Configures NotificationClient handlers, implements async dispatch workflows, and handles DispatchError failures for the pidge v3 notification library in async Python services. Use when working with pidge, pidge v3, pidge notifications, NotificationClient, async notifications, or pidge integration — including setting up API keys, dispatching messages, and handling delivery errors.

Use when the user asks to write unit tests, generate a test suite, or migrate/convert Jest or Vitest tests to Themis in Node.js/TypeScript repos. Produces Themis-native tests, runs validation commands, and applies Themis migration workflows.

Manage Things 3 tasks on macOS -- view lists, create tasks with deadlines and tags, complete tasks, move between projects, set due dates, search, and organize. This skill should be used when the user mentions Things 3, wants to manage tasks or to-dos, asks about their inbox, today, upcoming, or someday tasks, wants to create, complete, move, or delete tasks, discusses projects or task management, or says things like 'add a task', 'show my inbox', 'what do I need to do today', 'mark it done', 'my to-do list'.

Audits a Claude Code skill for security risks in three modes: before download (from a URL or install command), after download but before install (from a .skill file), or after install (from a local skills directory). Use this skill whenever a user is about to install a skill from any source — including GitHub URLs, git clone commands, npx/npm commands, curl/wget downloads, pip installs, marketplace links, or raw SKILL.md URLs. Also trigger when a user asks "is this skill safe?", "should I trust this skill?", "can you check this before I install it?", "audit this skill", or pastes any link to a skill repository or .skill file. If a user mentions installing ANY skill, proactively offer to audit it first — do not wait for them to ask.

Interview stakeholders to clarify ambiguous or underspecified requirements before writing code. Use when receiving a new task, feature request, or bug report that lacks clear acceptance criteria. Produces clarified requirements ready for spec authoring. Common triggers: "new feature", "build me", "implement", "add support for", or any task where requirements are vague or incomplete.

Verify that implementation and tests remain synchronized with specs after code changes. Use when code has been generated or modified from specs, after implementation is complete, or when reviewing a PR that touches spec-covered code. Reports mismatched targets, broken test links, and undocumented behavioral changes. Common triggers: "verify the spec", "check spec alignment", "are specs up to date", or after completing implementation work.

Create or update .spec.md files from clarified requirements. Use when requirements have been gathered and confirmed, and specs need to be written or updated before implementation begins. Produces well-structured spec files with frontmatter, requirements, and test links. Common triggers: "write the spec", "update the spec", "create a spec for", or after requirement-gathering completes.

Use when the user asks to run E2E tests, verify a web page, generate tests for an app, prove destructive actions are blocked, check if a UI element is visible, fill out a form, or drive a browser with natural language. Returns per-step results with safety classifications, policy decisions, DOM diffs, structured page context, and a signed audit trail.

Expert OpenTelemetry guidance for collector configuration, pipeline design, and production telemetry instrumentation. Use when configuring collectors, designing pipelines, instrumenting applications, implementing sampling, managing cardinality, securing telemetry, writing OTTL transformations, or setting up AI coding agent observability (Claude Code, Codex, Gemini CLI, GitHub Copilot).

Your creative muse for writing. Reads your journals, notes, and past work, taps into an optional Signal DB for real-time trends, searches the web — then surfaces topic ideas that are timely, authentic, and uniquely yours. Use when asked to "find a topic", "what should I write about", "inspire me", "topic ideas", "help me pick a topic", "选题", or "写什么好".

Use and extend alias analysis in LLVM 22. Covers querying AAResults from a function pass, using IR-level hints (noalias, TBAA) as the preferred approach, writing a custom AA analysis with the New Pass Manager, and common ModRef patterns.

Add function/parameter attributes and IR metadata to LLVM 22 IR to unlock optimizer opportunities. Covers NoUnwind, ReadNone, NoCapture, Noundef, loop vectorization hints, branch weights, TBAA, !range, and !nonnull.

Add or wire a calling convention in an LLVM 22 in-tree target or document IR-level ABI choices for out-of-tree frontends. Covers CallingConv IDs, TableGen CallingConv.td, CCState/CCValAssign hooks, ISel lowering, and tests.

Build, scaffold, and demo Java AI agent systems with the langchain4j-agentic module — workflow patterns (sequential, loop, parallel, conditional), supervisor, and custom Planner strategies including the flagship typed-verdict (CriticResult-style) critic pattern, plus langchain4j-mcp tool servers and langchain4j-agentic-a2a remote agents. Use whenever the user mentions LangChain4j, langchain4j-agentic, Java AI agents, @Agent / @Tool, AgenticScope, AgenticServices, sequenceBuilder / loopBuilder / supervisorBuilder / plannerBuilder, MCP or A2A in Java, or wants to build a conference demo / workshop / POC around autonomous Java agents. Pinned to 1.15.0 core + 1.15.0-beta25 agentic/mcp; refresh with scripts/check_versions.sh.

Use when the user asks to log work, record what was done, or save task progress. Creates a structured markdown task log in `agent-logs/` with validation, waivers, and a final gates summary.

Use when the user asks you to implement a feature, fix a bug, or complete a repository task end-to-end (from scoping through code changes, validation, and final gate summary).

Use when `.tf` or `.tfvars` files have been edited, added, or removed and you need to verify that the code changes produce the intended Terraform plan before the task is considered complete. Runs `terraform plan` in `examples/test_app` and cross-checks the result against the change set you expected your edits to cause. This is a gate: do not declare a Terraform task done without passing it.

Optimizes RLS policies by enforcing SELECT-wrapped auth.uid() calls, mandatory B-Tree/GIN indexes on policy-referenced columns, and SECURITY DEFINER encapsulation of deep JOINs. Use when optimizing RLS performance, fixing policy full table scans, wrapping auth.uid in SELECT, or indexing columns used in RLS policies.

Configures pgsodium Vault extension for API key and secret storage. Creates SECURITY DEFINER functions assigned to service_role for secure access. Eliminates hardcoded secrets. Use when storing API keys, managing secrets in Supabase, implementing pgsodium Vault, or replacing hardcoded credentials with Vault references.

Creates PL/pgSQL RPC implementing Reciprocal Rank Fusion (score = 1/(k+rank)) to fuse semantic pgvector results with full-text tsvector results. Use when implementing hybrid search, RRF search, semantic plus keyword search, exact SKU and conceptual queries, or vector and full-text fusion.