wan-huiyan

Claude Code skill: Multi-agent adversarial review panel — 4-6 AI reviewers debate your code/plans, then a supreme judge delivers the verdict. 9 auto-detected signal groups, built-in domain checklists, anti-groupthink mechanisms.

1 plugin · wan-huiyan/agent-review-panel

Audit and clean up Claude Code's persistent memory system — MEMORY.md, memory files, lessons, and ADRs

1 plugin · wan-huiyan/memory-hygiene

Coordination toolkit for parallel Claude Code sessions sharing one repo — issue-pickup claim protocol, worktree isolation pitfalls, parallel-PR conflict recovery, subagent integrity, and squash/merge mechanics. 61 skills, Pattern B multi-skill plugin.

1 plugin · wan-huiyan/agent-traffic-control

Fetch Google Trends data via browser automation, with daily-resolution multi-chunk stitching for date ranges > 90 days

1 plugin · wan-huiyan/google-trends-browser-fetch

Claude Code skill: execute implementation plans with fresh subagents per task, two-stage review gates, and parallel mode via worktree isolation. Based on obra/superpowers, parallel mode adapted from theradengai/spawn-tasks.

1 plugin · wan-huiyan/subagent-driven-development

End-of-session handoff that captures all knowledge, updates documentation, and prepares next-session prompts

1 plugin · wan-huiyan/session-handoff

Claude Code skill for measuring causal impact of marketing campaigns using Bayesian structural time series

1 plugin · wan-huiyan/causal-impact-campaign

Two Claude Code skills for passing context across boundaries: session-handoff (end-of-session, agent→human) + successor-handoff (mid-run, agent→agent). Install via Claude Code plugin marketplace.

2 plugins · wan-huiyan/context-baton

Three complementary skills for auditing and maintaining Claude Code ecosystem health: skills, memory, handoffs, ADRs, worktrees, and automation.

10 plugins · wan-huiyan/claude-ecosystem-hygiene

Integrate structured review panel findings into implementation plans with full traceability

1 plugin · wan-huiyan/plan-review-integrator

Two sister Claude Code plugins for autonomous overnight workflows — client-delivery polishing + ah-ha insight discovery, both with multi-agent review panels

8 plugins · wan-huiyan/overnight-workflows

promptback — feedback that comes back as a prompt. Claude Code skill: turn findings/plans/triages into a single-file interactive HTML review page (per-item decision chips + notes) whose decisions copy back as one structured prompt. No backend.

1 plugin · wan-huiyan/promptback

Six Claude Code skills that make the things you build cute, and check that the cute actually works: favicons, sparkle effects, little-world apps, explainer animations, terminal and README.

6 plugins · wan-huiyan/cutify-this

Build and customize the Claude Code status line and session banner

1 plugin · wan-huiyan/claude-statusline

Synchronous Claude Code toolkit for auditing live data dashboards end-to-end — parallel cluster agents methodology + the most common fix-shape + single-metric depth audit + the squash-merge gotcha. Sister to wan-huiyan/overnight-workflows.

4 plugins · wan-huiyan/dashboard-audit-toolkit

Claude Code skill: render per-instance SHAP waterfall charts correctly when a post-hoc isotonic / Platt calibrator sits between the model and the displayed score — Final bar matches chip, bar signs preserved, no rescale-to-fit.

1 plugin · wan-huiyan/shap-waterfall-calibrator-skill

Claude Code skill: find where GitHub Actions minutes actually go and cut them without losing test coverage. Per-job rounding, measurement traps, and an 11-lever fix catalogue with the trap in each.

1 plugin · wan-huiyan/ci-spend-audit

Measure what your Mac really needs, minute by minute (apps, Claude Code sessions and the browsers they start), then buy the right amount of RAM. Cute self-updating page, macOS only.

1 plugin · wan-huiyan/more-bananas

Claude Code skill: keep Jira in step with the work — drafts updates from meetings, Slack, email and PRs, writes only on your yes

1 plugin · wan-huiyan/jira-fairy

Patrol your Claude Code context budget: measure, trim (skillOverrides / disable-model-invocation), and report the runaway skills-catalog token tax.

1 plugin · wan-huiyan/context-police

Keep locally installed Claude Code skills in sync with their GitHub repos

1 plugin · wan-huiyan/skill-sync

Authoring checklist for deliberate model downshifting: a strong model writes a next-session prompt a cheaper model can execute, escalating only at pre-named forks.

1 plugin · wan-huiyan/downshift

Claude Code skill: Deploy .sqlx files to Google Cloud Dataform via REST API — full lifecycle with gotcha documentation

1 plugin · wan-huiyan/gcp-dataform-rest-api-deploy

Drift-aware training window extension assessment for production ML pipelines. Claude Code skill.

1 plugin · wan-huiyan/ml-training-window-assessor

Claude Code skill for publishing skills to GitHub and awesome-claude-skills lists. Encodes hard-won lessons from real publishing attempts.

1 plugin · wan-huiyan/publish-skill

Recover a Claude Code session that 400s on every request due to malformed transcript JSONL — orphan server-tool pairs & whitespace-only text blocks.

1 plugin · wan-huiyan/claude-code-session-repair

A Claude Code skill: turn technical findings into a plain-English HTML explainer that fact-checks its own translation against your source — one metaphor, honest numbers, an anti-drift verifier. Arcade-themed, opens from file://.

1 plugin · wan-huiyan/show-and-tell

Diagnose AI-generated art by measuring the output instead of rewriting the prompt — then get it onto a real app surface.

1 plugin · wan-huiyan/guide-your-ai-art

Scan Claude Code skills for client-specific data and anonymize for safe public sharing.

1 plugin · wan-huiyan/skill-anonymizer

Existence/strategy audit for a portfolio of published Claude Code skills/repos — should each exist at all? Per-artifact KEEP/CONSOLIDATE/KILL/PIVOT verdicts with web-verified differentiation.

1 plugin · wan-huiyan/skill-portfolio-existence-review

Quantitatively measure how effective a project's automated test suite is at catching real bugs, by replaying historical incidents at pre-fix commits and classifying CI failure history. A Claude Code skill.

1 plugin · wan-huiyan/test-effectiveness-auditor