memorysaver

E2E testing for paperlens — scripted gates (bun test), a declarative BDD journey dogfood driven by an agent (browser/device tool resolved per environment), and API drivers. Use when running tests, adding coverage, dogfooding a feature, running a user-story journey, seeding the test account, or executing the manual half of a layer gate.

Autonomous feature implementation in a workspace session. Use when a workspace agent starts building, or when the user says "build", "implement", "execute implementation". Covers the full autonomous flow — initialize harness, implement linearly with one commit per task, review, test, create PR, handle review feedback, and merge. Runs in an isolated git worktree on a feature branch without user interaction.

Pick the next story to work on and bridge it into the feature lifecycle. Use when ready to start building, or when the user says "what's next", "dispatch", "pick a story", "start next feature", "what should I work on". Reads product-context.yaml, syncs workspace signals, computes readiness score for routing, then scores stories by business value + unblock potential + critical path urgency + reuse leverage (penalized by ambiguity + interface risk), assembles context, and hands off to /aep-design or /aep-launch. Supports batch dispatch with WIP limits. For autonomous orchestration, use /aep-autopilot instead.

Generate (or upgrade) a project's e2e-test skill into the BDD layer-gate three-tier shape. Use when setting up E2E testing for a project, scaffolding the e2e-test skill, adding a BDD journey library, migrating a thin/bash e2e-test skill to BDD, or when the user says "scaffold e2e", "set up e2e testing", "add BDD journeys", "upgrade the e2e-test skill". Delegated to by /aep-scaffold. Emits a canonical, cross-tool skill (Claude Code + Codex + Pi) with a separate test-tool-selection guide.

Product-level opportunity and product framing. Use when starting a new product from scratch, revisiting product direction, or when the user says "new product idea", "validate this idea", "product framing", "what should we build", "revisit our assumptions". Walks through opportunity validation and produces a Context Document that feeds into /aep-map and /aep-design.

Host-agnostic executor abstraction for spawning and steering implementation agents. This is a utility skill — it defines how /aep-launch, /aep-build, and /aep-autopilot start a worktree-bound agent, send it mid-flight instructions, check liveness, surface human gates, present it for review, and tear it down, across Claude Code (native background subagents / background sessions) or Codex (native subagents / exec workers), with tmux+cmux as the legacy pinned fallback. Reference its files from any skill that needs to run work in an isolated workspace. Triggers on "executor", "which backend", "launch mode", "spawn workspace", "run under codex", "native-bg-subagent", "agent teams", "claude-team", "no tmux", "with tmux", "run as a workflow", "host detection".

Reusable generator/evaluator pattern for honest artifact validation. This is a utility skill — it provides the scoring framework, agent contracts, evaluation protocol, and findings format used by /aep-build, /aep-validate, and any skill that needs to evaluate agent-produced work. Use directly when you need to run a gen/eval loop on any artifact, or reference its files from other skills. Triggers on "gen/eval", "generator evaluator", "evaluate honestly", "separate evaluator", "scoring framework".

Spawn an autonomous workspace agent for feature implementation. Use after /aep-design is complete, or when the user says "launch workspace", "start building", "spawn agent", "send it to build". Creates a git worktree on a feature branch, starts the selected executor mode (Claude Code native background subagents or background sessions; Codex native subagents or exec workers; tmux only when pinned), and optionally sets up a separate evaluator agent. Followed by /aep-build (which runs autonomously in the workspace).

Generates or upgrades a project's e2e-test skill to the three-tier BDD layer-gate shape. Use for "scaffold e2e", "set up e2e testing", "add BDD journeys", or thin/bash migration; normally delegated by /aep-scaffold.

Implements one feature autonomously in an isolated workspace, including task commits, review, tests, PR, feedback, and merge. Use when a workspace agent should build or implement; this workflow does not interact with the user.

Designs a feature interactively on the integration branch with OpenSpec exploration, proposal, review, and committed artifacts. Use for "design a feature" or "explore and propose"; next run /aep-launch.

Launches an autonomous workspace agent for a designed feature by creating its worktree, selecting an /aep-executor backend, and optionally adding an evaluator. Use after /aep-design or for "launch workspace" and "spawn agent".

Archives OpenSpec artifacts and cleans the workspace after a PR merges. Use for "wrap up", "archive", or "post-merge cleanup"; this is the final feature step before /aep-dispatch or /aep-reflect.

Runs the dispatch-to-wrap cycle continuously for one layer from the main workspace. Use for "autopilot", "hands-free", or unattended multi-story execution; prefer /aep-dispatch for one story only.

Spawns and steers workspace agents across Claude Code and Codex backends. Used by /aep-launch, /aep-build, and /aep-autopilot; invoke directly for backend choice, launch mode, host/tmux detection, or workflow execution.

