Pick your Claude skills

Presentation Day

Turn a rough doc or idea into a full slide deck, apply a consistent theme, and drop in diagrams and infographics. It even validates the exported .pptx, so last-minute decks still land clean.

Blog Publishing Day

Clean a messy draft into readable Markdown, then generate a cover image and a visually consistent illustration set. Fact-check the claims and translate it so the post is ready for every channel you publish to.

Code Review Day

Hostile reviewer personas and parallel sub-agents tear into your diff so no lazy LGTM slips through. Tech debt, security holes, AI code smells, commit hygiene and CI status all get checked before merge.

Data Cleanup Day

Profile CSV, Parquet and JSON at speed with DuckDB/Polars and surface missingness, outliers and leakage first. Then run the right statistical test, plot it honestly, and ship an Excel report with the findings.

Paper Writing Day

Pull evidence from 11 scholarly APIs, normalize citations into validated BibTeX, and build a claim-to-source evidence matrix. Report your stats in APA form, format for the venue, and run a structured self peer review before submission.

Document Pile Day

Convert PDFs, Word and PowerPoint files into clean Markdown, then extract tables, merge, split and OCR as needed. Phone photos of paper become scanner-quality PDFs, and finished work exports back out as polished PDF or self-contained HTML.

Ship the UI Day

Design interfaces with a real point of view instead of templated defaults, then prove they work with screenshots from a live browser. Accessibility violations, responsive breaks and state bugs get caught before you call it done.

Long Project Kickoff

Keep plan, findings and progress in on-disk Markdown so multi-week work survives /clear and compaction. Fan out parallel research for cited evidence, recover interrupted sessions, and distill whatever you repeat into a reusable skill.

Launch Marketing Day

Rewrite content so answer engines cite you, then generate ad copy that fits each platform's limits. Wire up GA4/GTM tracking, design a statistically valid A/B test, and close the loop with attribution and ROAS analysis.

Minutes & Memo Day

Turn a raw transcript into evidence-backed minutes with decisions, owners and action items, then spin it into an internal update. Co-author proposals and specs, edit real .docx files, add Mermaid diagrams, and roll it up into a board deck.

Anthropic's official skill for building new Claude Code skills, testing them with evals and benchmarks, and tuning descriptions for reliable triggering.

Lets Claude drive a real browser to navigate sites, fill forms, capture screenshots and extract page data.

Analyzes CSV, Parquet and JSON data at maximum speed by intelligently routing between DuckDB and Polars — never pandas.

Search and rewrite code across 25 languages by syntax shape (AST) instead of text, with a safe two-pass codemod workflow.

Drive a real browser from Claude via the agent-browser CLI for navigation, form filling, screenshots, and data extraction.

Manus-style persistent planning that keeps task_plan.md, findings.md, and progress.md on disk so work survives /clear and context compaction.

A Manus-style skill that keeps your plan, findings, and progress in markdown files on disk so work survives /clear, compaction, and context loss.

Keeps plan, findings and progress in on-disk markdown files so multi-step work survives context loss and /clear.

Turns a chaotic stream of thoughts, tasks, and ideas into a four-section actionable system with zero information loss.

Sizes ops headcount, flags utilization risk, and sequences a 12-month hiring plan using Erlang-C queueing math.

Runs medical-device CAPA investigations end to end: root cause analysis, action planning, effectiveness verification and program metrics.

Marketing analysis skill that runs multi-touch attribution, funnel drop-off analysis, and ROI/ROAS/CPA math on your JSON campaign data.

Pressure-tests any AI plan with six CAIO questions covering eval sets, hallucination SLOs, EU AI Act tiering, cost trajectory and AI hiring.

An index and router skill that maps 33 C-suite advisory skills and points you to the right entry point.

A virtual C-suite of 13 executive personas and 21 /cs:* commands that pressure-test founder decisions end to end.

Routes internal-operations questions to one of six BizOps sub-skills — process, vendor, capacity, comms, knowledge, procurement — and returns a ≤200-word digest.