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
1 imaging-data-commonsK-Dense-AI/scientific-agent-skillsQuery and download public cancer imaging data from NCI Imaging Data Commons. Invoke for any question about IDC collections, cancer imaging datasets, DICOM data access, radiology (CT, MR, PET) or pathology AI training sets, metadata queries, visualization, or license checks — even when the user doesn't explicitly… Skill ▲ +1,394 40k A 75
2 lab-hardware-cadK-Dense-AI/scientific-agent-skillsDesign custom laboratory hardware as parametric build123d models and export fabrication-ready STEP, STL, and DXF files - microfluidic chips and molds, optomechanical mounts and breadboard adapters, cuvette and microplate holders, tube racks, animal-behavior rigs, and 3D-printed instrument fixtures. Use when a research… Skill ▲ +1,394 40k A 106
3 scientific-agent-skills AGENTS.mdK-Dense-AI/scientific-agent-skillsAGENTS.md instructions for K-Dense-AI/scientific-agent-skills, covering repository guidance, what belongs here, layout, creating a skill and skill title. Instructions file ▲ +1,394 40k A 4,326
4 applyMadsLorentzen/ai-job-searchYou are orchestrating a two-agent job application workflow. The job posting is provided below as $ARGUMENTS (either a URL or pasted text). Command ▲ +967 39k A 0
5 setupMadsLorentzen/ai-job-searchYou are running the onboarding setup for the AI Job Search framework. Your goal is to collect the user's professional information and populate all profile files so the /apply workflow works out of the box. Command ▲ +967 39k A 0
6 scrapeMadsLorentzen/ai-job-searchFinds new job postings matching your profile via installed portal-search CLIs (LinkedIn, local job boards, and any skills added with /add-portal). Deduplicates across runs. Triggers on: job scrape, find jobs, search jobs, new jobs, job search, scrape jobs, /scrape. Skill ▲ +967 39k A 67
7 upskillMadsLorentzen/ai-job-searchCompares tracked job postings against the candidate profile to identify skill gaps and generate a prioritized learning plan with study resources. Triggers on: /upskill, upskill, skill gaps, what should I learn, learning plan. Skill ▲ +967 39k A 48
8 gemini-research-expertMadsLorentzen/ai-job-searchUse this agent when the user needs to perform research tasks, gather information from external sources, or investigate topics that require web searches and synthesis of information. Agent ▲ +967 39k A 37
9 ai-job-search CLAUDE.mdMadsLorentzen/ai-job-searchClaude Code instructions for MadsLorentzen/ai-job-search, covering job application assistant for [yourname], role, candidate profile, identity and education. Instructions file ▲ +967 39k A 2,161
10 ai-job-search AGENTS.mdMadsLorentzen/ai-job-searchAGENTS.md instructions for MadsLorentzen/ai-job-search, covering agent guidelines: ai job search and thin-pointer design (single source of truth). Instructions file ▲ +967 39k A 368
11 ai-job-searchMadsLorentzen/ai-job-searchAgent settings declaring 12 allowed tools. Settings file ▲ +967 39k A
12 systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes. Skill ▲ +583 280k A 21
13 writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment. Skill ▲ +583 280k A 20
14 superpowers CLAUDE.mdobra/superpowersClaude Code instructions for obra/superpowers, covering superpowers — contributor guidelines, if you are an ai agent, pull request requirements, what we will not accept and third-party dependencies. Instructions file ▲ +583 280k A 1,824
15 superpowers-devobra/superpowersDevelopment marketplace for Superpowers core skills library. Plugin ▲ +583 280k A
16 superpowersobra/superpowersCore skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques. Plugin ▲ +583 280k A
17 SessionStartobra/superpowersRuns when a session starts on startup, clear and compact, executing run-hook.cmd. From obra/superpowers. Hook ▲ +583 280k A
