Kind: skill

[skaile-development] Code review for staged or committed changes in the skaile-dev monorepo. Checks quality, security, performance, scope, and repo-specific rules. Works locally without CI - designed for direct-to-main workflows.

[skaile-development] Cross-session analysis of Claude Code session data for the skaile-dev monorepo. Reads a pre-computed digest (≤10KB) from the Python pipeline, triages improvement opportunities, reads implicated SKILL.md files, and proposes concrete diffs to reduce token waste and improve workflow adherence. Run after ./run.sh in _scripts/session-analysis/.

[skaile-development] Reviews the current Claude Code implementation session for the skaile-dev monorepo: reads the session JSONL to report token usage, cache efficiency, estimated cost, and workflow adherence against the skaile-development skill sequence. Outputs optimization tips and skillset improvement suggestions. Run at the end of any implementation session.

Take one piece of work in one repository from "somebody described it" to a traceable, reviewed, checks-green change whose fate the human decided. Use whenever someone wants something in a repository actually changed rather than explained - however casually they put it. "can you sort it", "can you take it", "can we get X on this", "have a look at #12" and "fix it and push it" are all this skill; the person does not have to mention branches, a pull request, review or merging, and the change can be as small as one constant, one string of copy or one dependency bump. Also use when handed an issue number or link to build, or an already-open pull request from this kind of work to carry the rest of the way. It runs the whole cycle in one flow - files the tracker issue, branches in an isolated worktree, implements, gets the diff reviewed, opens the PR, drives CI and review feedback to green - then recaps in plain language and asks once whether to squash-merge and clean up. Do not use for questions, diagnosis or code explanation, for reviewing someone else's existing code, for plans or design proposals, for filing an issue when implementation is explicitly deferred, for throwaway local experiments, or for work spanning several repositories.

[skaile-development] Use when reasoning about whether and how to build an app idea on the Skaile/PostXL stack -- choosing between platform skills+flows, forge integration tiers, the agent runtime, or PostXL alone. Loads the four context packs (agent framework, ecosystem, platform, PostXL) on demand and routes the question to the relevant doc(s). Trigger when the user asks 'should we build X with Skaile?', 'where in the stack does this fit?', 'platform or standalone app?', 'PostXL or just NestJS?', or any architectural orientation question across the Skaile/PostXL surface.

Use when the user names something they want — an artifact, a screen, a question, a request — and the skill that produces it or what it needs is unclear, when a project has no recorded scope or expectations, or to walk the concept top-down (frame → look → data → features) before anything is built. Triggers on 'which skill', 'where do I start', 'how do we work together', 'walk me through the app', 'what is decided', 'continue the concept', 'describe this screen', 'I have a bug report', 'a feature was requested'.

Use when integrating LLM agent sidecars (omp RPC) into a web frontend. Covers the Typed Action Protocol: SkillAction/ConsumerResponse bidirectional events, skill state machine, adapter layer, structured input/approval flows, API key resolution, and default model selection. Expert-level programming and pattern management.

Use when you need to design, build, or refine LLM agent skill systems with pipeline orchestration, artifact-based gates, cross-references, profiles, and UI integration. Expert-level skill architecture and pattern management.

Use when one feature needs its permanent spec — compares it with the features and ideas that exist, grills the user, draws the in/out line, then writes the feature spec and adds its roster row. Triggers on 'spec this feature', 'what features do we need', 'group the features', 'lock down acceptance criteria', 'what is in vs out'.

Cross-document reference repair across the skaile-dev monorepo. Scans README ↔ CLAUDE.md ↔ docs/<pkg>/ ↔ DOMAIN.md ↔ monorepo CLAUDE.md and finds broken links, missing back-references, orphan Starlight pages, stale _sources frontmatter, and drift between the monorepo domain table and actual ai-assets/*/DOMAIN.md files. Shows a complete diff of proposed changes before applying — non-destructive.

[skaile-development] Set up and generate end-to-end tests for skaile-dev packages: forge apps, platform/frontend, and the agent-framework CLI. Scaffolds Playwright for web apps (forge + platform) including config, global setup/teardown, sandbox, and fixtures. For CLI packages, generates shell-based end-to-end tests that invoke the bin and assert stdout/artifacts. Verifies tests run against a real dev server or real process.

