Stats
Actions
Available In
Tags
More by goern
grade-openspec
0·
Grade a completed OpenSpec change with the Spec Quality Index (SQI) — a 0–100 score measuring how cheaply the spec implemented.
6d
goernBy goern
Claude Code skills, agents, and slash commands for multi-agent research with team review and humanizing pass.
Evidence-quality reviewer for research drafts. Audits sources for credibility, diversity, recency, and whether claims are actually supported. Pairs with dr-critic in a team — critic handles logic and structure, skeptic handles evidence base.
Reader-fit reviewer for research drafts. Asks whether the report actually answers the original research question for the intended reader, at the right depth, in the right format. Pairs with dr-critic, dr-skeptic, and dr-editor in a team.
Adversarial reviewer of research reports, drafts, briefs, and technical writeups. Surfaces only load-bearing critiques — claims that would mislead a careful reader, mis-cite a source, or collapse under scrutiny. Use when a draft feels too tidy and you want a hard "what's wrong here?" pass.
Structure and clarity reviewer for research drafts. Audits narrative scaffolding, section ordering, headline-to-body fit, transitions, and whether the report's argument is reconstructable from its TOC. Pairs with dr-critic and dr-skeptic in a team.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A collection of Claude Code skills, agents, and slash commands by goern.
Turns a single research prompt into three artifacts — a deep-research artifact, a publishable humanized report, and a companion blog post — through parallel multi-agent research, iterative synthesis, citation verification, multi-perspective team review, and a final humanizing pass.
Inspired by Anthropic's multi-agent research system.
Four single-shot reviewer agents that audit a research draft from orthogonal angles:
| Agent | Role |
|---|---|
dr-critic | Adversarial — load-bearing logical and factual breakage |
dr-skeptic | Evidence audit — citation quality, source diversity, claim-source fit |
dr-editor | Structure and clarity — argument reconstructability, narrative scaffolding |
dr-audience | Reader-fit — does the draft answer the question for the intended reader |
These ship as reusable subagent types. Use them directly via the Agent tool or spawn the whole team with /team:review.
Spawns a 4-teammate review team (dr-critic + dr-skeptic + dr-editor + dr-audience) against any research draft, report, or technical writeup. Synthesizes convergent findings, auto-applies unambiguous patches, surfaces stalemates as open questions.
/team:review research-output/topic-2026-04-28.md
/team:review research-output/topic.md | What are the tradeoffs of X for Y?
Requires CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 (see Requirements below).
deep-research WorksPrompt → Plan → Parallel Research (2-8 subagents) → Synthesis → Gap-Fill →
Citation Verification → Write Artifact → Team Review → Blog Post → Humanize
dr-critic + dr-skeptic + dr-editor + dr-audience review the artifact, lead synthesizes and auto-applies patches (skipped gracefully if agent teams are not enabled)write-like-goern skill (Critical/Analytical register, structure preserved)Each report uses the Outcomes / Outputs / Results framework and includes a full bibliography with credibility ratings and verification status.
claude plugin marketplaces add https://github.com/goern/goern-skills
claude plugin install goern-skills
Or for development:
claude --plugin-dir /path/to/goern-skills
The /team:review command and Phase 6.5 of deep-research use Claude Code's experimental agent teams feature. To enable it, set the environment variable in your shell:
export CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1
Or via direnv (recommended) — drop a .envrc in the project where you call deep-research:
echo 'export CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1' >> .envrc
direnv allow
If unset, the deep-research skill will skip Phase 6.5 with a one-line note in the plan file and proceed without team review. The pipeline still produces the deep-research artifact, the blog post, and the publishable report — just without the multi-perspective hardening pass.
The Phase 8 humanize pass requires the write-like-goern skill (or any compatible skill named write-like-goern) to be available. If absent, the skill notes the gap and skips humanization.
/goern-skills:deep-research "What is RLHF?"
/goern-skills:deep-research "Compare RAG vs fine-tuning for enterprise LLM deployment"
/goern-skills:deep-research https://arxiv.org/abs/2401.12345
Output is written to ./research-output/:
<slug>-<date>.md<slug>-publishable-<date>.md<slug>-blog-<date>.md| Complexity | Subagents | When |
|---|---|---|
| Simple | 1–2 | Single concept, definitional |
| Moderate | 3–4 | Comparison, multi-faceted, emerging field |
| Complex | 5–8 | Cross-domain, controversial, primary sources needed |
npx claudepluginhub goern/skills --plugin deep-researchGrade a completed OpenSpec change with the Spec Quality Index (SQI) — a 0–100 score measuring how cheaply the spec implemented.
goernComplete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
greyhaven-aiv9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
nyldnUpstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
upstashComprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research
wshobsonComprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications
wshaddixComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Jeffallan