agent-skills

Run one canonical SDLC stage (intake → shape → slice → plan → implement → verify → review → handoff → ship → retro), a perf/observability augmentation (instrument, experiment, benchmark, profile), the compressed design workflow (design), runtime-truth verification (probe), read-only review-and-route triage (simplify), or the end-to-end lifecycle driver (auto), and write its artifact to `.ai/workflows/<slug>/`. The intake stage also dispatches compressed entry modes (fix, rca, investigate, discover, hotfix, refactor, update-deps, ideate). For navigating existing workflows, use $wf-meta; for documentation, use $wf-docs. ($wf-quick is retired — use $wf intake <mode>, $wf probe, and $wf simplify.)

Run one canonical SDLC stage (intake → shape → slice → plan → implement → verify → review → handoff → ship → retro), a perf/observability augmentation (instrument, experiment, benchmark, profile), the compressed design workflow (design), runtime-truth verification (probe), read-only review-and-route triage (simplify), the end-to-end lifecycle driver (auto), or the autonomous lifecycle driver (yolo), and write its artifact to `.ai/workflows/<slug>/`. The intake stage also dispatches compressed entry modes (fix, rca, investigate, discover, hotfix, refactor, update-deps, ideate). For navigating existing workflows, use `/wf-meta`; for documentation, use `/wf-docs`.

Documentation router. Orchestrator mode runs the full discover → audit → plan → generate → review pipeline against a project or workflow slug. Primitive mode writes a single Diátaxis document — tutorial, how-to, reference, explanation, or readme — or runs a docs review.

Navigate, inspect, and meta-control existing SDLC workflows — pick what to run next, check status, resume, sync the registry, amend or extend a plan, skip a stage, close a slug, or explain how something works. Does not produce stage artifacts; for those use $wf.

Navigate, inspect, and meta-control existing SDLC workflows — pick what to run next, check status, resume, sync the registry, amend or extend a plan, skip a stage, close a slug, or explain how something works. Does not produce stage artifacts; for those use `/wf`.

Generate an image from a text prompt using the best available method, with automatic fallback (built-in image_gen → gpt-image-2 → nano-banana-pro → text-only scene sentence). Returns the image file path and the method used. Internal to `/wf design`; not user-invocable.

Code review across 31 dimensions (correctness, security, performance, architecture, accessibility, supply-chain, and more — see `argument-hint`). `$review <dimension>` runs one rubric inline; `$review sweep <aggregate>` fans out one reviewer sub-agent per dimension sequentially by default (or in parallel if the user explicitly requested it) and synthesizes a unified verdict. Auto-trigger on review or audit requests scoped to a PR, worktree, diff, file, or repo.

Code review across 31 dimensions (correctness, security, performance, architecture, accessibility, supply-chain, and more — see `argument-hint`). `/review <dimension>` runs one rubric inline; `/review sweep <aggregate>` fans out one reviewer sub-agent per dimension in parallel and synthesizes a unified verdict. Auto-trigger on review or audit requests scoped to a PR, worktree, diff, file, or repo.

Documentation router. Orchestrator mode runs the full discover → audit → plan → generate → review pipeline against a project or workflow slug. Primitive mode writes a single Diátaxis document — tutorial, how-to, reference, explanation, or readme — or runs a docs review.

Analyze errors, stack traces, and logs to identify root causes and propose targeted fixes. Trigger on debugging, incident-response, or "why is this failing" requests.

Patterns for safe behavior-preserving refactoring — extract, rename, move, simplify — with test-baseline and rollback guidance. Trigger on refactor or restructure requests.

Set up wide-event logging with tail sampling to replace scattered logs with canonical log lines. Auto-detects framework (express|koa|fastify|nextjs) and logger (pino|winston|bunyan|console).

Patterns for generating and organizing tests — unit, integration, data factories, coverage strategies — across multiple languages and frameworks. Trigger on test-writing or coverage-improvement requests.

Design and implement wide-event logging with tail sampling for context-rich, queryable observability

Analyze errors, stack traces, and logs to identify root causes and propose targeted fixes. Trigger on debugging, incident-response, or "why is this failing" requests.

