Vite build tool configuration, plugin API, SSR, and Vite 8 Rolldown migration. Use when working with Vite projects, vite.config.ts, Vite plugins, or building libraries/SSR apps with Vite.

Talk to Claude asynchronously about a specific task by asking it to write its response into a file, then wait for that file to appear.

Run a systematic health check over `wiki/` following the pattern in `llm-wiki.md` and the conventions in `.cursor/rules/wiki-maintainer.mdc`.

>-

>-

Compile rolling daily briefs into a convergence-led narrative with content outputs and explicit accept/defer/reject decisions for recursive learning.

Create and configure Claude Agent SDK applications with TypeScript or Python, including MCP integration, subagents, permissions, and custom tools. Use when building Claude Code agents, integrating MCP servers, or creating specialized AI agents.

Generates git commit messages following this repository's conventions. Analyzes staged changes and outputs properly formatted commit messages. Use when user asks to write, generate, or format a commit message.

When triggered, execute the following steps in order. Each step should be a distinct phase with a clear handoff.

Registration → Confirmation → Reminders → Live Event → Follow-up → Replay → Conversion

Implements three Bayesian sub-agents for hypothesis-driven development. Use when generating hypotheses, designing experiments, evaluating evidence, performing backwards reasoning from effects to causes, finding conditional variables, verifying results, or creating git worktree schemas. Agent 1 generates hypotheses and schemas; Agent 2 evaluates evidence and creates worktrees; Agent 3 performs backwards probability reasoning to find causes.

Manage language versioning and perform large-scale codebase upgrades.

Interactive PRD exploration and Product Decision Record creation (greenfield)

Release one or more packages from this monorepo using the scripts in `.cursor/scripts/release/`.

Generate changelogs for SDK pod packages using tag-based GitFlow. Use when preparing a release, generating changelog, or creating CHANGELOG_LLM.md.

Updates benchmark documentation with latest results including README tables, speedup plots, and library metadata. Use when updating documentation, generating comparison tables, or when the user mentions update_docs.sh or documentation generation.

tiptap

Skill roster that helps select the right specialist skill for the current task. This skill is always relevant and should be consulted when the task would benefit from specialist expertise. Use proactively at the start of complex tasks.

Ownership, borrowing, and lifetime expert. Handles compiler errors E0382, E0597, E0506, E0507, E0515, E0716, E0106 and provides systematic solutions for memory safety patterns.

Use when the user wants to position their product or define market category. Applies April Dunford's framework, Moore's positioning statement, and Neumeier's Onliness Test. Produces positioning doc, category analysis, and messaging hierarchy. Triggers: positioning strategy, market category, differentiate from competitors. Works standalone; uses /fh:startup-design output if available. Does NOT handle code planning or development. (Codex adapter)

Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.

Manage GitHub issue execution with `gh` in this repository, including scanning open issues, retrieving issue details, creating issue branches, opening draft PRs, and keeping test/push hygiene. Use when a user asks to work an issue, check issue/PR status, or start/continue issue-driven implementation.

Set or refine source-control policy for repository structure, branch naming, merge strategy, commit hygiene, and secrets-in-git discipline. Use when bootstrapping a repo, tightening PR flow, or documenting branch and release policy.

Analyze, trim, and optimize project dependencies

Activate this skill ONLY if the current repo is `watchfolio_backend`, or

Apply ML/AI project delivery guidance for data exploration, feasibility, experimentation, testing, responsible AI, and operating ML systems. Use when the repo includes model training, inference, data science workflows, or ML-specific delivery planning.

>

Validate readiness to advance between development phases. Produces a PASS/CONCERNS/FAIL verdict with specific blockers and required artifacts.

Use when a user brings a new capability, feature request, or enhancement need for greater in vague terms. Interviews conversationally and produces a scoped-need document. Applies Gate 1 (greater-mission alignment), Gate 2 (narrowest scope with API stability), Gate 3 (specialist routing).

Validate spec-implementation-test alignment and convergence for spec groups. Checks spec completeness, atomic spec coverage, implementation evidence, test evidence, and traceability. Use after implementation and tests are complete.

Deploy locally, run security scans and behavioral tests, check CI/CD, and verify OpenSpec spec compliance

Apply strong frontend design language and quality heuristics (audit, critique, normalize, polish).

Synchronize `lib/api` wrappers with the generated contract under `api/generated`. Use when regenerated APIs or DTOs changed, when wrapper drift between `api/generated/lib/**` and `lib/api/**` must be audited, or when Codex needs a generated-first baseline sync for services, controllers, models, `api.dart`, or `api_client.dart`.

Use when improving the Chokobot admin operational flow, especially dashboard usability, process tracking, handoff clarity, table-to-detail journeys, action priority, and operator-facing workflow design in the modern Next.js admin.

Use when auditing or repairing a specific podcast with recurring transcript quality issues such as inconsistent speaker labels, generic guest names, language mismatches, duplicate translations, or episodes that need source recovery before repolish.

Refactor code structure while preserving behavior, filling test gaps as needed

Use when writing or updating mobile-first Playwright coverage for the badminton H5 flow, including home CTA, upload readiness, candidate clip selection, processing progress, report rendering, history, compare, and error recovery.

Debug rendering and layout issues in Rezi apps. Use when UI looks wrong, has layout problems, or renders unexpectedly.

Set up or refine open-source .NET code-quality gates for CI: formatting, `.editorconfig`, SDK analyzers, third-party analyzers, coverage, mutation testing, architecture tests, and security scanning. Use when a .NET repo needs an explicit quality stack in `AGENTS.md`, docs, or pipeline YAML.

Run JetBrains ReSharper CLI `jb cleanupcode` with the repository's narrow, versioned cleanup profile to apply safe automated cleanup edits such as removing unused `using` directives, shortening redundant qualified references, and removing redundant XAML namespace aliases. Use when the user wants ReSharper-driven cleanup changes rather than a dead-code report or a broad style rewrite.

>

Use this skill when you need a four-agent execution team that humans can see and type into directly.

Conduct structured multi-source research, synthesize evidence, compare options, and produce actionable conclusions. Designed for technical, product, and market investigations.

Test-driven development workflow with test generation, coverage analysis, and multi-framework support

>

>-

>

Handle Netlify Forms in TanStack Start. Use when implementing contact forms, signup forms, or any form submission handling on Netlify-hosted TanStack Start sites.

Meta-skill for the Turri bundle that routes natural language health conversations to the right capability — nutrition logging, health profile, pattern discovery, experiments, news, or daily coaching.

academic-search