18 impeccable CLAUDE.mdpbakaus/impeccableClaude Code instructions for pbakaus/impeccable, covering project instructions for claude, architecture (v3.0+), modes (persuade / operate / read / experience), platform (web / ios / android / adaptive) and artifact staleness and the doctor pass. Instructions file ▲ +538 65k A 9,680
19 impeccable AGENTS.mdpbakaus/impeccableAGENTS.md instructions for pbakaus/impeccable, covering repository guidelines, project structure & module organization, build, test, and development commands, generated provider output policy and sandbox gotchas for codex agents. Instructions file ▲ +538 65k A 3,427
20 impeccable-manual-edit-applierpbakaus/impeccableApplies leased Impeccable live manual copy-edit batches to source and returns canonical Apply results. Agent ▲ +538 65k A 30
21 impeccable-finish-reviewerpbakaus/impeccableReviews a finished Impeccable build against its direction contract, the approved comp, and the chosen world's quality bar, returning an ordered list of material fixes. Agent ▲ +538 65k A 41
22 impeccablepbakaus/impeccableUse when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states.… Skill ▲ +538 65k A 189
23 impeccablepbakaus/impeccablePlugin marketplace listing 1 plugin: impeccable. Plugin ▲ +538 65k A
24 PostToolUsepbakaus/impeccableRuns after a tool call finishes for Edit and Write tool calls, executing hook.mjs. From pbakaus/impeccable. Hook ▲ +538 65k A
25 impeccablepbakaus/impeccableDesign fluency for frontend development. 1 skill with 23 commands (/impeccable polish, /impeccable audit, /impeccable critique, etc.) and curated anti-pattern detection. Plugin ▲ +538 65k A
26 codex AGENTS.mdopenai/codexAGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context. Instructions file ▲ +530 121k A 5,182
27 babysit-propenai/codexBabysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep… Skill ▲ +530 121k A 114
28 imagegenopenai/codexGenerate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output… Skill ▲ +530 121k A 113
29 orchestratoropenai/codexAgent "orchestrator" from openai/codex, covering user updates spec, reviews and general guidelines. Agent ▲ +530 121k A 0
30 mle-workflowaffaan-m/ECCProduction machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks. Skill ▲ +403 245k A 44
31 frontend-patternsaffaan-m/ECCFrontend development patterns for React, Next.js, state management, performance optimization, and UI best practices. Use when building or reviewing React or Next.js components, state, or render performance. Skill ▲ +403 245k A 41
32 code-revieweraffaan-m/ECCExpert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes. Agent ▲ +403 245k A 38
33 architectaffaan-m/ECCSoftware architecture specialist for system design, scalability, and technical decision-making. Use PROACTIVELY when planning new features, refactoring large systems, or making architectural decisions. Agent ▲ +403 245k A 36
34 ECC copilot-instructions.mdaffaan-m/ECCCopilot instructions for affaan-m/ECC, covering ecc for github copilot, core workflow, prompt defense baseline, coding standards and immutability. Instructions file ▲ +403 245k A 1,025
35 eccaffaan-m/ECCPlugin marketplace listing 1 plugin: ecc. Plugin ▲ +403 245k A
36 eccaffaan-m/ECCHarness-native ECC plugin for engineering teams - 68 agents, 286 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses. Plugin ▲ +403 245k A
37 add-language-rulesaffaan-m/ECCWorkflow command scaffold for add-language-rules in everything-claude-code. Command ▲ +403 245k A 20
38 database-migrationaffaan-m/ECCWorkflow command scaffold for database-migration in everything-claude-code. Command ▲ +403 245k A 18
39 firecrawl-buildfirecrawl/firecrawlIntegrate Firecrawl into application code whenever a product, agent, or workflow needs web data inside the app — web search, live search results, page scraping, structured extraction, or browser interaction. Use when building any feature that needs data from the web in code, even if the user does not mention Firecrawl… Skill ▲ +394 175k A 149
