codervisor

The end-to-end spec-issue-driven dev loop for lean-spec — spec → branch → implement → PR → merge → closure. Use when asked "how do I start work", "what's the process", "SDD loop", "spec-driven development", "how do we ship a change on lean-spec", "from scratch what do I do", or when you're about to begin a non-trivial change on `codervisor/leanspec` and haven't yet decided how to split spec/PR. Delegates to `issue-spec` (spec writing), `leanspec-pre-push` (pre-push checks), `leanspec-pr-lifecycle` (post-push), and `leanspec-development` (commands, CI, publishing, i18n).

Manage a lean-spec PR after it's been pushed — spec-issue linking, CI triage, review-comment discipline, merge-conflict recovery on open PRs, webhook subscription, and CHANGELOG follow-through on merge. Triggers include "CI is failing", "check is red", "link this issue", "Closes vs Part of", "respond to review", "subscribe to PR", "triage PR", "the PR is ready", "PR has conflicts", "branch has conflicts with main", "merge conflict on the PR", or when a github-webhook-activity event arrives on a lean-spec PR. Paired with `leanspec-dev-process` (overall loop), `issue-spec` (spec creation), and `leanspec-pre-push` (which owns the pre-push conflict walkthrough).

Run before pushing code to the lean-spec repo to catch what reviewers and CI will catch later, and confirm the branch has a linked spec issue in a valid state. Reproduces the merge-preview environment, walks through this repo's common merge-conflict patterns, and runs the project's typecheck / clippy / test gates. Triggers include "before push", "ready to push", "pre-push check", "push readiness", "prep for PR", "resolve merge conflict", "merge conflict", "branch has conflicts", "sync with main", or proactively before any git push on a lean-spec branch.

Development workflows, commands, publishing, CI/CD, changelog management, and contribution guidelines for LeanSpec. Use when contributing code, fixing bugs, setting up dev environment, running tests or linting, working with the monorepo structure, looking up build/dev/test/publish/format/lint commands, preparing releases, publishing to npm, bumping versions, syncing package versions, testing dev builds, troubleshooting npm distribution, updating changelogs, triggering CI/CD workflows, monitoring build status, debugging failed runs, managing artifacts, checking CI before releases, or researching AI agent runners. Triggers include any development, scripting, publishing, CI/CD, changelog, or runner research task in this project.

Watch GitHub Actions CI status for the current commit until completion. Use after pushing changes to monitor build results.

The spec-coding methodology for AI-assisted development. Use when planning features, creating/refining/implementing/verifying specs, or organising a project. Works with whatever spec backend your team already uses — local markdown, GitHub Issues, Azure DevOps, Jira — by delegating platform-specific details to a LeanSpec adapter.

Enable the GitHub CLI (`gh`) in Claude Code cloud sessions and GitHub Copilot coding agent environments. Use this skill when: (1) setting up a project so cloud AI agents can use `gh` for PRs, issues, and releases, (2) configuring setup scripts or SessionStart hooks for `gh` installation, (3) adding `copilot-setup-steps.yml` for GitHub Copilot agents, (4) troubleshooting `gh` auth failures in cloud sessions, or (5) configuring `GH_TOKEN` for headless environments. Triggers on: "enable gh", "github integration", "Claude Code cloud setup", "copilot setup steps", "gh auth in cloud", "gh not working in cloud", "setup script", or any request involving GitHub CLI access from cloud-based AI coding agents.

Scaffold a new Rust+Node.js hybrid monorepo with pnpm workspaces, Cargo workspace, CI workflows, and publish infrastructure. Use when: (1) starting a new project from scratch, (2) adding missing infrastructure to an existing repo, (3) figuring out the canonical project structure for a Rust+Node.js tool. Triggers on "bootstrap", "scaffold", "new project", "set up project", or "init" in a Rust+Node.js context.

GitHub Actions CI/CD for Rust+Node.js hybrid repos. Covers workflow structure, installable composite actions, artifact flow, caching, and dev versioning. Use when: (1) setting up or fixing GitHub Actions workflows, (2) adding CI for a Rust+Node.js project, (3) working with composite actions (setup-workspace, rust-cross-build, compute-version, wait-npm-propagation), (4) debugging CI failures, (5) setting up the cross-platform build matrix. Triggers on "CI", "workflow", "GitHub Actions", "cross-build", "artifact", or work in .github/workflows/.

