rust-supervisor

Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.

System architect and technical design leader. Use when the user asks to talk to Winston or requests the architect.

Senior software engineer for story execution and code implementation. Use when the user asks to talk to Amelia or requests the developer agent.

Facilitate interactive brainstorming sessions using diverse creative techniques and ideation methods. Use when the user says help me brainstorm or help me ideate.

Review code changes adversarially using parallel review layers (Blind Hunter, Edge Case Hunter, Acceptance Auditor) with structured triage into actionable categories. Use when the user says "run code review" or "review this code"

Break requirements into epics and user stories. Use when the user says "create the epics and stories list"

Creates a dedicated story file with all the context the agent will need to implement it later. Use when the user says "create the next story" or "create story [story identifier]"

Forensic case investigation with evidence-graded findings, calibrated to the input. Use when the user asks to investigate a bug, trace what caused an incident, walk through unfamiliar code, or build a mental model of a code area before working on it.

Working Backwards PRFAQ challenge to forge product concepts. Use when the user requests to 'create a PRFAQ', 'work backwards', or 'run the PRFAQ challenge'.

Create, update, or validate a product brief. Use when the user wants help producing, editing, or validating a brief.

Implements any user intent, requirement, story, bug fix or change request by producing clean working code artifacts that follow the project's existing architecture, patterns and conventions. Use when the user wants to build, fix, tweak, refactor, add or modify any code, component or feature.

Post-epic review to extract lessons and assess success. Use when the user says "run a retrospective" or "lets retro the epic [epic]"

Generate sprint status tracking from epics. Use when the user says "run sprint planning" or "generate sprint plan"

Summarize sprint status and surface risks. Use when the user says "check sprint status" or "show sprint status"

Automate the BMAD story build cycle across create, dev, QA automation, review, and retrospective steps with resumable tmux orchestration. Use when the user says "run story automator", "automate stories", or asks to build all stories in an epic.

Use when working on this Rust project for coding, refactoring, module ownership cleanup, API and architecture decisions, rust-analyzer assisted inspection, Rust service or CLI implementation, documentation updates, recurring-pattern capture, and focused validation. This is a project-local combo skill that coordinates the rust, rust-analyzer-workflows, rust-design-patterns, and write-project-commit skills when relevant.

Create or update the feature specification from a natural language feature description.

Analyze drift between specs and implementation. Compares requirements against code to find divergence.

Analyze drift between specs and implementation. Compares requirements against code to find divergence.

Apply approved drift resolutions to specs and/or code

Generate a new spec from unspecced code feature (backfill)

Detect and surface conflicts between specs or between specs and design docs

Propose resolutions for detected drift. AI generates spec updates or code changes.

Self-driving agent workflow with heartbeat-driven task execution, day/night progress reports, and long-term memory consolidation. Integrates with todo-management for task tracking.

Use when the user needs authoritative help with ACP (Agent Client Protocol): designing or implementing ACP clients, agents, adapters, or ACP-enabled products; interpreting protocol semantics; handling initialization, sessions, prompt turns, permissions, modes, transports, MCP bridging, interoperability debugging, and release validation.

Explain the Model Context Protocol (MCP) from an authoritative, standards-aware perspective, including documentation structure, core architecture, specification, extensions, registry, SEPs, governance, working groups, and community processes.

Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.

Multi search engine integration with 16 engines (7 CN + 9 Global). Supports advanced search operators, time filters, site search, privacy engines, and WolframAlpha knowledge queries. No API keys required.

Use when Codex needs IDE-like Rust semantic navigation, code intelligence, structured refactors, lightweight workspace diagnostics, or rust-analyzer-specific debug/inspection workflows. Covers stable CLI workflows (`parse`, `diagnostics`, `symbols`, `highlight`, `search`, `ssr`, `prime-caches`, `analysis-stats --skip-inference`, `lsif`, `scip`, `--print-config-schema`), direct LSP requests such as `definition`, `references`, `workspaceSymbol`, `completion`, `inlayHint`, `codeAction`, `rename`, `analyzerStatus`, `expandMacro`, `externalDocs`, `runnables`, `viewHir`, `viewMir`, `interpretFunction`, `openCargoToml`, `viewRecursiveMemoryLayout`, and known failure modes such as `unresolved-references` and full `analysis-stats` panicking on some workspaces.

Use when Codex needs to choose, implement, refactor, or review Rust design patterns and idioms, including GoF patterns in Rust, Rust Unofficial Patterns, ownership-aware alternatives, trait/generic/object-safety tradeoffs, API boundary design, and deciding when a pattern should not be used.

Production Rust patterns covering ownership, async Tokio, Axum web framework, SQLx, error handling, CLI tools, WASM, and PyO3 Python bindings

Reviews Rust test code for unit test patterns, integration test structure, async testing, mocking approaches, and property-based testing. Covers Rust 2024 edition changes including async fn in traits for mocks,

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Reviews serde serialization code for derive patterns, enum representations, custom implementations, and common serialization bugs. Use when reviewing Rust code that uses serde, serde_json, toml, or any serde-based serialization format. Covers attribute macros, field renaming, and format-specific pitfalls.

Execute the implementation plan by processing and executing all tasks defined in tasks.md

Apply a pending iteration to spec documents — update all artifacts that speckit.implement relies on, then hand off to implementation.

Define an iteration on the current feature — analyze the change request against current spec state and implementation progress, then write a reviewable iteration plan.

Prepare repo-local Git commits for this workspace. Use when Codex needs to inspect `git status`, isolate the correct path set, draft or execute a commit, explain commit boundaries, or summarize staged changes in the current project's style: Chinese topic line, flat `- 修改项` entries, only current-theme files, and pre/post commit verification.