Moving this week

Ranked by stars gained over seven days, not by the total. An absolute count tells you what was popular in 2024; a delta tells you what people are picking up now, and it cannot be inherited from a parent repository.

Window This week Today
#ModTypeThis weekStarsScanTokensRating
301 understanding-streamlit-architecturestreamlit/streamlitExplains Streamlit's internal architecture including backend runtime, frontend rendering, and WebSocket communication. Use when debugging cross-layer issues, understanding how features work end-to-end, planning architectural changes, or onboarding to the codebase. Covers ForwardMsg/BackMsg protocol, script rerun… Skill ▲ +15 46k A 75
302 qa-testing-featurestreamlit/streamlitPerforms QA testing on the feature implemented in the current branch. Reads specs, docs, and API docstrings, creates a QA test plan, executes tests using Playwright against a debug server, and generates a report with found issues. Use after implementing a feature to validate it meets requirements before finalizing a… Agent ▲ +15 46k A 67
303 migrate-from-openclawnanocoai/nanoclawMigrate from OpenClaw to NanoClaw v2. Detects an existing OpenClaw installation, extracts identity, channel credentials, scheduled tasks, and other config, then guides interactive migration. Triggers on "migrate from openclaw", "openclaw migration", "import from openclaw". Skill ▲ +15 31k A 71
304 add-dial-toolnanocoai/nanoclawGive chosen NanoClaw agents a real phone number as a container tool — the dial CLI baked into the agent image plus OneCLI credential injection for api.getdial.ai, scoped per agent, so the agents you pick can send SMS, place AI voice calls, and receive verification codes from inside the sandbox. Independent of the Dial… Skill ▲ +15 31k A 117
305 streamlit copilot-instructions.mdstreamlit/streamlitCopilot instructions for streamlit/streamlit, covering streamlit repo overview, tech stack, folder structure, shell & build policy and make commands. Instructions file ▲ +15 46k A 2,238
306 streamlitstreamlit/streamlitAgent settings declaring 4 hook events (SubagentStart, PreToolUse, PostToolUse, Stop) and 25 allowed tools. Settings file ▲ +15 46k A
307 cocoindex AGENTS.mdcocoindex-io/cocoindexAGENTS.md instructions for cocoindex-io/cocoindex, covering agents.md, build and test commands, building, testing and code formatting and linting. Instructions file ▲ +15 11k A 4,372
308 target-connectorcocoindex-io/cocoindexThis skill should be used when creating a new target connector for CocoIndex to integrate with external systems. It provides guidance on implementing TargetHandler, TargetActionSink, and related types for declarative target state synchronization with change detection and automatic cleanup. Skill ▲ +15 11k A 52
309 cocoindexcocoindex-io/cocoindexThis skill should be used when building data processing pipelines with CocoIndex, a Python library for incremental data transformation. Use when the task involves processing files/data into databases, creating vector embeddings, building knowledge graphs, ETL workflows, or any data pipeline requiring automatic change… Skill ▲ +15 11k A 88
310 PreToolUsestreamlit/streamlitRuns before the agent uses a tool for Skill and Bash tool calls, executing log_agent_metrics.py and pre_bash_redirect.py via uv (2 commands). From streamlit/streamlit. Hook ▲ +15 46k A
311 SubagentStartstreamlit/streamlitRuns when a subagent starts, executing log_agent_metrics.py via uv. From streamlit/streamlit. Hook ▲ +15 46k A
312 nanoclaw CLAUDE.mdnanocoai/nanoclawClaude Code instructions for nanocoai/nanoclaw, covering ⚠️ stop — read this first if you are claude ⚠️, nanoclaw, quick context, entity model and two-db session split. Instructions file ▲ +15 31k B 7,210
313 settingsnanocoai/nanoclawA lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs directly on Anthropic's Agents SDK. Settings file ▲ +15 31k A
