AdityaVasireddy
UserSmall, disciplined AI capabilities — each with a pre-declared kill criterion and real usage numbers.
Categories
Indexed Skills (4)
crucible
Assumption-driven venture validation that compounds founder judgment across sessions. Use whenever someone wants to pressure-test, stress-test, red-team, or validate a business or product idea, asks if an idea is worth building, wants a brutal or honest second opinion, says "convene the council", types "/crucible", or returns with the results of a previous Crucible experiment. Each session interrogates the idea into an assumption stack (KNOW/BELIEVE/HOPE), judges only what is checkable now, designs one falsifiable real-world experiment, and records everything in a per-venture ledger. The idea may be provided inline (e.g. "/crucible [the idea]").
engineering-historian
Capture engineering knowledge as a promotion pipeline (CASE → JUDGMENT → PRINCIPLE → STANDARD) and retrieve answers from it. Capture is automatic — a post-session sweep drafts cases with status:auto; the user reviews them at /distill. Use whenever the user types "/history", "/case", or "/distill", says "log this session", "wrap up and record", "capture this decision", or ends a working session where decisions, deployments, debugging, or configuration happened. ALSO use for retrieval whenever the user asks about their own past work or rules — "how did I deploy X", "why did I stop using Y", "what did we decide about Z", "do we have a rule/standard for W" — by searching the knowledge/ vault (standards first, then principles, then cases) before answering from general knowledge. Every retrieval must be logged to the retrieval log.
five-gate-method
Evidence-driven task discipline for hard tasks. Use PROACTIVELY the moment you notice a task has many layers - multiple dependent steps, unknowns that could change the approach, debugging where the first theory might be wrong, or anything that needs verification before handoff. Also use when a task keeps failing or stalling, or when the user says "five gates", "five-gate method", "fable mode", "think like Fable", "slow down and do this right", or "think this through first". Loads a five-gate task loop (scope, evidence, adversarial reasoning, verification, calibrated reporting) plus standing habits. Model-agnostic - runs on any capable LLM.
session-handoff
Use when the user says "session handoff", "wrap up session", "hand off", "handoff summary", "let's wrap up", "summarize before I clear", or wants a structured end-of-session summary before clearing context. Also use proactively when the user says they are about to /clear and no handoff has been produced yet. Generates a handoff document saved as a file (in the project's docs/handoffs/ directory, or as a downloadable file in chat environments) with required sections (objective, status, decisions + rationale, key files, next action) plus situational sections included only when they apply, so a fresh agent can continue seamlessly without re-deriving lost context.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.