All authors
Claude Skills by mickeyyaya
github.com/mickeyyaya34 skills0 installs73 views
- Evals- `test -f /Users/danleemh/ai/claude/evolve-loop/skills/code-review-simplify/SKILL.md` - `head -5 /Users/danleemh/ai/claude/evolve-loop/skills/code-review-simplify/SKILL.md | grep -q "^---"`Votes: 0GitHub stars: 5
- SurfacefixtureThis file exists solely to prove the flagreaders guard scans non-Go surfaces. It references a flag that has NO registry row, the way `skills/loop/SKILL.md` referenced `EVOLVE_TRIAGE_ENABLED` while cycle-360 removed flags that still had shell readers: EVOLVE_FAKE_NONGO_ONLY_FLAG=1 evolve loop It also references a real, registered flag which MUST NOT be reported as an orphan (it has a row): set `EVOLVE_SANDBOX=1` to force the sandbox. A dynamic-prefix fragment that must be IGNORED (it ends in `...Votes: 0GitHub stars: 5
- Adversarial TestingUse 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.Votes: 0GitHub stars: 5
- AuditUse 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.Votes: 0GitHub stars: 5
- BuildUse 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.Votes: 0GitHub stars: 5
- Code Review SimplifyUse when reviewing code changes for quality, security, performance, or maintainability issues and identifying simplification opportunities in a single token-efficient passVotes: 0GitHub stars: 5
- CommitUse 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.Votes: 0GitHub stars: 5
- Diff ReviewBudget-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.Votes: 0GitHub stars: 5
- Engineering CraftUse 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.Votes: 0GitHub stars: 5
- EvaluatorUse 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 defensesVotes: 0GitHub stars: 5
- ExplainUse 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.Votes: 0GitHub stars: 5
- FableUse 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.Votes: 0GitHub stars: 5
- Golang Test ReviewUse 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.Votes: 0GitHub stars: 5
- InspirerUse 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 lensesVotes: 0GitHub stars: 5
- IntentPre-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.Votes: 0GitHub stars: 5
- LoopUse 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 phasesVotes: 0GitHub stars: 5
- MinimalismUse in any coding session when writing or changing code — enforces the laziest solution that actually works (YAGNI, stdlib-first, shortest diff) while never trimming validation, error handling, security, accessibility, or the pipeline's tests/gates. Also triggers on "minimalism", "be lazy", "simplest/minimal solution", "yagni", "do less", "shortest path", or complaints about over-engineering, bloat, boilerplate, or unnecessary dependencies.Votes: 0GitHub stars: 5
- Phase CreateUse 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.Votes: 0GitHub stars: 5
- Plan ReviewUse 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.Votes: 0GitHub stars: 5
- PublishUse 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.Votes: 0GitHub stars: 5
- RefactorUse 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 groupVotes: 0GitHub stars: 5
- ReleaseUse 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 /evo:publish. Does NOT reimplement the release pipeline.Votes: 0GitHub stars: 5
- RetroUse 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.Votes: 0GitHub stars: 5
- ScoutUse 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.Votes: 0GitHub stars: 5
- Security Review ScoredSecurity-focused code review that emits a numeric composite score (0.0–1.0) suitable for the evolve-loop Builder self-review convergence loopVotes: 0GitHub stars: 5
- SetupUse 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. On a project that declares a `cli_r...Votes: 0GitHub stars: 5
- ShipUse after audit returns Verdict PASS. Atomic git commit + tag + ledger update. Single-writer; cannot fan-out.Votes: 0GitHub stars: 5
- TddUse 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.Votes: 0GitHub stars: 5
- Verify ReleaseUse when the user invokes /evo: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.Votes: 0GitHub stars: 5
- Solution AuditPreloaded 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.Votes: 0GitHub stars: 5
- Solution BuildPreloaded 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.Votes: 0GitHub stars: 5
- Solution ScoutPreloaded 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.Votes: 0GitHub stars: 5
- Architecture ReviewUse when reviewing the structure of a code change read-only — single sources and duplicated beliefs, dependency direction, design-pattern fit with its forces, the three-book audit (test-driven, clean code, design patterns) and mutation probes — and writing the findings, each with a suggested fix, into a report. The code-review phase's structural rubric; also usable standalone after any structural change.Votes: 0GitHub stars: 5
- Quality IndexUse when reviewing or auditing a code change against the shared quality index — the ten dimensions (correctness, architecture, maintainability, test-quality, robustness, concurrency, performance, debuggability, security, docs-consistency), each scored 1–5 or N/A against a bar of 4 — and when writing the Review Plan, findings and Scores sections the code-review phase and the audit share.Votes: 0GitHub stars: 5