TanStack

105 mods across 5 repositories, 34k stars between them.

global-filtering

25

TanStack/table

Skill Claude CodeCodex

Apply globalFilter across eligible columns with globalFilteringFeature, columnFilteringFeature, filteredRowModel, globalFilterFn, and manual server filtering. Load when columns unexpectedly participate or a global filter changes state without changing rows.

28k 2d ago A 47 tokens original MIT

grouping

26

TanStack/table

Skill Claude CodeCodex

Group rows with columnGroupingFeature, groupedRowModel, groupedColumnMode, and manualGrouping. Load for grouped or placeholder cells and grouping interactions with expansion or pagination.

28k 2d ago A 36 tokens original MIT

pagination

27

TanStack/table

Skill Claude CodeCodex

Paginate with rowPaginationFeature and paginatedRowModel or manualPagination. Load for pageIndex/pageSize state, rowCount/pageCount, unknown next-page limits, already-paginated server data, or autoResetPageIndex surprises.

28k 2d ago A 49 tokens original MIT

row-pinning

28

TanStack/table

Skill Claude CodeCodex

Pin stable row IDs into top, center, and bottom collections with rowPinningFeature and keepPinnedRows. Load for filtering/pagination visibility, explicit region rendering, or renderer-owned sticky CSS.

28k 2d ago A 43 tokens original MIT

row-selection

29

TanStack/table

Skill Claude CodeCodex

Maintain rowSelection ID state with stable getRowId, single, multi, subrow, and Shift-range rules, selected row models, handler anchors, and manual-pagination semantics. Load when implementing getToggleSelectedHandler, enableRowRangeSelection, selectChildren, deselectParents, or selected IDs that outlive loaded Row…

28k 2d ago A 68 tokens original MIT

sorting

30

TanStack/table

Skill Claude CodeCodex

Sort with rowSortingFeature, sortedRowModel, sortFns, multi-sort and removal options, sortUndefined, and manualSorting. Load for comparator direction, incoming server order, or product-specific sorting cycles.

28k 2d ago A 43 tokens original MIT

table-features

31

TanStack/table

Skill Claude CodeCodex

Register TanStack Table v9 tableFeatures, feature plugins, createRowModel factories, and function registries in prerequisite order. Load when an option, state slice, or instance API is missing, or when choosing explicit features versus stockFeatures.

28k 2d ago A 53 tokens original MIT

typescript

32

TanStack/table

Skill Claude CodeCodex

Preserve TanStack Table v9 inference with createColumnHelper, columns(), tableOptions, tableFeatures, and metaHelper. Load for ColumnDef errors, reusable tables, typed meta, named registries, or unnecessary manual feature generics.

28k 2d ago A 50 tokens original MIT

bugfix-pr

33

TanStack/ai

Skill Claude CodeCodex

Treats bug-fix pull requests as invasive and untrusted. The agent must security-scan the PR first, must not run any command supplied by the author or issue, must reproduce the claimed bug on clean main with an agent-written repro, and must reject hunks that are not required to kill that bug. The agent must…

3.0k 2d ago A 188 tokens original MIT

docs

34

TanStack/ai

Skill Claude CodeCodex

Use when writing, editing, or organizing documentation, when planning what docs a feature needs, and whenever planning or implementing a new feature or change in a repo (docs ship with the code). Also use when tempted to write docs without showing the discovered readers to the user, without asking for tone, or without…

3.0k 2d ago A 118 tokens original MIT

gap-analysis

35

TanStack/ai

Skill Claude CodeCodex

Audit TanStack AI provider adapters for feature parity gaps and outdated model lists. Triggered as /gap-analysis |models|--all>. Produces a dated markdown report under .agent/gap-analysis/. Maintainer tool — does not edit feature-support.ts or model-meta.ts directly.

3.0k 2d ago A 65 tokens original MIT

i-have-adhd

36

TanStack/ai

Skill Claude CodeCodex

Use when the user invokes /i-have-adhd, says they have ADHD, or asks for ADHD-friendly output. Also used as a required writing filter by the docs skill. Don't use for marketing copy or after the user says "stop adhd mode" or "normal mode".

