Curate Claude Code's auto-memory into durable project knowledge. Analyze MEMORY.md for patterns, promote proven learnings to CLAUDE.md and .claude/rules/, extract recurring solutions into reusable skills. Use when: (1) reviewing what Claude has learned about your project, (2) graduating a pattern from notes to enforced rules, (3) turning a debugging solution into a skill, (4) checking memory health and capacity.
Proactively preserve critical information before automatic context pruning destroys it.
Maintain structured working notes throughout execution to prevent information loss during context pruning.
Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.
Plan and orchestrate multi-slide PowerPoint creation from scratch. Use before generating a full deck with subagents: classify each slide type, enforce visual variety, set typography/spacing rules, and run text-based QA to catch content issues.
Troubleshoot OpenSandbox issues by running diagnostics (logs, inspect, events, summary) via CLI or HTTP API to diagnose sandbox failures like OOM, crash, image pull errors, network problems, etc.
Identify grammar, logical, and flow errors in text and suggest targeted fixes without rewriting the entire text. Use when proofreading content, checking writing quality, or reviewing a draft.
Fix common issues in geographic data contributions to the CSC database. Use this skill whenever you need to fix, correct, repair, patch, or resolve issues in a data contribution or PR. Trigger on: "@copilot fix this", "auto-fix" label on issues, "can you fix", "please correct", "help me fix", "what's wrong with my PR", removing auto-managed fields, correcting country codes, fixing mismatched foreign keys, or formatting JSON. Also use when a PR has validation errors and you need to commit fixes directly. Read common-fixes.md in this directory for fix patterns and examples.
Triage and classify new issues for the CSC database repository. Use this skill whenever an issue is opened, assigned to you, or needs classification. Trigger on: new issue triage, "classify this issue", "what type of issue is this", labelling requests, issue assignment, data correction reports, data addition requests, bug reports, feature requests, or any time you need to categorise, label, prioritise, or respond to a GitHub issue. Also use when deciding whether an issue can be auto-fixed or needs human intervention.
Fix a GitHub issue on OpenPipe/ART and open a PR. Use when the user asks to fix, solve, or work on an ART issue, or references a GitHub issue URL containing "OpenPipe/ART". Triggers: "fix ART issue", "solve this issue" with an OpenPipe/ART URL, "work on ART #N".
Explore and understand Nx workspaces. USE WHEN answering questions about the workspace, projects, or tasks. ALSO USE WHEN an nx command fails or you need to check available targets/configuration before running a task. EXAMPLES: 'What projects are in this workspace?', 'How is project X configured?', 'What depends on library Y?', 'What targets can I run?', 'Cannot find configuration for task', 'debug nx task failure'.
Triage GitHub issues with codebase research and actionable recommendations
Scan all GDDs against the entity registry to detect cross-document inconsistencies: same entity with different stats, same item with different values, same formula with different variables. Grep-first approach — reads registry then targets only conflicting GDD sections rather than full document reads.
Navigate the Valibot repository structure. Use when looking for files, understanding the codebase layout, finding schema/action/method implementations, locating tests, API docs, or guide pages. Covers monorepo layout, library architecture, file naming conventions, and quick lookups.
Use this skill for requests related to LangGraph in order to fetch relevant documentation to provide accurate, up-to-date guidance.
Structured scratch tracking document for investigation state during bug hunts - prevents re-reading code, losing context, and rabbit holes; maintains external memory so you don't re-derive conclusions
Load when working with the module registry in workerd — reading, modifying, debugging, or reviewing module resolution, compilation, evaluation, or registration code. Provides pointers to three reference documents covering the legacy registry, V8 module internals, and the new registry design.
Use when you need to ask questions about a codebase or understand code using a knowledge graph
UseCase implementation pattern — DI, Result handling, error types, decorators, CMS repositories, entry mappers, and schema-based permissions. Use this skill to implement, inject, override, or decorate any Webiny UseCase, or to build repositories that persist data via CMS.
Webiny project layout, webiny.config.tsx anatomy, and extension registration. Use this skill when the developer asks about folder structure, where custom code goes, how to register extensions, what webiny.config.tsx does, or how the project is organized. Also use when they need to understand the relationship between extensions/, webiny.config.tsx, and the different extension types (Api, Admin, Infra, CLI).
Clean up messy spreadsheet data — trim whitespace, fix inconsistent casing, convert numbers-stored-as-text, standardize dates, remove duplicates, and flag mixed-type columns. Use when data is messy, inconsistent, or needs prep before analysis. Triggers on "clean this data", "clean up this sheet", "normalize this data", "fix formatting", "dedupe", "standardize this column", "this data is messy".
Populates investment banking pitch deck templates with data from source files. Use when: user provides a PowerPoint template to fill in, user has source data (Excel/CSV) to populate into slides, user mentions populating or filling a pitch deck template, or user needs to transfer data into existing slide layouts. Not for creating presentations from scratch.
