feat: add playbook skills for AI coding agents#1293
Open
KyleAMathews wants to merge 11 commits intomainfrom
Open
feat: add playbook skills for AI coding agents#1293KyleAMathews wants to merge 11 commits intomainfrom
KyleAMathews wants to merge 11 commits intomainfrom
Conversation
Add SKILL.md files to each package so AI coding agents can discover and use TanStack DB correctly. Core skills (collection setup, live queries, mutations, sync) ship with @tanstack/db. Framework-specific skills ship with each adapter package. Covers 33 validated failure modes across 10 skill files. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
🦋 Changeset detectedLatest commit: a3f3677 The changes in this PR will be included in the next version bump. This PR includes changesets to release 12 packages
Not sure what this means? Click here to learn what changesets are. Click here if you're a maintainer who wants to add another changeset to this PR |
More templates
@tanstack/angular-db
@tanstack/db
@tanstack/db-ivm
@tanstack/electric-db-collection
@tanstack/offline-transactions
@tanstack/powersync-db-collection
@tanstack/query-db-collection
@tanstack/react-db
@tanstack/rxdb-db-collection
@tanstack/solid-db
@tanstack/svelte-db
@tanstack/trailbase-db-collection
@tanstack/vue-db
commit: |
Contributor
|
Size Change: 0 B Total Size: 92.6 kB ℹ️ View Unchanged
|
Contributor
|
Size Change: 0 B Total Size: 3.7 kB ℹ️ View Unchanged
|
- Add missing `and` import to code examples across 6 framework skills - Remove nonexistent `ne` operator from live-queries frontmatter - Add Svelte destructuring reactivity warning (HIGH priority mistake) - Add `isIdle` and `isCleanedUp` to Vue and Angular return shape docs Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The existing skill only covered `===`. Now explicitly shows all three wrong forms: bare property refs (todo.completed), negation (!todo.completed), and comparison (todo.completed === false). Explains the isExpressionLike() validation mechanism. Addresses #1297. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Reference files provide agents with deep API documentation that exceeds what fits in a single SKILL.md: - Per-adapter configs (Electric, Query, PowerSync, RxDB, TrailBase) - Full query operator reference (comparison, logical, aggregate, string, math) - Schema validation deep-dive (TInput/TOutput, transforms, defaults, errors) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Every code sample was verified against the actual documentation, example code, and source. Key fixes: - Electric: handlers call API endpoints, not raw SQL. Txid generation is server-side code. Added all three sync strategies (txid return, awaitMatch, simple timeout). Fixed pg_current_xact_id casting (::xid::text not ::text). - Query: fixed import from @tanstack/query-core (not react-query). Added expression helpers, queryOptions interop. - PowerSync: imports from @powersync/web per docs. Added all 4 option patterns. Added required onDeserializationError. - RxDB: imports from rxdb/plugins/core per docs. Added title field, startSync option, replication example. - TrailBase: fixed initClient() (not new Client()). Unix timestamps (not ISO strings). id is required. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Add SKILL.md files to 6 packages so AI coding agents can discover and use TanStack DB correctly. Skills ship inside each npm package — agents read them directly from
node_modules.Approach
Generated using skill-tree-generator v2.0 from the domain map and skill spec produced by skill-domain-discovery. The skill tree is split into two layers:
@tanstack/db) — framework-agnostic: collection setup, query builder, mutations/optimistic state, sync/connectivitySkills live inside each package directory (not a central
skills/folder) so they ship withnpm publish. Eachpackage.jsongets"skills"added to itsfilesarray.Key invariants
requires: db-coreso agents load core concepts firstNon-goals
references/overflow files — all skills stayed under 500 linesFiles changed
packages/db/skills/db-core/SKILL.mdpackages/db/skills/db-core/collection-setup/SKILL.mdpackages/db/skills/db-core/live-queries/SKILL.mdpackages/db/skills/db-core/mutations-optimistic/SKILL.mdpackages/db/skills/db-core/sync-connectivity/SKILL.mdpackages/react-db/skills/react-db/SKILL.mdpackages/vue-db/skills/vue-db/SKILL.mdpackages/svelte-db/skills/svelte-db/SKILL.mdpackages/solid-db/skills/solid-db/SKILL.mdpackages/angular-db/skills/angular-db/SKILL.mdpackages/*/package.json"skills"tofilesarray (6 packages)Verification
Feedback
Review posted to TanStack/playbooks#3 (comment) with spec gaps and suggestions for skill-tree-generator v2.1.
🤖 Generated with Claude Code