Publish Rust binaries to npm using the optionalDependencies platform package pattern. Covers the full publish pipeline, version sync, workspace:* protocol, and platform package architecture. Use when: (1) publishing Rust binaries to npm, (2) setting up the platform package pattern (main + per-OS packages), (3) debugging publish failures, (4) managing version sync across pnpm + Cargo workspaces, (5) working with workspace:* protocol. Triggers on "publish", "platform packages", "optionalDependencies", "bin.js", "version sync", "workspace protocol", "npm tag", or "prepare-publish".

Best practices for creating clean, atomic git commits with good messages. Use when: (1) staging and committing changes, (2) writing commit messages, (3) deciding what to group in a single commit, (4) handling pre-commit hook failures, (5) choosing between amend and new commit. Triggers on "commit", "stage", "git add", "write a commit message", or "commit my changes".

Run multiple AI coding agent sessions in parallel using git worktrees — each agent isolated in its own worktree, working on a separate branch. Use this skill whenever the user wants to: run two or more AI agents simultaneously on different features or bugs, set up isolated agent workspaces in the same repo, push parallel branches to GitHub and open/update PRs, coordinate between concurrent agent sessions, or clean up after merging. Triggers on: "parallel agents", "multiple agent sessions", "git worktree", "run agents in parallel", "work on two things at once", "isolated agent workspace", "spin up another agent", or any request involving simultaneous AI-assisted development streams.

Generative-adversarial coordination — locks a generator and critic agent in an escalating quality loop. The critic actively tries to break the generator's output with increasing sophistication. Quality emerges from adversarial pressure, not checklist compliance. Use when you need deep quality hardening beyond standard review, or when the user invokes /adversarial run <spec-path>.

Coding factory — transforms a spec into a reviewed PR via BUILD → INSPECT pipeline with adversarial review. Use when you need to implement a spec end-to-end with independent code review, or when the user invokes /factory run <spec-path>.

Fractal decomposition — recursively split a complex task into orthogonal sub-specs, solve each leaf independently via subagents, then reunify results bottom-up. Use when a task is too large for a single agent pass, when you need to decompose a problem into independently-solvable pieces, or when the user invokes /fractal decompose <task-or-spec-path>.

Speculative swarm — forks N agents to explore divergent strategies for the same task, cross-pollinates insights at checkpoints, prunes convergent branches, and fuses the best fragments into a composite result. Use when a problem has multiple viable approaches and you want to explore them simultaneously, or when the user invokes /swarm run <spec-path>.

Guidance for implementing and reviewing changes in ClawDen. Use this skill whenever modifying ClawDen Rust, TypeScript, dashboard, SDK, CLI, config, tests, or docs, especially for refactors, bug fixes, command behavior changes, or cross-crate work. Prefer this skill by default for repository development tasks unless a more specific ClawDen skill applies.

Research upstream claw runtimes using DeepWiki MCP tools to gather accurate metadata, track breaking changes, and align ClawDen's adapters and descriptors with upstream reality. Use when: (1) Adding a new runtime adapter or descriptor and need to gather upstream metadata (channels, config format, ports, capabilities, language, install method), (2) Checking whether an existing runtime's metadata is still accurate, (3) Investigating a specific upstream runtime's architecture, config options, or channel support for any ClawDen integration work, (4) Auditing adapter/descriptor alignment with upstream repos, (5) Answering questions about a claw runtime's features, breaking changes, or migration paths, (6) Working with any claw runtime integration — even if the user doesn't explicitly ask for "research", any runtime-related task benefits from checking upstream first. Requires: mcp_deepwiki MCP tools.

Spec-Driven Development methodology for AI-assisted development. Use when working in a LeanSpec project.

Access Railway deployments, logs, and environment variables. Use when asked to check deployment status, view service logs, inspect or update environment variables, redeploy a service, or diagnose production issues on Railway.

Development conventions and tooling for the telegramable monorepo. Use when working on code, dependencies, or builds.

Spec-Driven Development methodology for AI-assisted development. Use when working in a LeanSpec project.

Spec-Driven Development methodology for AI-assisted development. Use when working with specs, planning features, creating/implementing/refining/organizing specs, checking progress, updating specs, task breakdowns, design decisions, or any task involving a specs/ folder or .lean-spec/config.json.

Monitor skill health, diagnose failures, and auto-improve skills. Use when a user reports a skill isn't working well, wants to check skill health, says "this skill keeps failing", "improve the docx skill", "why does X skill do Y wrong", or wants to run a health check on their skill system. Also triggers when the user says "evolve", "fix my skill", "skill is broken", "skill regression", or asks to analyze skill performance. Even if the user doesn't name a specific skill, trigger if they express frustration with output quality from a skill-powered task.