314 gpt-imagewuyoscar/GPT-Image2-SkillUse this skill whenever a user asks to generate, create, draw, render, or edit images with GPT Image 2 / gpt-image-2, text-to-image, reference-image editing, inpainting, posters, typography, Chinese text, UI mockups, diagrams, or gallery prompts. Analyze the user's prompt, search the bundled Reference Gallery/craft… Skill ▲ +15 5.0k A 120
315 gpt-imagewuyoscar/GPT-Image2-SkillOpenAI GPT Image 2 prompt gallery, image prompt library, agentic skill + CLI. Gallery-first prompt patterns, reference-image editing workflows, and a packaged CLI for skill-capable agent runtimes. Plugin ▲ +15 5.0k A
316 wuyoscar-skillswuyoscar/GPT-Image2-SkillPlugin marketplace listing 1 plugin: gpt-image. Plugin ▲ +15 5.0k A
317 testingcallstack/agent-deviceRepository-specific testing traps you cannot learn from the test runner alone. Executable gate ownership lives in scripts/check-affected/ and scripts/gate/. Agent ▲ +14 4.3k A 0
318 pull-requestscallstack/agent-deviceAgent "pull-requests" from callstack/agent-device, covering pull requests, readiness, rebasing onto a moving main, pr body and reviewing. Agent ▲ +14 4.3k A 0
319 agent-devicecallstack/agent-deviceAutomates Apple-platform apps (iOS, tvOS, macOS), Android devices, and Amazon Vega OS TV apps in Vega Virtual Devices. Use when navigating apps, taking snapshots/screenshots where supported, driving TV remotes, tapping, typing, scrolling, extracting UI info, collecting evidence, or planning agent-device CLI commands. Skill ▲ +14 4.3k A 69
320 android-emulatorcallstack/agent-deviceVerify and debug native, React Native, Expo, or Flutter apps on an Android Emulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an Android virtual device. Skill ▲ +14 4.3k A 65
321 agent-device AGENTS.mdcallstack/agent-deviceAGENTS.md instructions for callstack/agent-device, covering agents.md, incident-derived principles, declaration sites and enforcement, hard repository rules and module and test topology. Instructions file ▲ +14 4.3k A 2,120
322 agent-devicecallstack/agent-deviceMCP server for mobile app automation: verify, control, and debug iOS, Android, TV, and desktop apps. Runs locally from the agent-device npm package. MCP server ▲ +14 4.3k A
323 skill-creatorzhayujie/CowAgentCreate, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task. Skill ▲ +13 47k A 61
324 image-generationzhayujie/CowAgentGenerate or edit images from text prompts. Use when the user asks to create, draw, design, or edit an image, illustration, photo, icon, poster, or any visual content. Skill ▲ +13 47k A 41
325 hive.browser-automationaden-hive/hiveRequired before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues… Skill ▲ +13 11k A 142
326 hive.worker-delegationaden-hive/hiveConcrete patterns for breaking colony work into parallel worker jobs via runplaybook — when fan-out helps, how to model the goal as a tracker table, write the worker skill, author the playbook, pilot, and let convergence retry/resume the gap. Skill ▲ +13 11k A 58
327 wiki-lintAr9av/obsidian-wikiAudit and maintain the health of the Obsidian wiki. Use this skill when the user wants to check their wiki for issues, find orphaned pages, detect contradictions, identify stale content, fix broken wikilinks, or perform general maintenance on their knowledge base. Also triggers on "clean up the wiki", "what needs… Skill ▲ +13 3.3k A 152
328 wiki-queryAr9av/obsidian-wikiAnswer questions by searching the compiled Obsidian wiki. Use this skill when the user asks a question about their knowledge base, wants to find information across their wiki, asks "what do I know about X", "find everything related to Y", or wants synthesized answers with citations from their wiki pages. Also use when… Skill ▲ +13 3.3k A 200
329 aoeagent-of-empires/agent-of-empiresUse when launching, monitoring, or controlling AI coding agents (Claude Code, Codex, OpenCode, etc.) in tmux via Agent of Empires (aoe). Covers creating sessions, capturing agent output, running parallel worktree agents, and organizing work into groups and profiles. Prefer aoe over raw tmux for agent management. Skill ▲ +13 3.2k A 71
330 aoeagent-of-empires/agent-of-empiresManage AI coding agent sessions via Agent of Empires (aoe). Skill ▲ +13 3.2k A 17