Patterns for safe behavior-preserving refactoring — extract, rename, move, simplify — with test-baseline and rollback guidance. Trigger on refactor or restructure requests.

Patterns for generating and organizing tests — unit, integration, data factories, coverage strategies — across multiple languages and frameworks. Trigger on test-writing or coverage-improvement requests.

Manage stacked branches and pull requests with the gh-stack GitHub CLI extension. Use when the user wants to create, push, rebase, sync, navigate, or view stacks of dependent PRs. Triggers on tasks involving stacked diffs, dependent pull requests, branch chains, or incremental code review workflows.

Use when a documentation request is ambiguous, involves planning a docs structure, or a page seems to mix multiple purposes. Classifies content into Diátaxis quadrants (tutorial, how-to, reference, explanation), proposes a documentation map, and produces a writing plan with ordering. Triggers on phrases like "plan my docs", "what docs do I need", "help me organise my documentation", "docs architecture", "I need to write docs for my project", or when a user asks for a README and a full docs set together.

Use when the user asks for conceptual guides, architecture overviews, design rationale, trade-off discussions, background on how a subsystem works, historical context, or "why is it built this way?" documentation. Creates understanding-oriented content that builds mental models — the why, not the how. Do not use for direct task execution (use how-to) or factual lookup (use reference).

Use when the user asks for a how-to guide, step-by-step instructions for a specific goal, troubleshooting guide, configuration guide, deployment steps, migration guide, or operational runbook. Creates goal-oriented guides for competent users who know what they want to achieve. The reader already understands the basics — this is about getting work done. Do not use for beginner onboarding (use tutorial) or conceptual background (use explanation).

Use when the user asks for a README, a GitHub front page, an open source library landing page, or a documentation homepage for a repository. Writes the README as a front door that orients readers and routes them to the right deeper docs — not a tutorial, not a full reference manual, not a conceptual essay. Use a different diataxis skill when the request is specifically for a step-by-step lesson, a task guide, API details, or conceptual background.

Use when the user asks for API docs, CLI command reference, configuration reference, parameter tables, schema documentation, error code lists, or version compatibility matrices. Creates neutral, structured, scannable technical reference — factual description of the machinery for lookup during active work. Do not use for onboarding, task guides, or conceptual justification.

Use when the user asks for a tutorial, beginner walkthrough, getting-started lesson, first-project guide, or onboarding material for new users. Creates learning-oriented step-by-step lessons where readers learn by doing something meaningful. The goal is skill and confidence, not task completion. Do not use for advanced tasks, troubleshooting, or exhaustive product coverage — those are how-to guides.

Comprehensive guide for using DailyTags - a Jetpack Compose markdown library that supports custom tags. Use this skill when working with markdown rendering, custom markup, rich text formatting in Compose, or creating pattern-based text parsers for Android applications. DailyTags parses text into nodes styled with AnnotatedString, providing a WebView-free solution for rendering markdown and HTML with full customization support.

Analyzes a codebase and prepares it for OtterStack deployment. Use when preparing docker-compose projects, checking OtterStack compatibility, scanning for environment variables, validating compose files, or setting up zero-downtime deployments. Triggers on "prepare for otterstack", "validate compose file", "check deployment readiness", or "scan env vars".

Calculate semantic version bumps for any project type using version file adapters

Generate changelog entries from commits for any project type

Detect project type and configuration for generic application releases

Synchronize version numbers across any project type using version file adapters

Execute git commit, tag, and push operations with configurable patterns for any project type

Validate release readiness for any project type with comprehensive checks

Analyze git changes to determine release scope (marketplace/plugin/variants)

Deploys to archivist@194.163.189.144 VPS and iteratively debugs until successful. Use when deploying to VPS, debugging deployment failures, investigating container issues, checking health endpoints, or fixing OtterStack errors. Triggers on "deploy to vps", "debug deployment", or "fix container failure".

Complete guide for using OtterStack - a Git-driven Docker Compose deployment tool with zero-downtime deployments. Use when deploying Docker Compose apps, managing projects, configuring environment variables, or troubleshooting deployments. Triggers on "how to use otterstack", "otterstack commands", "deploy with otterstack", "otterstack project", "otterstack env", or questions about OtterStack usage.