Canonical generator/evaluator pattern for artifact scoring, agent contracts, eval protocol, and findings. Used by /aep-build, /aep-validate, and /aep-launch; invoke for "gen/eval", "separate evaluator", or artifact review.

End-to-end testing for looplia CLI from local source. Builds the CLI, initializes workspace, runs the writing-kit workflow, and verifies outputs. Use when testing local development or validating workflow execution.

This skill should be used when the user wants to execute a looplia workflow, run workflow steps, or process a workflow.md file. Use when someone says "run the looplia workflow", "execute this looplia pipeline", "/run writing-kit", "start the looplia automation", or "process these workflow steps". Architecture: One workflow step triggers one general-purpose subagent call, which then invokes skills to accomplish the step's mission. Each step = separate context window. Handles sandbox management, per-step orchestration, and validation state tracking. v0.6.9: Unified general-purpose subagent strategy for all providers (context offload).

Bump version across all looplia-core package.json files, changelog, and documentation. Use when: releasing a new version, preparing a version bump PR, updating version numbers across the monorepo. Handles all 5 package.json files, CHANGELOG.md, docs/README.md, and the landing page version badge.

This skill should be used when the user wants to create a new looplia workflow, generate a workflow definition file, or compose workflow steps from skill recommendations. Use when someone says "create a looplia workflow", "generate workflow.md", "compose workflow steps", "build me an automation pipeline", or "/build" (final step). Final step in looplia workflow building: transforms skill recommendations into valid v0.7.0 workflow YAML/Markdown files. Each step uses skill: + mission: syntax, following the one workflow step → one skill-executor → multiple skills architecture. v0.7.0: Generates explicit `skills:` declaration for selective plugin loading. v0.6.3: Supports input-less workflows using input-less capable skills (e.g., search).

Load the skill catalog for workflow building. This skill should be used when discovering available looplia skills or listing what capabilities are available. Use when someone says "what looplia skills are installed", "list available skills", "/build", "what can looplia do", or "show me all looplia capabilities". v0.7.0: Replaces plugin-registry-scanner with skill catalog for faster access. Auto-syncs from all sources on every build to ensure freshest skill catalog.

This skill should be used when matching user requirements to available skills from a compiled registry. It receives a skill registry (from registry-loader) and user requirements, then scores each skill based on capability alignment, producing prioritized matches with confidence scores. Triggers: "match skills to requirements", "find relevant skills for workflow", "which skill handles X", "score skill capabilities", "/build" (after registry load), "find skills for this task", "match my requirements to skills". Second step in looplia workflow building pipeline: takes user requirements and skill registry, recommends skill sequences with missions. Designs one workflow step → one skill-executor → multiple skills orchestration pattern.

Generate structured ContentSummary JSON from analyzed content. Use after media-reviewer to produce final output with all 16 fields.

Looplia writer skill for generating content ideas with personalization. Reads user profile for context. Generates hooks, angles, and thought-provoking questions. Use after media-reviewer to transform analysis into creative content ideas.

Helps analyze systemic problems, teach systems-thinking concepts, and turn conclusions into explainable diagrams, model portfolios, Remotion animation briefs, presentation storyboards, and visual assets. Use when the user wants to understand a complex recurring problem, learn how to read systems diagrams, apply many-model thinking, compare multiple models, prepare a presentable explanation, animate a system map, create a Remotion video plan, make a presentation deck, generate conceptual images, mentions systems thinking, causal loops, feedback loops, Sherwood, Seeing the Forest for the Trees, Scott E. Page, The Model Thinker, stock and flow, leverage points, root causes, unintended consequences, or asks to make a diagram of a business, product, organizational, social, or operational system.

Ultra-compressed communication mode that keeps technical accuracy while stripping filler. Use when the user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes "/caveman".

Stress-test a user's plan or design by interviewing them through the decision tree until shared understanding is reached. Use when the user wants to be grilled, stress-test a plan, sharpen a design, or mentions "grill me".

Create portable agent skills with clear triggers, concise instructions, progressive disclosure, and optional bundled resources. Use when the user wants to create, write, build, improve, or package a new skill.

Use when setting up a new project, auditing an existing one, or aligning a project so the same project-level skills and agent guide work under Claude Code, Codex, and Pi Agent. Trigger on phrases like "make this project canonical", "set up canonical skills layout", "ensure canonical skills style", "migrate CLAUDE.md to AGENTS.md", "make claude/codex/pi share the same agent guide here", "standardize the agent layout for this repo", or whenever the user opens a fresh project and wants the five project invariants (skills/ real dir, .claude/skills symlink, .agents/skills symlink, AGENTS.md canonical, CLAUDE.md = @AGENTS.md) to hold. Also trigger when the user mentions only one of these symptoms (drifted CLAUDE.md vs AGENTS.md, .claude/skills or .agents/skills as a real directory, multiple skills directories) — the goal is to converge to the canonical shape every time, not just react to the symptom they named.

