mickeyyaya
@mickeyyaya
Public Skills
loop
by mickeyyaya
Use when the user invokes /evo:loop or asks to run autonomous improvement cycles, self-evolving development, compound discovery, or multi-cycle code improvement with research, build, audit, and learning phases
adversarial-testing
by mickeyyaya
Use when authoring evals/predicates (Scout, TDD-Engineer), framing an audit (Auditor), or justifying which phases run (PhaseAdvisor/router). Codifies Google's 4-phase adversarial-testing methodology mapped onto evolve-loop's eval, audit, routing, and red-team surfaces.
plan-review
by mickeyyaya
Use when scout-report.md exists and TDD/Build hasn't started yet. Runs four lenses (CEO, Eng, Design, Security) in parallel on the task list and produces a verdict (PROCEED, REVISE, ABORT) before code is written. Catches misaligned plans before they cost cycles.
solution-build
by mickeyyaya
Preloaded persona for the build phase of a DOCUMENT cycle (ADR-0099) — deliver the registry contract under its configured root as several mechanistically distinct candidate strategies, a recommendation that compares them, and an evidence file every number cites; self-check with evolve solution check <slug> before handoff.
solution-scout
by mickeyyaya
Preloaded persona for the scout phase of a DOCUMENT cycle (ADR-0099) — discovery over a solution corpus (strategies, plans, deal designs under solutions/) instead of a codebase; selects document tasks, declares goal_type/deliverable_kind, and writes evals whose [code] grader is evolve solution check plus [model] rubrics.
solution-audit
by mickeyyaya
Preloaded persona for the audit phase of a DOCUMENT cycle (ADR-0099) — grade the candidate strategies of a document deliverable against the acceptance criteria and the eval's [model] rubrics with path:line evidence; verify every number traces to the evidence file the contract names; steelman the non-recommended options; the deterministic contract line is already enforced.
retro
by mickeyyaya
Use after ship completes. Three sub-reflectors (instinct, gene, failure) run in parallel to extract lessons, update gene pool, and analyze any failures. Off the latency-critical path.
intent
by mickeyyaya
Pre-Scout intent capture phase. Structures vague user goals into intent.md before any subagent budget is spent. Opt-in via policy.json workflow.phase_enables.intent=on.
ship
by mickeyyaya
Use after audit returns Verdict PASS. Atomic git commit + tag + ledger update. Single-writer; cannot fan-out.
scout
by mickeyyaya
Use when starting a new evolve-loop cycle and the cycle goal is ambiguous or only described as a one-line objective. Generates a structured specification before any code is written. Surfaces assumptions explicitly.
setup
by mickeyyaya
Use when the user runs /evo:setup (or /evo:setup), asks to configure evolve-loop, onboard, pick per-phase models, or learn how the pipeline works. Auto-detects available LLM CLIs/subscriptions, explains the pipeline concisely, then presents THREE ready-made config presets (Recommended/Economy/Max-quality) the Go binary computes deterministically from the public profiles — the user makes ONE choice and the binary writes per-phase pins to .evolve/policy.json. Runs once on first launch (the loop nudges) and is re-runnable anytime.
diff-review
by mickeyyaya
Budget-capped adversarial review + simplification pass over a STAGED DIFF only — one agent, two lenses, findings-first. Use for commit-gate reviews instead of dispatching separate whole-repo reviewer and simplifier agents; the caller declares what already ran (tests, lint, gates) and the reviewer verifies claims against the diff's one-hop neighborhood, never the whole tree.
engineering-craft
by mickeyyaya
Use when writing or changing any production code or tests — new features, bug fixes, refactors, or test authoring, in any language, by any model on any CLI.
audit
by mickeyyaya
Use after build has produced build-report.md. Validates the build via four parallel sub-auditors (eval-replay, lint, regression, build-quality) and produces ALL-PASS verdict. Adversarial mode default-on per CLAUDE.md.
explain
by mickeyyaya
Use when the user asks to explain how a feature/subsystem works and how the loops built it, or what the concurrent loops/lanes/cycles did and why. Default output = per-FEATURE HTML explainer pages (two movements — how it works today, then how it got built, with verified file:line claims and drift callouts) under docs/explain/; per-batch/per-lane story pages are the fallback framing. Derived from geoffreylitt/explain-diff-html, customized for evolve-loop.
fable
by mickeyyaya
Use when running any LLM agent below Fable 5 — Claude (Opus/Sonnet/Haiku), GPT via codex, Gemini via agy, or local models via ollama — to adopt Fable 5's operating discipline — evidence-first investigation, premise verification, root-cause-only fixes, adversarial self-review, calibrated autonomy, and honest failure reporting. Load at session start or as a persona overlay for phase agents on any CLI.
publish
by mickeyyaya
Use when the user invokes /evo:publish or asks to release a new version, ship a release, or publish a tag. Wraps the go-native self-healing release pipeline (evolve release) — pre-flight checks, auto-changelog, atomic ship, marketplace propagation poll, auto-rollback on failure.
inspirer
by mickeyyaya
Use when the user invokes /evo:inspirer or asks to brainstorm creatively, think outside the box, explore unconventional approaches, break out of stagnation, or generate research-backed ideas with provocation lenses
golang-test-review
by mickeyyaya
Use when reviewing Go test code (new or changed *_test.go files, test harnesses, fixtures, or test tooling) for a Go-test-expert pass — behavior-over-surface, determinism, parallel-safety, build-tag correctness, and harness reuse. Complements the general code-reviewer with test-specific rigor.
build
by mickeyyaya
Use after tdd has written RED tests and the contract is in team-context.md. Implements the minimum code to turn RED tests GREEN. Runs in a worktree with single-writer invariant.
evaluator
by mickeyyaya
Use when the user invokes /evo:evaluator or asks to evaluate, assess, score, or independently audit code quality, project health, or improvement priorities with multi-dimensional scoring and anti-gaming defenses
refactor
by mickeyyaya
Use when the user asks to refactor code, review code quality, or fix code smells — orchestrates the full refactoring pipeline from detection through fix, with parallel worktree isolation per independent refactoring group
commit
by mickeyyaya
Use when the user asks to commit changes (interactively, not inside an autonomous cycle). Runs code-simplifier + one reviewer (general code-reviewer OR the matching language reviewer, ECC agents/skills), then lint + targeted tests via evolve commit-gate run, writes a tree-SHA-bound attestation, commits + pushes via the sanctioned evolve ship --class manual path (which hard-verifies the attestation), then watches GitHub CI with one auto-fix-on-red pass.
code-review-simplify
by mickeyyaya
Use when reviewing code changes for quality, security, performance, or maintainability issues and identifying simplification opportunities in a single token-efficient pass