weft

Use this skill when refreshing Weft public documentation, AGENTS.md, CLAUDE.md, or mirrored skills from recent pull requests.

Use this skill when restoring or protecting Weft coverage with LCOV-backed branch targeting, structural test doubles, coverage allowlists, conformance fixtures, or tests for hard-to-reach protocol, schema, lifecycle, and CLI paths.

Use this skill when a Weft change touches ack-gated flows, pending promises, WebSocket workers, shutdown, disposal, cancellation, retries, reconnects, heartbeats, timers, or any lifecycle path where ordering can leave work hanging.

Use this skill when writing or reviewing Weft comments, JSDoc, documentation, README examples, test prose, or operation descriptions that describe wire responses, server diagnostics, masked errors, public APIs, or runtime recovery.

Use this skill when a Weft change renames, reshapes, normalizes, hashes, serializes, or replays persisted data such as effect-log records, checkpoints, tool calls, tool results, JSONValue content, storage payloads, or compatibility fixtures.

Run the full verification cycle before declaring work done: build, typecheck, lint, test, export review, diff review. Use when the user says "verify", "validate", "check everything passes", "run the full suite", "make sure it's ready", or before committing, opening a PR, or finishing a feature. Also use proactively after completing any non-trivial implementation work.

Security review checklist for weft covering server routes, MCP authentication, workflow trust boundaries, storage, activity isolation, and credential handling. Use when the user says "security review", "check for vulnerabilities", "audit security", "review trust boundaries", or when changes touch server routes, authentication, storage, or any code that handles untrusted input. Also use proactively when implementing features that cross trust boundaries.

Security review checklist for weft covering server routes, MCP authentication, workflow trust boundaries, storage, activity isolation, and credential handling. Use when the user says "security review", "check for vulnerabilities", "audit security", "review trust boundaries", or when changes touch server routes, authentication, storage, or any code that handles untrusted input. Also use proactively when implementing features that cross trust boundaries.

Use this skill before refactoring Weft engine, server, storage, worker, or agent internals where overload ergonomics, ordering, event sequences, return shapes, type-level behavior, or public examples must remain unchanged.

Use this skill when cutting, preparing, validating, tagging, publishing, or troubleshooting a Weft npm release for @lostgradient/weft.

Test-driven development workflow for weft using Bun's test runner, TestEngine, TimeControl, and ActivityMockRegistry. Use when writing new features, fixing bugs, or implementing acceptance criteria. Trigger on: "write tests for", "TDD", "test-driven", "add tests", "implement with tests", "red green refactor", or any task that involves writing both tests and implementation code.

Preserve Weft external-dashboard mount contracts and avoid reintroducing the removed bundled dashboard.

Implement a new feature for the weft durable execution engine following a structured workflow. Use when the user asks to "implement", "add", "build", or "create" a feature, capability, or acceptance criterion. Trigger on: "implement X", "add support for X", "build the X feature", "work on X from the architecture doc".

Implement a new feature for the weft durable execution engine following a structured workflow. Use when the user asks to "implement", "add", "build", or "create" a feature, capability, or acceptance criterion. Trigger on: "implement X", "add support for X", "build the X feature", "work on X from the architecture doc".

Use the `tasks` CLI when you need to inspect or update the local task graph for this project. The `tasks` CLI manages a local SQLite database of tasks, their relationships, and their lifecycle state. It also provides commands for synchronizing task state with Git branches and GitHub pull requests, recording incremental progress, and inspecting the current work in the context of the project.

Autonomous development loop that reads the architecture doc, picks the next body of work, implements it with TDD, opens a PR, monitors for reviews and CI, merges, and repeats. Use when the user says "ship", "start the development loop", "work through the architecture", "implement the next feature from the roadmap", or "keep building".