← all publishers

geronimo-iia

@geronimo-iia source repo

12 published skills

  1. My Skill 2 · geronimo-iia
    Does something useful. Use when the user needs to perform the task. Do not use for unrelated tasks.
    0
    installs
  2. Agentctl · geronimo-iia bundle
    Validate and generate index.json for agent skill and doc hubs, manage hub registry, install/update/remove skills, and manage local agentctl config using agentctl. Use when maintaining hub directories, publishing hub indexes, managing installed skills, or configuring agentctl.
    0
    installs
  3. My Skill · geronimo-iia
    Does something useful. Use when the user needs to perform the task. Do not use for unrelated tasks.
    0
    installs
  4. Oracle · geronimo-iia
    Second-model review pattern: bundle a prompt plus relevant files and send to a separate model for cross-validation, debugging, design checks, or independent analysis. Use when you want an opinion from a different model than the one currently running — debugging hard problems, validating architecture decisions, or getting a fresh read on a refactor.
    0
    installs
  5. Anti Slop · geronimo-iia
    Strip AI slop from written artifacts: KB documents, analysis, synthesis, research notes, technical docs, PR descriptions. Enforces structural writing rules and blocks known slop patterns. Invoke before writing any non-trivial prose artifact. Not for chat responses (caveman mode covers those).
    0
    installs
  6. PDF Parse · geronimo-iia
    Extract text and structure from PDF files into Markdown or plain text. Selects the right tool automatically: xberg for machine-readable PDFs (fast, Rust core, no ML overhead), marker-pdf for scanned or image-heavy PDFs (OCR + layout detection). Includes tool installation, update, and cleanup. Use before any task that requires reading PDF content.
    0
    installs
  7. Summarize · geronimo-iia
    Summarize URLs, local files (PDFs, documents, audio), and YouTube links. Composable pipeline using llm + markitdown + Jina Reader. Supports local models via Ollama. Use when you need a quick one-shot summary without ingesting into the knowledge base.
    0
    installs
  8. Coding Agent · geronimo-iia
    Orchestrate Claude Code (or other coding agents) as background processes for non-interactive work. Use for batch PR reviews, parallel issue fixing with git worktrees, or any multi-agent coding task. Prefer background mode over interactive sessions for programmatic control.
    0
    installs
  9. Kb Conventions · geronimo-iia
    Shared conventions for the agent-knowledge repository: directory layout, confidence annotation markers, KB divergence markers, and analysis frontmatter schema. Read this skill whenever writing or reviewing any KB document. Referenced by research-paper and research-extraction.
    0
    installs
  10. Research Paper · geronimo-iia
    Process an academic paper (PDF or URL) into the agent-knowledge repository. Extracts text, produces a confidence-annotated structured analysis, and integrates findings into the appropriate topic. Use when asked to read, analyse, or integrate a research paper into the knowledge base. Do NOT use for general web pages or blog posts. For multi-source deep extraction, use research-extraction instead.
    0
    installs
  11. Wiki Ingest PDF · geronimo-iia
    Use when adding one or more PDF files as sources in a llm-wiki knowledge base. Covers source folder creation, PDF extraction, structured analysis, index update, and wiki ingest. Triggers on: "add this PDF to the wiki", "ingest this paper", "create a source for this file", "add as source in my wiki".
    0
    installs
  12. Research Extraction · geronimo-iia
    Deep extraction of research corpora into structured knowledge documents using a Workflow-driven subagent/reviewer pattern. Use when you have raw source documents (theses, papers, reports) and need structured extraction across multiple axes (architecture, messages, algorithms, forms, etc.) with confidence-annotated claims, cross-document tracing, and reviewer-gated progression. Do NOT use for single-paper analysis — use research-paper instead.
    0
    installs