file-intel
Run the Gemini file processor on any folder — extracts content from PDF, PPTX, XLSX, DOCX, CSV, JSON, and any text format, then generates Obsidian-ready summaries. Use when asked to "summarise this folder", "run file intel", "process these files", or a folder path is provided and summaries are needed.
What this skill does
# File Intel — Gemini File Processor Runs `scripts/process_files_with_gemini.py` on a folder of files and produces Obsidian-ready summaries. ## Step 1: Get the folder Use `AskUserQuestion`: ``` Question: "Which folder should I process?" Options: 1. "This vault's inbox/" — process the inbox folder 2. "Custom path" — user specifies a folder ``` If the user selects option 2, they'll type the path in the "Other" input. ## Step 2: Run the script Run via Bash from the vault root: ```bash python scripts/process_files_with_gemini.py <folder_path> ``` - If inbox/: `python scripts/process_files_with_gemini.py inbox/` - If custom path: pass it as the argument Show the terminal output as it runs so the user can see files being processed live. ## Step 3: Open the output After the script completes, open the output folder: ```bash open "outputs/file_summaries/YYYY-MM-DD/" ``` Replace `YYYY-MM-DD` with today's date from the script output. ## Step 4: Report back Tell the user: - How many files were processed - Where the summaries landed - Point them to `MASTER_SUMMARY.md` as the single-file digest of everything - Suggest: "Open Claude Code and say: Sort everything in inbox/ into the right folders" ## Notes - Supported formats: PDF, PPTX, XLSX, DOCX, CSV, JSON, XML, MD, TXT, PY, JS, HTML, CSS - Output: `outputs/file_summaries/YYYY-MM-DD/` - Each file gets its own `*_summary.md` - `MASTER_SUMMARY.md` combines all summaries into one digest - Summaries are context-aware: deliverables (invoices, reports) vs reference files (code, config) get different formats --- ## Gotchas - **Encoding detection is best-effort, not deterministic:** Files saved as Windows-1252 or Latin-1 may be processed as garbled UTF-8 instead of failing loudly. Spot-check the first summary of any batch from unknown sources — if accented characters render as mojibake, the source encoding was misdetected. - **Password-protected and encrypted PDFs return blank summaries:** Gemini cannot extract text from locked PDFs but the script does not flag them as failures. Check the file size of each `*_summary.md` — anything under ~200 bytes is suspect. - **Scanned-image PDFs depend on OCR confidence:** Low-DPI scans, handwriting, or rotated pages produce summaries with hallucinated content rather than honest "could not read." Verify scanned documents against the original before trusting downstream decisions. - **XLSX files with multiple sheets summarize only the active sheet:** The processor reads what the workbook opens to by default; other sheets are skipped silently. For multi-sheet financials, split into separate files or expect partial coverage. - **MASTER_SUMMARY.md grows linearly and exceeds context on large folders:** A 200-file inbox produces a digest too large to feed back into another LLM call without truncation. For batches over ~50 files, work from the per-file summaries instead of the master. - **Re-running on the same folder writes to a new `YYYY-MM-DD/` subdirectory:** Two runs on the same day overwrite each other; runs on different days produce duplicates without cross-reference. Clear or archive prior output before re-processing.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.