メニュー
Download and analyze PDF files from URLs or local paths — extract text, answer questions, summarize content. Use when analyzing, reading, or extracting information from a PDF.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | analyze-pdf |
| description | Download and analyze PDF files from URLs or local paths — extract text, answer questions, summarize content. Use when analyzing, reading, or extracting information from a PDF. |
| argument-hint | <URL or file path> |
When the user asks to analyze, read, or extract information from a PDF:
URL: Use the pdf-download CLI tool to download and archive the PDF:
bun ~/.pal/skills/analyze-pdf/tools/pdf-download.ts -- <url> [--filename <name.pdf>]
The tool downloads the file, saves it to memory/downloads/{YYYY}/{MM}/{DD}/{filename}.pdf, and returns JSON with the saved path.
Local path: Use the file directly.
Use your native PDF reading capability (e.g. a Read tool or equivalent). Most modern multimodal models can parse PDF content directly — no external dependencies, libraries, or conversion tools are needed.
Do NOT install PDF processing tools (poppler, pdftotext, etc.) unless the user explicitly asks. Native reading is sufficient.
If the Read tool fails to open the PDF (e.g. error mentioning pdftoppm, missing renderer, or unsupported format), fall back to the text-extraction CLI:
bun ~/.pal/skills/analyze-pdf/tools/pdf-read.ts -- <path>
Use the stdout output as the document content and proceed with the user's request as normal.
If pdf-read.ts also fails, stop completely — report the exact errors from both attempts and ask the user how to proceed. Never infer PDF content from filename, metadata, or assumptions.
Follow the user's request. Common tasks:
Rewrites text to remove AI slop and make it sound human: eliminates em-dashes and en-dashes, LLM tell-words (delve, leverage, robust, seamless), 'not just X, it's Y' constructions, rule-of-three padding, boilerplate openers/closers, hedging, and decorative emoji, while preserving meaning and voice. Use when asked to humanize text, de-slop, remove AI dashes or em-dashes, strip AI tells, make writing sound human, or clean AI-generated prose.
Author a NEW skill that ships WITH the PAL repo (committed to assets/skills/ and installed for every downstream user). Use only when working inside the portable-agent-layer repo and adding a shared, general-purpose skill. For a user's own private skill, use create-skill instead.
Create a user-scoped subagent for every installed agent (Claude Code, opencode, Cursor, Copilot) from one merged definition, then install and run the doctor on it. Use when the user asks to create a subagent, add a custom agent, delegate a role to a specialized agent, or "make a subagent that…".
Create a new personal skill for this user, scaffolded into their own ~/.pal/skills/ and linked into every installed agent. Use when the user asks to create a skill, add a capability, build a custom command, or "make a skill that…".
Convert markdown files into a styled PDF. Use when creating a PDF from existing markdown files, combining markdown into a report, or converting .md to .pdf.
Project context management. PROACTIVE — use when the user references a project (by name or as "this repo", "current work"), asks to add/update/complete a project, says "store under a named project", "track this", "what am I working on", "my projects", "my priorities". Also triggered by ISC/ISA terminology — ISC stands for Ideal State Criteria, a project's verifiable done-conditions stored as `ISC-N:` lines in the Criteria section of its ISA.md spec. Phrases like "ISC", "open/opening the ISC", "open ISCs" (unfinished criteria), "create/creating a ticket for a project", "new ticket", or "project ticket" all map here: use `list-isc` to read them, `add-isc` to create one, `complete-isc`/`reopen-isc` to change status.