← All creators

mickeyyaya

User

Self-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.

31 indexed · 0 Featured · 2 stars · avg score 76
Prolific

Categories

Indexed Skills (31)

Code & Development Listed

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

2 Updated today
mickeyyaya
Code & Development Listed

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.

2 Updated today
mickeyyaya
Data & Documents Listed

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.

2 Updated today
mickeyyaya
Code & Development Listed

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

2 Updated today
mickeyyaya
Code & Development Listed

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.

2 Updated today
mickeyyaya
Code & Development Listed

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

2 Updated today
mickeyyaya
Code & Development Listed

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

2 Updated today
mickeyyaya
Code & Development Listed

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

2 Updated today
mickeyyaya
Code & Development Listed

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.

2 Updated today
mickeyyaya
Code & Development Listed

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

2 Updated today
mickeyyaya
Code & Development Listed

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.

2 Updated today
mickeyyaya
Code & Development Listed

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

2 Updated today
mickeyyaya
AI & Automation Listed

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.

2 Updated today
mickeyyaya
Code & Development Listed

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.

2 Updated today
mickeyyaya
Code & Development Listed

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.

2 Updated today
mickeyyaya
Code & Development Listed

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.

2 Updated today
mickeyyaya
Code & Development Listed

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.

2 Updated today
mickeyyaya
Code & Development Listed

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.

2 Updated today
mickeyyaya
Code & Development Listed

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.

2 Updated today
mickeyyaya
Code & Development Listed

ship

Use after audit returns Verdict PASS. Atomic git commit + tag + ledger update. Single-writer; cannot fan-out.

2 Updated today
mickeyyaya
Code & Development Listed

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.

2 Updated today
mickeyyaya
Testing & QA Listed

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.

2 Updated today
mickeyyaya
Code & Development Listed

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.

2 Updated today
mickeyyaya
Code & Development Listed

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.

2 Updated today
mickeyyaya
Code & Development Listed

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.

2 Updated today
mickeyyaya
Code & Development Listed

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.

2 Updated today
mickeyyaya
Code & Development Listed

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.

2 Updated today
mickeyyaya
Code & Development Listed

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.

2 Updated today
mickeyyaya
Code & Development Listed

evolve-ship

Use after evolve-audit returns Verdict PASS. Atomic git commit + tag + ledger update. Single-writer; cannot fan-out.

2 Updated today
mickeyyaya
Code & Development Listed

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.

2 Updated today
mickeyyaya
Code & Development Listed

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.

2 Updated today
mickeyyaya

Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.