40 firecrawl-build-onboardingfirecrawl/firecrawlGet Firecrawl credentials and SDK setup into a project. Use when an application needs FIRECRAWLAPIKEY, when an agent should add Firecrawl to .env, when the user wants to authenticate Firecrawl for app code, or when choosing the first SDK and docs for a new Firecrawl integration. This skill includes its own browser… Skill ▲ +394 175k A 89
41 firecrawl AGENTS.mdfirecrawl/firecrawlAGENTS.md instructions for firecrawl/firecrawl: Firecrawl is a web scraper API. The directory you have access to is a monorepo. Instructions file ▲ +394 175k A 363
42 firecrawl CLAUDE.mdfirecrawl/firecrawlClaude Code instructions for firecrawl/firecrawl: Firecrawl is a web scraper API. The directory you have access to is a monorepo. Instructions file ▲ +394 175k A 413
43 herdr AGENTS.mdherdrdev/herdrAGENTS.md instructions for herdrdev/herdr, covering herdr, scope and audience, universal project rules, principles and multiplicative performance paths. Instructions file ▲ +372 34k A 4,985
44 herdrherdrdev/herdrControl Herdr, a terminal multiplexer for coding agents. Use only when the user explicitly mentions Herdr or asks to use Herdr to inspect or control panes, tabs, workspaces, commands, or another agent. Do not use merely because a task could benefit from a background terminal, delegation, or parallel work. Requires… Skill ▲ +372 34k A 74
45 herdr-throwaway-reproherdrdev/herdrCreate and control a disposable named Herdr session from inside an existing Herdr session. Use for isolated Herdr runtime, pane, terminal, process, API, persistence, or agent reproductions that should be driven through the CLI/API without touching the default session. Skill ▲ +372 34k A 60
46 install-openviking-memoryvolcengine/OpenVikingInstall and configure the OpenViking long-term memory plugin for OpenClaw via natural conversation. Once installed, the plugin automatically captures facts from chats and recalls relevant context before each reply (auto-capture + auto-recall, cross-session). Covers prerequisites, install through OpenClaw's plugin… Skill ▲ +369 35k A 191
47 openviking-context-databasevolcengine/OpenVikingUse OpenViking from OpenClaw through @openviking/openclaw-plugin: long-term memory, session archives, resource and Agent Skill import, semantic recall, recall trace debugging, and externalized tool-result recovery. Prefer this skill when the user wants to use, query, debug, or operate OpenViking context from an… Skill ▲ +369 35k A 95
48 openvikingvolcengine/OpenVikingOpenViking plugins for Claude Code. Plugin ▲ +369 35k A
49 openviking-memoryvolcengine/OpenVikingLong-term semantic memory for Claude Code, powered by OpenViking. Auto-recall relevant memories at session start and capture important information during conversations. Plugin ▲ +369 35k A
50 openviking-memoryvolcengine/OpenVikingUse OpenViking as the durable memory and context backend. Cursor rule ▲ +369 35k A 96
51 SessionStartvolcengine/OpenVikingRuns when a session starts, executing session-start.mjs via node. From volcengine/OpenViking. Hook ▲ +369 35k A
52 UserPromptSubmitvolcengine/OpenVikingRuns when you submit a prompt, before the agent sees it, executing auto-recall.mjs via node. From volcengine/OpenViking. Hook ▲ +369 35k A
53 graphify AGENTS.mdGraphify-Labs/graphifyAGENTS.md instructions for Graphify-Labs/graphify: This project has a graphify knowledge graph at graphify-out/. Instructions file ▲ +322 113k A 90
54 agent-agentruvnet/rufloAgent skill for agent - invoke with $agent-agent. Skill ▲ +270 70k A 13
55 agent-crdt-synchronizerruvnet/rufloAgent skill for crdt-synchronizer - invoke with $agent-crdt-synchronizer. Skill ▲ +270 70k A 25