331 agent-of-empires AGENTS.mdagent-of-empires/agent-of-empiresAGENTS.md instructions for agent-of-empires/agent-of-empires, covering repository guidelines, where to look, commands, code rules and tests. Instructions file ▲ +13 3.2k A 1,165
332 hiveaden-hive/hiveAgent settings declaring 1 hook event (PostToolUse) and 59 allowed tools. Settings file ▲ +13 11k A
333 hive AGENTS.mdaden-hive/hiveAGENTS.md instructions for aden-hive/hive, covering repository guidelines, coding agent notes, multi-agent safety and change hygiene. Instructions file ▲ +13 11k A 377
334 PostToolUseaden-hive/hiveRuns after a tool call finishes for Edit, Write and NotebookEdit tool calls, running an inline shell check. From aden-hive/hive. Hook ▲ +13 11k A
335 toolsaden-hive/hiveMCP server "tools" as configured in aden-hive/hive. Runs aden_tools.mcp_server with python. MCP server ▲ +13 11k A
336 obsidian-wiki copilot-instructions.mdAr9av/obsidian-wikiCopilot instructions for Ar9av/obsidian-wiki, covering obsidian wiki — copilot context, project overview, key concepts, skills reference and coding conventions. Instructions file ▲ +13 3.3k A 689
337 obsidian-wikiAr9av/obsidian-wikiObsidian Wiki skill-based framework for building and maintaining knowledge bases. Use these rules whenever engaging with the vault, wiki, ingestion, or knowledge management. Cursor rule ▲ +13 3.3k A 636
338 obsidian-wiki AGENTS.mdAr9av/obsidian-wikiAGENTS.md instructions for Ar9av/obsidian-wiki, covering obsidian wiki — agent context, readme translation parity, configuration, targeting a specific vault and vault structure. Instructions file ▲ +13 3.3k B 3,876
339 StopAr9av/obsidian-wikiRuns when the agent finishes a response, executing wiki-stop-capture.sh via bash. From Ar9av/obsidian-wiki. Hook ▲ +13 3.3k A
340 obsidian-wikiAr9av/obsidian-wikiAgent settings declaring 1 hook event (Stop). Settings file ▲ +13 3.3k A
341 captureopenclaw/PeekabooCapture live screens/windows or ingest video; adaptive frames + contact sheet. Command ▲ +12 5.1k A 0
342 clickopenclaw/PeekabooTarget UI elements via peekaboo click. Command ▲ +12 5.1k A 0
343 peekabooopenclaw/PeekabooUse Peekaboo for macOS desktop automation, screenshots, visual UI maps, native accessibility inspection, app/window/menu/dialog control, native app and browser chrome control, browser-page MCP tooling, MCP diagnostics, and Peekaboo repo validation. Use when Codex needs current macOS UI state, direct desktop control… Skill ▲ +12 5.1k A 82
344 convex-cursorrules-prompt-filePatrickJS/awesome-cursorrulesCursor rules for Convex development with best practices. Cursor rule ▲ +12 41k A 6,270
345 engineering-ticket-template-cursorrules-prompt-filePatrickJS/awesome-cursorrulesCursor rules for engineering development with ticket template integration. Cursor rule ▲ +12 41k A 1,997
346 Peekaboo AGENTS.mdopenclaw/PeekabooAGENTS.md instructions for openclaw/Peekaboo, covering repository guidelines, start here, project structure & modules, build, test, and development commands and coding style & naming conventions. Instructions file ▲ +12 5.1k A 1,070
347 crabboxopenclaw/PeekabooUse the Crabbox wrapper for OpenClaw remote validation across Linux, macOS, Windows, and WSL2, including delegated Blacksmith Testbox proof. Report the actual provider and id. Skill ▲ +12 5.1k B 43
348 review-prnrwl/nxDeep code review of a single open PR in nrwl/nx. Checks the PR out only inside an isolated sandbox, then runs four fixed reviewers: implementation (correctness, errors, types, performance), verification (tests, ticket grounding, comments, and docs), approach, and security. A reproduce-verifier executes a runnable… Skill ▲ +11 29k A 118
349 author-migrationnrwl/nxAuthor or scope a first-party Nx migration. Use whenever code removes, renames, or deprecates an option/flag/executor/generator-schema field, changes a default, or bumps a dependency, and someone asks whether existing workspaces need a migration so they don't break on nx migrate/upgrade. Covers writing the colocated… Skill ▲ +11 29k A 176
