unaided reasoning.
    1 install
  19. Deep Research Exa · closedloop-technologies bundle
    Run Exa-backed deep research, neural search, and page-content retrieval with bounded result and page-read counts. Use when a task needs Exa Search, Exa Contents, or Exa Research inside a source-discovery or benchmark workflow.
    1 install
  20. Deep Research You · closedloop-technologies bundle
    Run You.com Research API or You.com MCP-backed deep research with explicit research_effort and cost controls. Use when a task needs You.com research, ARI-style workflows, finance research options, or benchmark comparison.
    1 install
  21. Deep Research Jina · closedloop-technologies bundle
    Use Jina Reader and Jina Search APIs for deep research retrieval, URL-to-markdown conversion, and markdown-oriented search results. Use when a workflow needs clean page extraction, search snippets, or reader output before synthesis.
    1 install
  22. Deep Research Gemini · closedloop-technologies bundle
    Run Google Gemini deep research and search-grounded Gemini research tasks with bounded scope and captured outputs. Use when research should rely on Gemini, Google Search grounding, or Google-hosted document context.
    1 install
  23. Deep Research Openai · closedloop-technologies bundle
    Run OpenAI deep research models through the Responses API with explicit effort, model, cost, and output controls. Use when launching citation-backed OpenAI research runs, smoke-testing OpenAI provider behavior, or capturing reproducible benchmark output.
    1 install
  24. Deep Research Tavily · closedloop-technologies bundle
    Use Tavily Search API for bounded deep research retrieval, RAG-ready snippets, and low-cost web search. Use when a workflow needs search grounding, source discovery, or benchmarkable retrieval rather than full report-writing.
    1 install
  25. Deep Research Xai Grok · closedloop-technologies bundle
    Run xAI Grok research with optional web and X search tools for current-event, social, market, or news-oriented research. Use when a task needs Grok-backed synthesis, X-aware source discovery, or provider comparison.
    1 install
  26. Deep Research API Calls · closedloop-technologies
    Prepare and run bounded calls across deep research provider APIs with explicit cost limits, API-key sources, benchmark prompts, and output capture. Use when comparing providers, creating reproducible API commands, or normalizing raw provider outputs after a research run.
    1 install
  27. Deep Research Langchain · closedloop-technologies bundle
    Run LangChain Open Deep Research or LangGraph-based iterative research workflows with configurable retrieval, reflection, and server-backed execution. Use when a benchmark or task needs inspectable graph orchestration rather than a single hosted research API.
    1 install
  28. Tool Shadow Calibration · closedloop-technologies
    Evaluate, challenge, calibrate, and improve a Tool Shadow using authoritative results, physical outcomes, active learning, and decision-aware metrics rather than average prediction error alone.
    1 install
  29. Deep Research Perplexity · closedloop-technologies bundle
    Run Perplexity Sonar and Sonar Deep Research for web-grounded answers with citations and bounded search context. Use when a research task needs current web synthesis through Perplexity or comparison against other provider APIs.
    1 install
  30. Deep Research Smolagents · closedloop-technologies bundle
    Run Hugging Face Smolagents as a code-as-action deep research agent with optional web search and model backends. Use when a benchmark needs explicit intermediate tool actions, code execution, or an open-source agent framework.
    1 install
  31. Notagenius · closedloop-technologies bundle
    Turn a raw product or service idea into an evidence-backed, economically plausible service through JTBD discovery, competing bets, experiments, value-path design, outcome measurement, and falsification. Use when deciding whether an idea deserves investment, what evidence to gather next, or whether to continue, revise, return, or stop.
    1 install