56 debuggerrtk-ai/rtkUse this agent when encountering errors, test failures, unexpected behavior, or when RTK doesn't work as expected. This agent should be used proactively whenever you encounter issues during development or testing.\n\nExamples:\n\n \nContext: User encounters filter parsing error.\nuser: "The git log filter is crashing… Agent ▲ +233 78k A 0
57 issue-triagertk-ai/rtkIssue triage: audit open issues, categorize, detect duplicates, cross-ref PRs, risk assessment, post comments. Args: "all" for deep analysis of all, issue numbers to focus (e.g. "42 57"), "en"/"fr" for language, no arg = audit only in French. Skill ▲ +233 78k A 70
58 code-reviewerrtk-ai/rtkUse this agent when you need comprehensive code quality assurance, security vulnerability detection, or performance optimization analysis. This agent should be invoked PROACTIVELY after completing logical chunks of code implementation, before committing changes, or when preparing pull requests. Examples:\n\n… Agent ▲ +233 78k A 0
59 audit-codebasertk-ai/rtkRTK Codebase Health Audit — 7 catégories scorées 0-10. Command ▲ +233 78k A 16
60 test-routingrtk-ai/rtkTest RTK command routing without execution (dry-run) - verifies which commands have filters. Command ▲ +233 78k A 17
61 pr-triagertk-ai/rtkPR triage: audit open PRs, deep review selected ones, draft and post review comments. Args: "all" to review all, PR numbers to focus (e.g. "42 57"), "en"/"fr" for language, no arg = audit only in French. Skill ▲ +233 78k A 64
62 rtk CLAUDE.mdrtk-ai/rtkClaude Code instructions for rtk-ai/rtk, covering claude.md, project overview, name collision warning, development commands and build & run. Instructions file ▲ +233 78k A 1,835
63 rtk copilot-instructions.mdrtk-ai/rtkCopilot instructions for rtk-ai/rtk, covering copilot instructions for rtk, using rtk in this session, instead of: use, build, test & lint and pre-commit gate (must all pass before any pr). Instructions file ▲ +233 78k A 846
64 opencode AGENTS.mdanomalyco/opencodeAGENTS.md instructions for anomalyco/opencode, covering branch names, commits and pr titles, style guide, general principles and destructuring. Instructions file ▲ +188 203k A 1,893
65 agents-sdkanomalyco/opencodeBuild AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, or chat applications. Covers Agent class, state management, callable RPC, Workflows integration, and React hooks. Skill ▲ +188 203k A 59
66 cloudflareanomalyco/opencodeComprehensive Cloudflare platform skill covering Workers, Pages, storage (KV, D1, R2), AI (Workers AI, Vectorize, Agents SDK), networking (Tunnel, Spectrum), security (WAF, DDoS), and infrastructure-as-code (Terraform, Pulumi). Use for any Cloudflare development task. Skill ▲ +188 203k A 68
67 OpenHands AGENTS.mdOpenHands/OpenHandsAGENTS.md instructions for OpenHands/OpenHands, covering repository notes, general, repository map — what belongs where, cross-repository boundaries and pr description human check. Instructions file ▲ +113 86k E 27,982
68 bug-triageUntrivial-ai/agent-orchestratorTriage bugs reported in chat/issues, search for duplicates, file or update GitHub issues with full context, and push fix PRs. Skill ▲ +112 11k A 33
69 agent-orchestrator AGENTS.mdUntrivial-ai/agent-orchestratorAGENTS.md instructions for Untrivial-ai/agent-orchestrator, covering agents.md, repo layout, commands, where to look first and distribution. Instructions file ▲ +112 11k A 2,188
70 ao-desktop-devUntrivial-ai/agent-orchestratorLaunch, restart, or troubleshoot the real AO Electron desktop app from this repository; run a checkout against isolated or real local AO data; combine PR branches for local UI review; and diagnose stale Electron processes, port conflicts, or preload bridge mismatches. Use whenever asked to run, open, show, or visually… Skill ▲ +112 11k A 88