350 ci-watchernrwl/nxPolls Nx Cloud CI pipeline and self-healing status. Returns structured state when actionable. Spawned by /nx-cloud-ci-monitor command to monitor CI Attempt status. Agent ▲ +11 29k A 37
351 ci-monitornrwl/nxYou are the orchestrator for monitoring Nx Cloud CI pipeline executions and handling self-healing fixes. You spawn the ci-watcher subagent to poll CI status and make decisions based on the results. Command ▲ +11 29k A 0
352 monitor-cinrwl/nxMonitor Nx Cloud CI pipeline and handle self-healing fixes. USE WHEN user says \. Command ▲ +11 29k A 0
353 comment-analyzernrwl/nxUse this agent during PR review to check that a PR's comments and doc-comments are TRUE. It verifies every load-bearing claim in a changed comment against the code it describes, and flags comments the diff left stale. It does not ask for more comments - this repo's committed CLAUDE.md rules default to no comment, so… Agent ▲ +11 29k A 122
354 nx AGENTS.mdnrwl/nxAGENTS.md instructions for nrwl/nx, covering documentation contributions, quick reference, github issue response mode, plan-first mode (default) and immediate implementation mode. Instructions file ▲ +11 29k A 2,038
355 nx CLAUDE.mdnrwl/nxClaude Code instructions for nrwl/nx, covering documentation contributions, quick reference, github issue response mode, plan-first mode (default) and immediate implementation mode. Instructions file ▲ +11 29k A 2,245
356 nxnrwl/nxAgent settings declaring 23 allowed tools. Settings file ▲ +11 29k A
357 obsidian-mind CLAUDE.mdbreferrari/obsidian-mindClaude Code instructions for breferrari/obsidian-mind, covering obsidian mind, skills & capabilities, custom slash commands, vault structure and obsidian cli. Instructions file ▲ +11 4.6k A 9,405
358 nono AGENTS.mdnolabs-ai/nonoAGENTS.md instructions for nolabs-ai/nono, covering nono - development guide, project overview, library vs cli boundary, build & test and build everything. Instructions file ▲ +11 3.9k A 2,506
359 vault-migratorbreferrari/obsidian-mindClassify, transform, and migrate vault content from a source vault into this obsidian-mind instance. Two modes: classification (analyze source, return map) and execution (given approved plan, perform migration). Invoked by /om-vault-upgrade. Agent ▲ +11 4.6k A 58
360 excalidraw-diagrambreferrari/obsidian-mindGenerate Excalidraw diagrams from text content. Supports three output modes - Obsidian (.md), Standard (.excalidraw), and Animated (.excalidraw with animation order). Triggers on "Excalidraw", "diagram", "standard excalidraw", "animate". Skill ▲ +11 4.6k A 67
361 om-vault-upgradebreferrari/obsidian-mindImport and migrate content from an existing Obsidian vault into this obsidian-mind instance. Works with older obsidian-mind versions and arbitrary Obsidian vaults. Command ▲ +11 4.6k A 0
362 mermaid-visualizerbreferrari/obsidian-mindTransform text content into professional Mermaid diagrams for presentations and documentation. Use when users ask to visualize concepts, create flowcharts, or make diagrams from text. Supports process flows, system architectures, comparisons, mindmaps, and more with built-in syntax error prevention. Skill ▲ +11 4.6k A 57
363 om-correctbreferrari/obsidian-mindSweep a corrected fact through the vault — finds every note restating it, applies the correction at the single source, replaces restatements with links, and preserves notes that correctly record what was believed at the time. Command ▲ +11 4.6k A 43
364 correction-sweepbreferrari/obsidian-mindFind every note restating a corrected fact and classify each as authoritative, restatement, or historical. Discovery and judgement only — never edits. Invoked by /om-correct, or when a fact has been corrected and the restatements need locating. Agent ▲ +11 4.6k A 56
365 ctf-webNetw0rkNoob/VulnClawA reference guide for Web Capture the Flag (CTF) security puzzles, especially PHP weaknesses, injections, file inclusion, source-code discovery, and common flag locations. It focuses on concrete challenge techniques rather than general penetration-testing planning. Skill ▲ +11 3.1k A 56