Set up and generate integration tests for any skaile-dev package. Covers API routes, DB operations, and cross-module flows. Knows the storage backends: SQLite + drizzle for forge apps, PostgreSQL + Prisma for platform/backend, temp-dir state for agent-framework. Scaffolds test DB isolation (in-memory SQLite / ephemeral test DB / temp workspaces), auth helpers, seed fixtures, then generates tests. Verifies tests run.

Generates a per-package test plan for any skaile-dev package. Reads CLAUDE.md (architecture, public API), the source tree, and existing tests; produces <package>/TEST_PLAN.md listing untested units, coverage gaps, integration seams, and recommended scenarios per layer (unit/integration/e2e). Used as the input for test-unit, test-integration, and test-e2e.

Set up and generate unit tests for any skaile-dev package (forge apps, agent-framework libraries, platform frontend/backend). Reads TEST_PLAN.md when present, otherwise discovers testable units from source. Scaffolds missing test infra (vitest.config.ts, test harness), then generates one test file per module with test cases mapped to CLAUDE.md Architecture. Verifies tests run before completing.

Test construction and execution for the standalone skaile repos. Two modes: 'run' executes the test suite for one or more packages and reports results; 'construct' generates new tests for recently implemented code. Knows each repo's test stack and runs it from that repo's root: Vitest in workspaces (Biome repo; coverage via @vitest/coverage-istanbul under Bun, ratcheted by packages/workspaces/_scripts/check-coverage-ratchet.ts), Jest (platform backend), Vitest (platform frontend), Playwright (platform e2e), plus the forge apps' own scoped Vitest and Playwright runs.

Use when you need to read the contents of an office document fast - Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, or a digital-native PDF - and convert it to Markdown for orientation, summarization, or data extraction. Pinned Rust CLI (`@firecrawl/anydoc@0.2.4`), no API key, no OCR, no ML models. Read-only: it cannot edit a document, and it drops formulas and cell addresses, so it is not a substitute for mcp:excel or mcp:ppt when the task is to modify a file.

Use when you need to search for programming library documentation or fetch up-to-date code examples via the Context7 REST API. Provides direct CLI access to Context7 without requiring the MCP server — search libraries by name and retrieve markdown documentation with code examples. Use when the user asks about library APIs, how to use a package, or needs current documentation for a specific library version.

Opt-in only, not for default use. Use when a project has deliberately installed a pinned, offline docling (>= 2.132.0) and you need OCR, a vision model or speech transcription on a local file. For reading ordinary office documents and digital PDFs, use use-anydoc instead.

Use when you need to convert markdown speaker dialogue and text into audio using the ElevenLabs API. Includes support for single voice TTS and multi-voice conversational dialogues.

Use when you need to search the web or find code examples using Exa's AI-powered search. Queries Exa's public MCP endpoint with JSON-RPC — no API key required for basic web search and code search.

Use when you need to generate an image from a text prompt - posters, logos, illustrations, photoreal scenes, images with legible text. Calls the Skaile platform capability platform.generate_image, which uses the organization's configured image provider (Ideogram, Recraft, FLUX or another) and saves the result into the session workspace. Needs no API key: the platform holds the provider and its key.

Use when you need to interact with MCP (Model Context Protocol) servers, OpenAPI specs, or GraphQL endpoints via CLI. Converts API schemas into token-efficient CLI commands at runtime without code generation.

Search, read, and manage Outline wiki documents. Use when: (1) searching wiki for documentation, (2) reading wiki pages or articles, (3) listing wiki collections or documents, (4) creating or updating wiki content, (5) exporting documents as markdown. Works with any Outline wiki instance (self-hosted or cloud).

Search, read, and manage Outline wiki documents. Use when: (1) searching wiki for documentation, (2) reading wiki pages or articles, (3) listing wiki collections or documents, (4) creating or updating wiki content, (5) exporting documents as markdown. Works with any Outline wiki instance (self-hosted or cloud).