71 browserUntrivial-ai/agent-orchestratorInspect and control the current AO session's target-isolated browser. The desktop app must be open. The agent and user share the same live page, cookies, navigation state, and WebContentsView; the runtime remains usable while the Browser panel is hidden. Tabs in this worker share an ephemeral browser profile, while… Command ▲ +112 11k A 0
72 previewUntrivial-ai/agent-orchestratorOpen a URL or workspace file in the desktop browser panel for the current session, or start a deterministic session-owned dev server from an existing .ao/launch.json. Command ▲ +112 11k A 0
73 agent-orchestrator CLAUDE.mdUntrivial-ai/agent-orchestratorClaude Code instructions for Untrivial-ai/agent-orchestrator, covering claude.md, app state lives under /.ao only and design system. Instructions file ▲ +112 11k A 486
74 agentscope copilot-instructions.mdagentscope-ai/agentscopeCopilot instructions for agentscope-ai/agentscope, covering agentscope code review guide, 1. code quality, 2. [must] code security, 3. [must] testing & dependencies and 4. code standards. Instructions file ▲ +108 30k A 741
75 headroom-marketplaceheadroomlabs-ai/headroomPlugin marketplace listing 1 plugin: headroom. Plugin ▲ +94 68k A
76 headroom copilot-instructions.mdheadroomlabs-ai/headroomCopilot instructions for headroomlabs-ai/headroom: When performing a pull request review in this repository. Instructions file ▲ +94 68k A 138
77 headroomheadroomlabs-ai/headroomHeadroom startup hooks for Claude Code and GitHub Copilot CLI. Plugin ▲ +94 68k A
78 SessionStartheadroomlabs-ai/headroomRuns when a session starts on startup and resume, running headroom init hook ensure. From headroomlabs-ai/headroom. Hook ▲ +94 68k A
79 PreToolUseheadroomlabs-ai/headroomRuns before the agent uses a tool for Bash and PowerShell tool calls, running headroom init hook ensure. From headroomlabs-ai/headroom. Hook ▲ +94 68k A
80 autoresearchAgriciDaniel/claude-obsidianRun a bounded, source-grounded research loop, draft a cited dossier, and optionally propose a separately reviewed canonical vault merge. Use when the user wants autonomous or deep research that may access the public web. Triggers: /autoresearch, autoresearch, research this topic, deep dive into, investigate, find… Skill ▲ +90 14k A 80
81 wiki-ingestAgriciDaniel/claude-obsidianIngest supplied source material into an Obsidian vault with provenance and claim tracking: pasted text, files staged in the selected vault's inbox or .raw archive, or explicitly approved URLs. Use for a single source or bounded batch, not for saving an assistant answer. Triggers: ingest, ingest this file, ingest this… Skill ▲ +90 14k A 88
82 verifierAgriciDaniel/claude-obsidianFresh-context, read-only verifier for a proposed claude-obsidian change or release. Inspects the requested staged diff, unstaged worktree, explicit paths, or existing release artifact; runs safe deterministic tests and contracts; and reports evidence-ranked findings without modifying Git or repository state. Agent ▲ +90 14k A 60
83 wiki-ingestAgriciDaniel/claude-obsidianRead-only ingestion worker for one already-captured source. Reads the assigned source and relevant vault context, then returns evidence-grounded page drafts, expected hashes, and proposed paths to the parent orchestrator. It never writes or applies the shared transaction. Agent ▲ +90 14k A 53
84 claude-obsidianAgriciDaniel/claude-obsidianPortable rules for the claude-obsidian product and user vault workflows. Cursor rule ▲ +90 14k A 265
85 claude-obsidian GEMINI.mdAgriciDaniel/claude-obsidianGemini CLI instructions for AgriciDaniel/claude-obsidian: Read AGENTS.md as the canonical host-neutral contract. Skills live in skills/ /SKILL.md and the portable core lives in claudeobsidian/. Instructions file ▲ +90 14k A 219