366 osint-reconNetw0rkNoob/VulnClawA knowledge guide for open-source intelligence, or OSINT: collecting information from publicly available sources. It covers servers, websites, domains, and, when appropriate, people. Skill ▲ +11 3.1k A 42
367 obsidian-mindbreferrari/obsidian-mindAgent settings declaring 5 hook events (SessionStart, UserPromptSubmit, PostToolUse, PreCompact). Settings file ▲ +11 4.6k A
368 SessionStartbreferrari/obsidian-mindRuns when a session starts on startup, resume, clear and compact, executing session-start.ts via node with --disable-warning and --experimental-strip-types. From breferrari/obsidian-mind. Hook ▲ +11 4.6k A
369 UserPromptSubmitbreferrari/obsidian-mindRuns when you submit a prompt, before the agent sees it, executing classify-message.ts via node with --disable-warning and --experimental-strip-types. From breferrari/obsidian-mind. Hook ▲ +11 4.6k A
370 cherry-pick-prochatboxai/chatboxCherry-pick commits from chatbox-pro repo to the open chatbox repo, handling mobile-only files, package name differences, and other repo-specific exclusions. Skill ▲ +11 42k A 37
371 obsidian-mind AGENTS.mdbreferrari/obsidian-mindAGENTS.md instructions for breferrari/obsidian-mind, covering obsidian mind, hooks, commands, memory and reaching this vault from another repo. Instructions file ▲ +11 4.6k B 1,145
372 i18n-translatechatboxai/chatboxA translation helper for finding new or affected interface text keys in Chatbox Pro code changes and adding their translations to locale JSON files. Skill ▲ +11 42k A 88
373 CheatSheetSeries AGENTS.mdOWASP/CheatSheetSeriesAGENTS.md instructions for OWASP/CheatSheetSeries, covering non-negotiable rules, 1. sources must be real, read, and supportive, 3. stay in scope — one topic, one pr, one branch, 4. don't duplicate — link instead and 5. architecture over code — for general topics. Instructions file ▲ +11 33k A 1,982
374 review-cheatsheet-prOWASP/CheatSheetSeriesAggressively review an OWASP cheat sheet PR across security, practicality, links/sources, duplication, and language; produce a single MERGE/REQUESTCHANGES/CLOSE verdict. Command ▲ +11 33k A 37
375 qmdbreferrari/obsidian-mindMCP server "qmd" as configured in breferrari/obsidian-mind. Runs .claude/scripts/qmd-mcp.mjs with node. MCP server ▲ +11 4.6k A
376 cheatsheet-duplication-checkerOWASP/CheatSheetSeriesDuplication and placement reviewer for OWASP cheat sheet changes. Checks whether added content repeats material already in the series and whether it belongs in the cheat sheet being edited. Invoked by /review-cheatsheet-pr. Agent ▲ +11 33k A 52
377 cheatsheet-link-auditorOWASP/CheatSheetSeriesLink and source-quality auditor for OWASP cheat sheet changes. Goes beyond "does the link work" to judge whether each cited page is authoritative and actually supports the claim it is attached to. Invoked by /review-cheatsheet-pr. Agent ▲ +11 33k A 56
378 CheatSheetSeries CLAUDE.mdOWASP/CheatSheetSeriesClaude Code instructions for OWASP/CheatSheetSeries, covering claude.md and for maintainers. Instructions file ▲ +11 33k A 112
379 mempalaceMemPalace/mempalaceMemPalace — Local AI memory with 96.6% recall. Semantic search, temporal knowledge graph, palace architecture (wings/rooms/drawers). Free, no cloud, no API keys. Skill ▲ +10 59k A 47
380 mempalace CLAUDE.mdMemPalace/mempalaceClaude Code instructions for MemPalace/mempalace, covering claude.md, the mission, design principles, contributing and setup. Instructions file ▲ +10 59k A 1,683
381 mempalace-taskMemPalace/mempalaceCreate, hand off, claim, execute, and close agent tasks through the MemPalace logstream. Use when the user wants to delegate work, prepare a ready-to-paste task for another agent, receive a MemPalace task id, or explicitly launch a supported headless agent in controlled mode. Skill ▲ +10 59k A 67
382 claw-code AGENTS.mdultraworkers/claw-codeAGENTS.md instructions for ultraworkers/claw-code, covering project knowledge base, structure, where to look, code map and conventions. Instructions file ▲ +10 195k A 1,643
