Validate and diagnose diagram-cli tooling-envelope drift in this repo. Use this skill when work touches docs/agents/tooling.contract.json, scripts/check-environment.sh, scripts/codex-preflight.sh, scripts/verify-work.sh, .codex/environments/environment.toml, or docs that describe local projection behavior.

Use inside coding-harness when the user wants to find architecture deepening opportunities, reduce shallow/pass-through modules, improve testability, or make the Codex-first harness easier for agents to navigate while staying aligned with docs/roadmap/north-star.md.

Use when a repository needs a small, evidence-bound Coding Harness routine: orient, diagnose, preview installation, verify local work, or distinguish pull-request truth.

Validate and align required-check names across GitHub workflows, .harness/ci-required-checks.json, harness.contract.json, and repo docs. Use this skill when CI check names or required-check policy changes.

Critiques a plan, design, finding, or hypothesis using codex CLI and agy (Antigravity) CLI in parallel, then reconciles their feedback via advisor(). Use when seeking a second opinion before committing to a plan, validating an approach, stress-testing a design, or challenging your own conclusions. Also auto-fires before ExitPlanMode, exploratory finding presentation, and superpowers phase commits (brainstorming, writing-plans, systematic-debugging, finishing-a-development-branch).

Author an engineering-change Product Requirements Document (PRD) that requires inspecting a code repository — verifying the requester's claims against the actual codebase, interviewing them down the design tree, deciding module and interface boundaries, then filing the result as a GitHub or GitLab issue. Use when the deliverable is a repo-grounded implementation spec for engineers. Trigger on "spec this feature out", "turn this idea into an issue", "engineering PRD", "write this change up before we build it", "plan this against the codebase", or a rough feature idea that must become an actionable engineering spec. Runs five phases (INTAKE, VERIFY, INTERVIEW, MODULES, WRITE + FILE) gated on a decision ledger. Boundary — for PM-facing product requirements aimed at stakeholders (Lean PRD, one-pager, AARRR or HEART metrics) use `prd-generator` instead.

Use when the user wants to ship one or more Jira tickets (typically several) in parallel end-to-end — read each ticket, branch in an isolated git worktree, implement with red-green TDD, validate, get an independent review, re-validate, and open a DRAFT merge request per ticket. Trigger on "parallel dev", "/parallel-dev", "work these tickets in parallel", or a list of ticket keys to ship concurrently.

Use when the user wants to UNDERSTAND and RETAIN code, systems, or protocols — not just change them. Three modes. (1) VISUAL EXPLAINER — "make a visual explanation of this", "build an HTML presentation / slides explaining this code", "walk me through this module visually" — produce a self-contained HTML deck that teaches big-picture-first. (2) DIAGRAM-IT — "draw an ASCII diagram of this", "diagram this protocol / architecture / request flow", "sketch the state machine" — produce accurate monospace ASCII diagrams grounded in the actual code. (3) RECALL LOOP — "quiz me on this", "test my understanding", "help me remember this", "spaced repetition" — run a loop where the user explains, you probe gaps Socratically, and persist review cards. Trigger whenever the user is learning from a codebase — onboarding, building a mental model, or studying to remember — even if they don't name a mode. Also mention the Explanatory/Learning output style (/config) for ongoing "explain the why" narration.

Create distinctive, production-grade frontend interfaces with high design quality, ALIGNED with the Comanda editorial line. Use when the user asks to build web components, pages, or applications and wants polished, memorable design instead of generic AI aesthetics.

Guidelines for writing Python flow tests (end-to-end behavioral tests). Use this when writing new Python tests in tests/pytests/, and as the review criteria when reviewing changes to them.

Guidelines for writing Rust tests. Use this when you want to write Rust tests.

Review Rust code changes for unsafe correctness, security and robustness, documentation quality, and C-to-Rust porting fidelity. Use this when you want to review Rust changes before merging.

Run Rust tests after making changes to verify correctness. Use this when you want to verify your changes to Rust code.

Run Rust benchmarks and compare performance with the C implementation. Use this when you work on migrating C code to Rust and want to ensure performance is not regressed.

Guide for porting a C module to Rust. Use this when starting to port a C module to Rust.

Check code quality and formatting before committing changes. Use this to verify your changes meet our coding standards.

Determine which parts of the C codebase use Rust-defined C symbols. Use this when you want to understand which C code files may be impacted by changes to a Rust FFI crate.

Add a new OS platform to RediSearch CI. Use when adding a new distro version, OS, or container target to the build/test matrix.

KB article quality reviewer. Run against KB articles in docs/kb/ to review frontmatter, article type and structure, title format, product names, callout format, bolding/path formatting, image alt-text/external-references, and keyword quality. Use when editing or reviewing any file under docs/kb/.

Add missing test coverage for your local code changes by generating new test files (covers uncommitted and untracked changes, or the latest commit if everything is committed). Use when you want write tests for new logic or increase test coverage.