Investigate recurring Claude Code setup problems across six evidence lanes, select up to three repair families, and independently challenge the diagnosis, changes and outcome. Explicitly invoked, with existing permissions and specialist consent preserved. Attempt limits are not spending caps.
1 on GitHubby StartupBros / House of Vibev0.2.0MITupdated 25 days ago
/
Plugin harness-optimizer from marketplace hov in StartupBros-com/hov-marketplace. Commands read from the repo's manifest — 25 days ago.
What it installs
Skills (1)
harness-optimizer
Coordinate a selected batch of harness improvements when the operator explicitly requests it.
Subagents (2)
harness-optimizer-investigator
Investigate one selected harness-optimizer evidence lane within a bounded read-only packet.
harness-optimizer-reviewer
Challenge a bounded harness-optimizer batch using one assigned evidence lens.
Tell whether a change to an agent-consumed document actually worked. /skill-tuner:tune probes a SKILL.md, AGENTS.md or CLAUDE.md, fixes what three independent skeptics confirm, and proves the description still routes. Paired comparison with a confidence interval, content-hashed provenance with drift detection, and it reads skill-creator benchmark output.
The sleep cycle for Claude Code's auto-memory. /memory-dream:dream runs an operator-gated consolidation pass: deterministic triage finds superseded, stale, and oversized notes, a zero-tool subagent drafts the fixes it cannot apply, and you approve each change by hand before anything is written. /memory-dream:eval measures whether recall actually improved. Also a standalone stdlib-only CLI; it never merges, deletes, or compresses a note on its own.
Friction your agents route around silently, captured automatically and mined into ranked, verified fixes. A PostToolUseFailure hook logs every hard tool failure; a stdlib-only CLI ranks by distinct sessions hit, folds duplicates into causal families, and refuses to call a fix verified on silence alone.
Drive your real, logged-in Windows browser (Chrome, Edge, or Brave) from Claude Code inside WSL2 over the Chrome DevTools Protocol. Read authenticated dashboards, take real screenshots, and run a guided one-time setup; sends native-Windows users to the official extension instead.
Guardrails that keep AI agents on your design system. Posture-check whether a real, agent-wired, CI-enforced design system exists, derive a Google-spec DESIGN.md from the code you already ship, put open taste decisions on visual pages for the human to pick, and ratchet drift budgets that only move down. Read-only on application source — it authors under design/ and never edits your code.
Harness Adobe's creative AI-powered tools to edit images, automate design workflows, and bring creative visions to life — from background removal to vectorization and professional retouching.
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams
Multi-agent collaboration — spawn N parallel subagents that compete on code optimization, content drafts, research approaches, or any task that benefits from diverse solutions. 7 slash commands (/hub-init, /agenthub:spawn, /hub-status, /agenthub:eval, /agenthub:merge, /agenthub:board, /hub-run), agent templates, DAG-based orchestration, LLM judge mode, message board coordination.
8 skills · 1 agent · hooks
alirezarezvani/claude-skills 29,725
Maintain harness-optimizer?
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.