86 claude-obsidian AGENTS.mdAgriciDaniel/claude-obsidianAGENTS.md instructions for AgriciDaniel/claude-obsidian, covering claude-obsidian: agent instructions, product and vault boundaries, bootstrap, canonical skills and mutation protocol. Instructions file ▲ +90 14k A 1,123
87 agricidaniel-claude-obsidianAgriciDaniel/claude-obsidianAudited public distribution channel for claude-obsidian. Plugin ▲ +90 14k A
88 claude-obsidianAgriciDaniel/claude-obsidianLocal-first Agent Skills package and Claude Code plugin for source-cited Obsidian knowledge bases. Provides explicit vault initialization and adoption, recoverable operation transactions, deterministic lint and retrieval, provenance ledgers, offline-first capture foundations, and optional methodology modes. User… Plugin ▲ +90 14k A
89 SessionStartAgriciDaniel/claude-obsidianRuns when a session starts on startup, resume, clear and compact, running python3. From AgriciDaniel/claude-obsidian. Hook ▲ +90 14k A
90 StopAgriciDaniel/claude-obsidianRuns when the agent finishes a response, running python3. From AgriciDaniel/claude-obsidian. Hook ▲ +90 14k A
91 gitnexus-guideTabularisDB/tabularisUse when the user asks about GitNexus itself — available tools, how to query the knowledge graph, MCP resources, graph schema, or workflow reference. Examples: "What GitNexus tools are available?", "How do I use GitNexus?". Skill ▲ +83 4.6k A 56
92 tabularis-plugin-driverTabularisDB/tabularisUse when creating or updating a Tabularis database driver plugin in Rust. Covers modern manifest fields, JSON-RPC over stdio, modular plugin layout, MySQL-level feature coverage targets, optional UI extensions, and validation against Tabularis repo rules. Skill ▲ +83 4.6k A 57
93 tabularis AGENTS.mdTabularisDB/tabularisAGENTS.md instructions for TabularisDB/tabularis, covering agents.md, directives, gitnexus — code intelligence, always do and never do. Instructions file ▲ +83 4.6k A 857
94 agent-buildershareAI-lab/learn-claude-codeDesign and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI system" (2) want to understand agent architecture, agentic patterns, or autonomous AI (3) need help with capabilities, subagents, planning, or skill mechanisms (4) ask about Claude Code… Skill ▲ +82 76k A 125
95 code-reviewshareAI-lab/learn-claude-codePerform thorough code reviews with security, performance, and maintainability analysis. Use when user asks to review code, check for bugs, or audit a codebase. Skill ▲ +82 76k A 35
96 skills AGENTS.mdvercel-labs/skillsAGENTS.md instructions for vercel-labs/skills, covering agents.md, project overview, commands, architecture and update checking system. Instructions file ▲ +81 30k A 1,627
97 publish-clicline/clineUse when preparing, tagging, and publishing an apps/cli npm release. Guides changelog drafting, apps/cli/package.json version bumps, cli-vX.Y.Z tags, local npm publishing, and the publish-cli GitHub workflow. Skill ▲ +79 67k A 50
98 publish-desktopcline/clineUse when preparing, tagging, and publishing a Cline desktop app (apps/examples/desktop-app) release — stable (desktop-vX.Y.Z from main) or beta (desktop-vX.Y.Z-beta.N from desktop-experimental, shipped as the side-by-side "Cline Beta" app). Guides changelog drafting, version bumps in package.json + tauri.conf.json… Skill ▲ +79 67k A 107
99 cline AGENTS.mdcline/clineAGENTS.md instructions for cline/cline, covering cloud agent instructions, cline cli, build / lint / test, gui display and vs code extension (apps/vscode, package claude-dev). Instructions file ▲ +79 67k A 1,407
100 cline copilot-instructions.mdcline/clineCopilot instructions for cline/cline, covering copilot instructions for cline, architecture, build & test (critical — non-obvious commands), protobuf rpc workflow (4 steps) and adding api providers (silent failure risk). Instructions file ▲ +79 67k A 976

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.