mickeyyaya
UserSelf-improving AI pipeline that autonomously discovers, builds, audits, and ships improvements to any codebase. 4 agents, 5 phases, eval gating, continuous learning. Plugin for Claude Code & Gemini CLI.
Categories
Indexed Skills (31)
loop
Use when the user invokes /evolve-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
publish
Use when the user invokes /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.
phase-create
Use when the user (or the advisor) wants to design and register a NEW optional pipeline phase conversationally — "add a phase that does X". Interviews for goal-type, trigger signal, report sections, and verdict; synthesizes a phase.json + persona; registers them via `evolve phases create`; self-corrects from the command's JSON envelope. The Go binary is the single enforcement point, so this flow works from any LLM CLI.
code-review-simplify
Use when reviewing code changes for quality, security, performance, or maintainability issues and identifying simplification opportunities in a single token-efficient pass
commit
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 commit-gate-runner.sh, 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.
evaluator
Use when the user invokes /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
inspirer
Use when the user invokes /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
refactor
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
release
Use when the user asks whether a release is ready, or to gate/verify release criteria before publishing. A thin readiness-gate that runs the existing read-only verifiers (evolve release-preflight, evolve release-consistency), adds the CI-green-on-main and no-WIP-commit checks they don't cover, then delegates execution to /publish. Does NOT reimplement the release pipeline.
security-review-scored
Security-focused code review that emits a numeric composite score (0.0–1.0) suitable for the evolve-loop Builder self-review convergence loop
verify-release
Use when the user invokes /verify-release or asks to check whether a release has propagated, whether the marketplace is up to date, or whether installed plugins reflect the latest version. Wraps legacy/scripts/release/marketplace-poll.sh for standalone post-publish verification.
evolve-loop
Use when the user invokes /evolve-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
setup
Use when the user runs /setup, asks to configure evolve-loop, onboard, pick per-phase models, or learn how the pipeline works. Detects which LLM CLIs/subscriptions are available, explains the pipeline concisely, proposes a per-phase CLI/model assignment the user can adjust, writes per-phase pins to .evolve/policy.json, and verifies them against the integrity floor. Runs once on first launch (the loop nudges) and is re-runnable anytime.
build
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.
plan-review
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.
audit
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.
intent
Pre-Scout intent capture phase. Structures vague user goals into intent.md before any subagent budget is spent. Opt-in via EVOLVE_REQUIRE_INTENT=1.
retro
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.
scout
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.
ship
Use after audit returns Verdict PASS. Atomic git commit + tag + ledger update. Single-writer; cannot fan-out.
tdd
Use when the plan-review verdict is PROCEED (or plan-review is disabled) and code has not yet been written. Writes RED tests first, defining the contract Builder must satisfy. The mandatory hop before any implementation.
adversarial-testing
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.
evolve-audit
Use after evolve-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.
evolve-intent
Pre-Scout intent capture phase. Structures vague user goals into intent.md before any subagent budget is spent. Opt-in via EVOLVE_REQUIRE_INTENT=1.
evolve-plan-review
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.
golang-test-review
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.
evolve-build
Use after evolve-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.
evolve-retro
Use after evolve-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.
evolve-ship
Use after evolve-audit returns Verdict PASS. Atomic git commit + tag + ledger update. Single-writer; cannot fan-out.
evolve-spec
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.
evolve-tdd
Use when the plan-review verdict is PROCEED (or plan-review is disabled) and code has not yet been written. Writes RED tests first, defining the contract Builder must satisfy. The mandatory hop before any implementation.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.