3.6K skills · sorted by popularity
Document a solved and verified problem when its reasoning is missing from code, tests, and existing documentation. Save one durable lesson in the repository so future agents can find it and avoid repeating substantial investigation.
Audit saved project learnings against the current codebase to find outdated explanations, overlapping documents, and contradictions. Maintain the documentation with evidence-based updates, consolidation, replacement, or deletion, and deliver a per-document report with committed changes when applicable.
Share Markdown specs, plans, and drafts through Proof, a collaborative document editor. Read shared documents, add comments or tracked suggestions, edit text, and pull documents into local files, with confirmation of each requested operation.
Review an existing requirements document, plan, or specification from several role-based perspectives. Identify inconsistencies and obstacles to carrying out the work, verify their consequences, apply authorized corrections, and present improvements or decisions that still need attention.
Convert office documents, spreadsheets, presentations, ebooks, and PDFs into Markdown text that an agent can read. Save large conversions to a file and use hosted text recognition for scanned PDF pages when needed.
Reorganize NemoClaw documentation into focused pages with clearer navigation and a single home for each topic. Plan or implement structural changes while preserving useful information and existing published URLs, then validate routes, links, and builds.
Update NemoClaw documentation after merged changes or audit it for outdated guidance. Verify current behavior against source and tests, edit the pages responsible for that guidance, and check affected links and generated variants.
Draft a NemoClaw release announcement from verified GitHub tags and shipped pull requests. Produce a local Markdown draft with an opening narrative, categorized changes, visible pull request links, and thanks to external contributors.
Create and update Handsontable guide pages with consistent page metadata, headings, framework-specific examples, and sidebar entries. Follow the documentation site's writing conventions and generate JavaScript examples from TypeScript sources where required.
Turn recorded or starred procedures into reusable guides based on captured evidence. Organize prerequisites, steps, expected results, branches, and final checks, while clearly marking missing details and removing private information from examples.
Create charts, dashboards, scorecards, and styled summaries as standalone HTML reports for the screenpipe viewer. Keep styles, scripts, and images inside the file so the report renders in a sandbox with no network access.
Review a specific meeting’s notes and transcript to summarize decisions, commitments, named owners, and stated deadlines. Keep proposals and completed work separate, flag recording gaps, and draft a concise follow-up message when requested.
Edit patch release notes for GitHub Enterprise Server, correcting typos and style while preserving approved technical facts. Keep repeated notes consistent across versions and update known issue source comments so future releases inherit the same edits.
Find recurring questions in resolved Plain support tickets that existing knowledge articles do not cover. Draft articles from actual resolutions, avoid previously drafted topics, and open a pull request for human review.
Review PDF and Office documents for language errors, contradictions, confidential information, factual inaccuracies, and calculation mistakes. Produce an annotated copy with issue severity and suggested corrections, using external sources and calculations where needed.
Draft release notes from merged pull requests for releases that have already shipped. The skill filters internal changes, groups user-facing updates, matches the existing changelog style, and opens a pull request for human review.
Create and edit PDFs, combine or split pages, extract text, tables, and images, and fill forms. It also guides scanned document text recognition and format conversion, choosing tools suited to each task.
Convert office documents, spreadsheets, presentations, ebooks, and text-based PDFs into GitHub-Flavored Markdown, a plain-text format supporting tables. Make otherwise unreadable source files available for an agent to read and use in a task.
Create and edit Excel workbooks for data analysis, reports, and financial models. Build formulas that update with inputs, organize sheets, add charts and interactive pivot tables, and recalculate the workbook to check for formula errors.
Create, edit, extract, convert, and review Word documents while preserving styles, tracked edits, and live references. Support business document workflows, including PDF conversion, with text checks and page previews before handing over files.
Keep project documentation aligned with recent code changes. Review commits since the last checkpoint, update affected guides and README files, and open a pull request for human review only when documentation needs correcting.
Build presentation slides in HTML, preview them in a browser, and export PDF or PPTX files. Also create fully editable PowerPoint decks or modify existing templates, with checks for content, layout, and rendering issues.
Add or review research paper entries in TRL’s paper index. Organize each paper’s contribution, its connection to the implementation, and a Python configuration example using training settings supported by the paper.
Turn completed research, analysis, reports, or plans from the current session into a self-contained HTML artifact. A renderer controls layout, typography, and color, using structured content and a choice of two visual styles.