AI image generation, video generation, SVG/vector creation, and image editing powered by WaveSpeed AI CLI. Use when the user wants to generate images, create videos from text or images, edit/modify images with AI, create visual assets (hero images, thumbnails, placeholders, social media graphics), animate still images into video, batch-generate multiple assets, iterate on designs, generate SVG/vector logos or icons, restore old photos, relight images, colorize B&W photos, swap faces, or segment images. Also triggers for: 'make me an image', 'generate a thumbnail', 'create a placeholder', 'animate this', 'edit this photo', 'change the background', 'generate assets for my project', 'I need visuals', 'make me a logo', 'restore this old photo', 'relight this', 'which wavespeed model should I use', or any request involving AI-powered image/video creation or editing — even if the user doesn't mention WaveSpeed by name.

Craft high-quality prompts for Google Nano Banana Pro image generation. Use when the user wants to write, improve, or refine an image generation prompt, needs help describing a visual concept for AI generation, wants to adapt a prompt to a different style (photorealistic, anime, 3D, etc.), wants to build a prompt from a reference image description, asks 'how do I prompt for...', 'write me a prompt', 'improve this prompt', 'make this more cinematic/anime/realistic', 'nanobana prompt', 'nano banana prompt', 'I want to make an image of...', 'help me with my image prompt', 'this image gen result looks bad', 'show me example prompts', or any request about prompt engineering for image generation — even if they don't mention Nano Banana by name.

Use OpenCLI to gather information from websites without login. Trigger when the user wants to fetch data from websites (news, finance, research papers, tech trends, Stack Overflow, Wikipedia, etc.) via CLI, needs structured web data in JSON/CSV/Markdown, mentions opencli, or wants to discover public APIs on any website. Also use when the user asks to scrape, monitor, or pull live data from public web sources without authentication.

This skill should be used when the user needs to perform deep web research across multiple websites, extract data from JavaScript-rendered or dynamic pages, navigate through search results or paginated content, or build comprehensive research reports from multiple sources. Use this skill when the user says: "research this topic across sites", "scrape this website", "extract data from this page", "compare prices", "browse and extract information", "fill forms and get results", "navigate through pages", "click through search results", "research authenticated content", or "cross-reference multiple sources". Prefer this over WebFetch when pages require JavaScript, interaction, authentication, or multi-step navigation.

Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Use when starting complex tasks, multi-step projects, research tasks, or when the user mentions planning, organizing work, tracking progress, or wants structured output.

Read and parse RSS/Atom feeds to monitor news, blogs, and content updates. Use when you need to fetch RSS feeds, parse entries, or monitor content sources for updates.

Generate and revise production-oriented 2D game maps with built-in image generation as the default visual asset source, choosing a visual model, runtime object model, collision model, art direction, and engine/export target. Use when Codex needs to create or integrate RPG maps, monster-taming maps, tactical arenas, battle backgrounds, side-scroller/parallax scenes, tilemaps, layered raster maps, clean HD hand-painted maps, pixel-inspired maps, prop packs, collision zones, walkable areas, or map previews.

Generate and postprocess general 2D game assets and animation sheets: pixel-art sprites, clean HD map props, creatures, characters, NPCs, spells, projectiles, impacts, props, summons, and transparent GIF exports. Use when Codex should infer the asset plan from a natural-language request, match a reference or map art style, call built-in `image_gen` for solid-magenta raw sheets, and use the local processor only for chroma-key cleanup, frame extraction, alignment, QC, and transparent exports.

Use when setting up a new project, auditing an existing one, or aligning a project so the same project-level skills and agent guide work under Claude Code, Codex, and Pi Agent. Trigger on phrases like "make this project canonical", "set up canonical skills layout", "ensure canonical skills style", "migrate CLAUDE.md to AGENTS.md", "make claude/codex/pi share the same agent guide here", "standardize the agent layout for this repo", or whenever the user opens a fresh project and wants the five project invariants (skills/ real dir, .claude/skills symlink, .agents/skills symlink, AGENTS.md canonical, CLAUDE.md = @AGENTS.md) to hold. Also trigger when the user mentions only one of these symptoms (drifted CLAUDE.md vs AGENTS.md, .claude/skills or .agents/skills as a real directory, multiple skills directories) — the goal is to converge to the canonical shape every time, not just react to the symptom they named.

Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.