383 AGENTSultraworkers/claw-codeREPL slash-command surface: parsing, spec registry, help rendering, and a handful of in-crate handlers. Single flat src/lib.rs (7k lines). Deps: plugins, runtime, serdejson only. Note: tools depends on commands, not the reverse. Command ▲ +10 195k A 0
384 claude-code-action CLAUDE.mdanthropics/claude-code-actionClaude Code instructions for anthropics/claude-code-action, covering claude.md, commands, what this is, how it runs and key concepts. Instructions file ▲ +10 8.8k A 840
385 mempalace-recall-alwaysMemPalace/mempalaceAlways-on MemPalace recall — search the palace before answering about past work, people, projects, or prior decisions. Cursor rule ▲ +10 59k A 260
386 mempalace-recallMemPalace/mempalaceWhen the user asks about past work, prior decisions, people, projects, or events that may be filed in MemPalace, call mempalacesearch (or mempalacekgquery for relational or time-bound facts) before answering from model memory. Return stored content verbatim; never guess when the palace might know. Cursor rule ▲ +10 59k A 66
387 claw-code CLAUDE.mdultraworkers/claw-codeClaude Code instructions for ultraworkers/claw-code, covering claude.md, detected stack, verification, repository shape and working agreement. Instructions file ▲ +10 195k A 250
388 mempalace-initMemPalace/mempalaceSet up MemPalace — install the package, initialize a palace, register the MCP server with Cursor, and verify everything works. Command ▲ +10 59k A 26
389 mempalaceMemPalace/mempalacePlugin marketplace listing 1 plugin: mempalace. Plugin ▲ +10 59k A
390 mempalaceMemPalace/mempalaceGive your AI a memory — mine projects and conversations into a searchable palace. 45 MCP tools, auto-save hooks, and guided setup. Plugin ▲ +10 59k A
391 mineMemPalace/mempalaceMine projects and conversations into the MemPalace. Supports project files, conversation exports, and auto-classification. Command ▲ +10 59k A 22
392 example-bundledultraworkers/claw-codeExample bundled plugin scaffold for the Rust plugin system. Plugin ▲ +10 195k A
393 sample-hooksultraworkers/claw-codeBundled sample plugin scaffold for hook integration tests. Plugin ▲ +10 195k A
394 performance-revieweranthropics/claude-code-actionUse this agent when you need to analyze code for performance issues, bottlenecks, and resource efficiency. Examples: After implementing database queries or API calls, when optimizing existing features, after writing data processing logic, when investigating slow application behavior, or when completing any code that… Agent ▲ +10 8.8k A 0
395 security-code-revieweranthropics/claude-code-actionUse this agent when you need to review code for security vulnerabilities, input validation issues, or authentication/authorization flaws. Examples: After implementing authentication logic, when adding user input handling, after writing API endpoints that process external data, or when integrating third-party… Agent ▲ +10 8.8k A 0
396 review-pranthropics/claude-code-actionPerform a comprehensive code review using subagents for key areas. Command ▲ +10 8.8k A 4
397 claude-code-actionanthropics/claude-code-actionAgent settings declaring 1 hook event (PostToolUse). Settings file ▲ +10 8.8k A
398 PostToolUseanthropics/claude-code-actionRuns after a tool call finishes for Edit, Write and MultiEdit tool calls, running bunx [email protected] --no-config --write .. From anthropics/claude-code-action. Hook ▲ +10 8.8k A
399 test-serveranthropics/claude-code-actionMCP server "test-server" as configured in anthropics/claude-code-action. Launched with bun simple-mcp-server.ts. MCP server ▲ +10 8.8k A
400 source-command-audit-whitepapersFlorianBruniaux/claude-code-ultimate-guideAudit version freshness, FR/EN parity, and metadata quality of all whitepapers and recap cards. Skill ▲ +10 5.9k A 26

Two mods per repository at most, so one viral repository cannot occupy the chart. Star history starts when a repository is first crawled, so this list becomes meaningful after a week of runs rather than immediately.