Astro-Han

@astro-han source repo

17 skills
0 followers
13 hours ago last updated

▌
Office PDF · astro-han bundle
PDF parsing (uv + pdfplumber / pypdf): use this for reading or extracting text/tables from any PDF. PDF generation (author print-ready HTML, then print with PawWork's bundled Chromium) is best-effort — where the runtime exposes no print entry point, report that generation is unavailable rather than substituting another tool. Hard rule: never use PyMuPDF / fitz (AGPL).

0
installs
▌
Office DOCX · astro-han bundle
Native .docx generation and editing with Python python-docx: real Heading styles that drive the navigation pane and table of contents, explicit fonts and sizes, native tables, clean paragraph structure. Also reads and parses existing documents. Use this for any Word document, report, letter, or memo request, and for reading or modifying an existing .docx.

0
installs
▌
Office PPTX · astro-han bundle
Native .pptx generation by authoring one SVG per slide and converting with the bundled offline svg_to_pptx tool — every shape stays natively editable in PowerPoint / Keynote / WPS. Also reads and parses existing decks with python-pptx. Use this for any presentation, pitch deck, slides, or .pptx request, and for reading or modifying an existing .pptx.

0
installs
▌
Office XLSX · astro-han bundle
Native .xlsx generation and editing with Python openpyxl: real formulas the recipient can recalc, explicit number formats and fonts, native charts. Also reads and parses existing workbooks. Use this for any Excel, spreadsheet, or financial-model request, and for reading or modifying an existing .xlsx.

0
installs
▌
Tdd · astro-han
Use test-driven development when requested, or when a clear behavior change has a trustworthy automated seam and test-first feedback is worth its cost. Do not trigger merely for code edits, pure refactors, visual tweaks, configuration, or exploratory work.

0
installs
▌
Eli5 · astro-han
Create simple, beautiful visual explainers for people new to a topic. Use for ELI5 and picture-first requests.

0
installs
▌
Debug · astro-han
Diagnose and fix bugs, failures, and performance regressions. Read this skill BEFORE touching any code whenever the user reports a bug, broken behavior, a crash, wrong output, or a regression — even when the cause looks obvious and the user only asked for a fix. Do not use for a simple explanation of a known error when no diagnosis is requested.

0
installs
▌
Shape · astro-han
Interview the user to resolve material branches of a decision tree and converge on a shared plan before acting. Use when multiple reasonable choices would materially change scope, cost, reversibility, or outcome, or when the user asks to brainstorm, shape, or grill an idea. Do not use when facts can resolve the ambiguity or a reversible assumption would not materially affect the result.

0
installs
▌
Wrap Up · astro-han
Close a session cleanly by resolving session-owned loose ends and reporting the final state. Use when the session is ending or the user asks to wrap up or audit its end.

0
installs
▌
Pr Review · astro-han bundle
Review a pull request or queue from problem value through code correctness. Use for new review, rereview, batch review, or deciding findings and next steps. Do not use to implement feedback, report status, draft, merge, or monitor checks.

0
installs
▌
Craft Skill · astro-han bundle
Create or improve agent skills from concrete behavior and evidence. Use when building or revising SKILL.md, or testing whether a skill earns its context. Do not use for ordinary documentation or one-off prompts.

0
installs
▌
Goal Writer · astro-han bundle
Draft or review minimal, testable goals. Use only when the user explicitly asks to write, revise, or review a goal.

0
installs
▌
Learn Anything · astro-han
Teach with adaptive guidance, retrieval practice, and Socratic questioning. Use when the user wants to study a topic, build durable understanding, practice, or be coached. Do not use for one-off factual answers, quick explanations, or ordinary task guidance.

0
installs
▌
Simplify Audit · astro-han
Audit an existing repository or scoped architecture area for simplification opportunities, separating proven removals from those still blocked on a fact or a decision. Use when asked to find what can be removed or consolidated, reduce codebase-wide maintenance complexity, or identify obsolete or duplicated authorities, states, paths, contracts, or representations. Do not use to implement an already chosen change, fix a bug, optimize performance, or perform general code review without a simplification goal.

0
installs
▌
Review Feedback · astro-han
Adjudicate and act on existing code-review feedback: PR comments, inline threads, or findings from reviewers, review tools, external models, or delegated agents. Use whenever the user asks to fix, address, apply, resolve, respond to, or push back on review comments or findings — even a casual 'fix the review comments' — and before any code edit that review feedback may cause. Do not use to perform a fresh review, diagnose an unrelated bug, implement a new requirement, or merely summarize feedback.

0
installs
▌
Parallel Research · astro-han
Research with parallel agents, independent evidence angles, and cross-validation. Use when the user explicitly asks for parallel or delegated research, or when a high-cost question materially benefits from independent evidence.

0
installs
▌
Karpathy LLM Wiki · astro-han bundle
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.

0
installs

17 published skills