3.0k 2d ago C 63 tokens copy · 88% MIT

ponytail

37

TanStack/ai

Skill Claude CodeCodex

Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports…

3.0k 2d ago A 138 tokens original MIT

pr-description

38

TanStack/ai

Skill Claude CodeCodex

Use when writing a pull request title or body, when about to run gh pr create, when about to git push on a branch that already has an open PR, or when the user says /pr-description, "write the PR description", or "update the PR title". Don't use for commit messages, changelogs, or review comments.

3.0k 2d ago A 72 tokens original MIT

simple-english

39

TanStack/ai

Skill Claude CodeCodex

Write or rewrite technical text with the rules of ASD-STE100 Simplified Technical English so it is clear, unambiguous, and free of AI slop. Use for documentation, READMEs, runbooks, procedures, error messages, release notes, incident reports, and API guides. Also use when the user says "STE", "Simplified Technical…

3.0k 2d ago A 149 tokens copy · 81% MIT

triage-github

40

TanStack/ai

Skill Claude CodeCodex

Triage all open GitHub issues, PRs, and discussions in the current repository by fanning out up to 100 parallel subagents (one per item), then produce a single prioritized report ranking which PRs to review first, which issues to address first, and which discussions need maintainer attention. Use when the user asks to…

3.0k 2d ago A 121 tokens original MIT

ai

41

TanStack/ai

Settings file Claude Code

Agent settings declaring 40 allowed tools.

3.0k 2d ago A tokens not measured original MIT

pr-sweep

42

TanStack/ai

Skill Claude CodeCodex

Sweep open (or listed) PRs with up to 100 parallel agents: security-scan outside contributors, rebase onto main when behind (push --force-with-lease), approve pending first-time-contributor CI when relevant, optionally rebase in-house PRs, and report who should review. Supports full, changed-only, behind-only, and…

3.0k 2d ago A 159 tokens original MIT

ai AGENTS.md

43

TanStack/ai

Instructions file CodexOpenCode

Instructions for TanStack/ai, covering agents.md, docs skill (mandatory for claude, grok, and codex), bugfix pr skill (mandatory for claude, grok, and codex), contributing guide (mandatory for issues and prs) and ponytail skill (mandatory for claude, grok, and codex).

3.0k 2d ago A 1,968 tokens original MIT

ai CLAUDE.md

44

TanStack/ai

Instructions file

Instructions for TanStack/ai, covering claude.md, repository overview, package manager & tooling, common commands and testing.

3.0k 2d ago A 4,991 tokens original MIT

ai-code-mode

45

TanStack/ai

Skill Claude CodeCodex

LLM-generated TypeScript execution in sandboxed environments: createCodeModeTool() with isolate drivers (createNodeIsolateDriver, createQuickJSIsolateDriver, createQuickJSBunIsolateDriver, createCloudflareIsolateDriver), codeModeWithSnippets() for persistent snippet libraries, trust strategies, snippet storage…

3.0k 2d ago A 95 tokens original MIT

ai-mcp

46

TanStack/ai

Skill Claude CodeCodex

Host-side Model Context Protocol (MCP) client for TanStack AI: connect to external MCP servers, discover and run their tools inside any adapter's chat() loop, read resources and prompts, generate TypeScript types (typed tool names/pool keys) with the bundled CLI, and manage lifecycle with close()/await using.

3.0k 2d ago A 69 tokens original MIT

TanStack/ai

Skill Claude CodeCodex

Use when wiring hindsight() from @tanstack/ai-memory/hindsight — a hosted memory adapter that buckets memory per conversation and exposes retain/recall/reflect tools to the model. Requires the optional @vectorize-io/hindsight-client peer.

3.0k 2d ago A 57 tokens original MIT

TanStack/ai

Skill Claude CodeCodex

Use when wiring honcho() from @tanstack/ai-memory/honcho — a hosted memory adapter where recall is a dialectic answer over the user's representation (no discrete fragments). Requires the optional @honcho-ai/sdk peer.

3.0k 2d ago A 55 tokens original MIT