This skill should be used when the user wants to build, prototype, or reshape an app, tool, CLI, API, automation, workflow, requirements document, knowledge tree, policy, curriculum, argument outline, or other evaluable artifact before architecture. Responds to "let's build", "prototype this", "surface first", "SFD"…
This skill should be used when the user wants to create music with Suno (AI music generation) — a song, track, beat, anthem, jingle, or instrumental — or wants to execute an existing suno-pack for real via the suno-pp-cli integration — rendering packs into actual tracks, cover pipelines, Suno library checks, one-roll…
This skill should be used when the user wants to build, prototype, or reshape an app, tool, CLI, API, automation, or feature by starting from the interaction surface first. Responds to "let's build", "prototype this", "I have an idea for an app/tool", "show me what it would look like", "surface first", "SFD", "click…
Use when the user wants to start or reshape an app, tool, CLI, API, automation, or feature from the interaction surface first, by converging on a prototype before deriving contracts and building inward.
This skill should be used when the user says 'autopsy', 'shelve', 'done with this', 'extract value', or wants to close out a dead or shelved project. Extracts fascinations, writes a composting report, and feeds insights back into /spark.
This skill should be used when the user says 'contract', 'derive', 'extract contracts', 'freeze', 'invariants', 'nfr', or wants to lock down requirements from a converged prototype. Derives contracts, invariants, and NFR targets, freezes on approval.
This skill should be used when the user says 'decide', 'what should I do?', 'plan', 'milestones', 'next steps', or has made a push/pivot/shelve decision that needs a concrete plan. Creates milestones with natural re-evaluation points.
This skill should be used when the user says 'explore', 'directions', 'design space', 'sketch', 'contrast', 'compare', or wants to see fundamentally different design approaches. Proposes 3-4 divergent directions with inline sketches and contrast capability.
This skill should be used when the user says 'fascination', 'what am I into', 'patterns', 'show my interests', or wants to browse their fascination index. Displays themes, intensities, and cross-fascination connections in list or Mermaid map mode.
This skill should be used when the user says 'narrow', 'decide', 'pick one', 'lock direction', or is ready to commit to one design direction from /explore. Synthesizes reactions into a recommendation, locks on acceptance.
This skill should be used when the user says 'patterns', 'what do I keep building?', 'meta', 'trends', or wants cross-project insight into recurring themes and habits. Analyzes fascination index and project history to surface patterns, abandonment trends, and deepest fascinations.
This skill should be used when the user says 'pulse', 'momentum', 'am I stuck?', 'check in', 'how is my project doing', or wants a momentum assessment. Analyzes git history, detects novelty depletion, and proposes push/pivot/shelve with a specific recommendation.
This skill should be used when the user says 'what should I do next', 'where am I', 'pyro', 'status', asks about project state, or needs lifecycle navigation. Reads project state and recommends the next skill to invoke. Also handles 'pyro init', 'pyro status', and 'pyro list'.
This skill should be used when the user says 'reframe', 'bored', 'novelty', 'stuck', 'different angle on remaining work', or wants fresh energy on stale tasks. Injects novelty through creative domain lenses — each lens produces one concrete actionable move.
This skill should be used when the user says 'remix', 'different angle', 'creative lens', 'what if we approached this differently', or wants to reframe their current idea through domain lenses (game design, music, architecture, etc.). Produces concrete alternative proposals.
This skill should be used when the user says 'revive', 'old project', 'bring back', 'resurrect', or wants to evaluate an abandoned repo. Archaeological analysis with scored revival options (full revival, soul transplant, organ harvest, graceful burial).
This skill should be used when the user says 'scope', 'cut', 'too big', 'soul', 'minimum viable', or the project feels overwhelming. Soul-preserving scope cuts — finds the minimum version that satisfies the core curiosity.
This skill should be used when the user says 'ship', 'release', 'publish', 'ready?', 'what's left', or wants to know what remains before shipping. Gap analysis between current state and shippable.
This skill should be used when the user says 'I have a vague idea', 'something bugs me about...', 'spark', 'help me figure out what to build', or describes a feeling or annoyance without a clear project concept. Excavates concrete ideas from vague feelings using propose-react-iterate.
This skill should be used when the user says 'surface', 'prototype', 'build it', 'show me', or wants a working interactive prototype from their locked direction. Iterates on behavioral critique until convergence.