Best architecture decision records skills, page 8

Side-by-side comparison of ruflo vs HAL vs other GAIA harnesses — capability gaps, design decisions, and improvement roadmap

ruvnet/ruflo

One-command drift detection. An agent skill from ruvnet/ruflo.

ruvnet/ruflo

Run @metaharness/darwin evolve {repo} to mutate a harness's seven policy surfaces (planner/contextBuilder/reviewer/retryPolicy/toolPolicy/memoryPolicy/scorePolicy), sandbox-score each variant, and…

ruvnet/ruflo

7-section repo readiness report from metaharness genome {path}.

ruvnet/ruflo

Run a GEPA learning cycle via metaharness learn (upstream ADR-235, metaharness@0.3.0) — optimizes a harness genome against a SWE-bench-style slice manifest.

ruvnet/ruflo

Scaffold a custom AI agent harness via metaharness new {name} --template {id} --host {id}.

ruvnet/ruflo

Composite Phase-2 audit worker (ADR-150). An agent skill from ruvnet/ruflo.

ruvnet/ruflo

5-dimension harness readiness scorecard from metaharness score {path}.

ruvnet/ruflo

Run @metaharness/darwin security bench (upstream "Darwin Shield" / ADR-155) — evolves a champion security-detection harness against a 10-vuln / 9-decoy corpus and grades it on…

ruvnet/ruflo

ADR-152 — weighted similarity between two harness fingerprints (genome + score JSON).

ruvnet/ruflo

Author a workflow — either an MCP workflow template (persisted, lifecycle) or a native .claude/workflows/.js orchestration script (agent/parallel/pipeline fan-out)

ruvnet/ruflo

管理项目稳定领域上下文与难回退决策：按需建立边界严格的 CONTEXT.md，并用 docs/adr/README.md 统一索引、一项决策一个 ADR 文件。用于领域术语反复解释、同词异义、架构或数据库选型、认证/部署/数据模型/API 版本策略、需要记录为什么这样做及如何退出时。English triggers: domain context, context governance…

qshanx/docs-governance

Multi-axis adversarial review using friction engineering. An agent skill from ThibautBaissac/rails_ai_agents.

ThibautBaissac/rails_ai_agents

Apply production-grade design standards when building or reviewing pages, components, or UI.

rampstackco/claude-skills

Keep TestFx feature research and decision records, challenge material design choices, demonstrate user-visible behavior, and prove regression-test sensitivity with red/green comparisons.

microsoft/testfx

Interactive Q&A to gather run context before executing a ResearchOps tree node step.

CurryTang/Amadeus

Phase D of greenfield project bootstrap. An agent skill from papadopouloskyriakos/agentic-chatops.

papadopouloskyriakos/agentic-chatops

Documents the results of a completed technical or design spike, capturing the original question, approach, evidence-backed findings, and a clear proceed-or-not recommendation so the team does not…

product-on-purpose/pm-skills

A skill your agent uses when writing, proposing, or accepting Architecture Decision Records (ADRs) in this repo.

fullsend-ai/fullsend

A skill your agent uses when the user or project explicitly adopts hexagonal (ports and adapters) architecture — a README, CLAUDE.md, or ADR that says so is the opt-in.

citypaul/.dotfiles

Documentation templates for ADRs, runbooks, and architecture docs.

bybren-llc/safe-agentic-workflow

Generate a design document (design proposal) from a PRD, in the style of Go's official design proposals — Abstract / Background / Design / Rationale / Compatibility / Implementation, heavy on the…

smallnest/goal-workflow

Systematically evaluate architecture decisions, document trade-offs, and select appropriate patterns.

jwynia/agent-skills

Record Unity architecture decisions (ADR) with rationale. An agent skill from Besty0728/Unity-Skills.

Besty0728/Unity-Skills

Execute from repository evidence through applicable UI Spec and optional ADR decisions to complete frontend Design Doc approval

shinpr/claude-code-workflows

Generate PRD and Design Docs from existing codebase through discovery, generation, verification, and review workflow

shinpr/claude-code-workflows

Update existing design documents (Design Doc / PRD / ADR) with review

shinpr/claude-code-workflows

Compact the current conversation into a handoff document for another agent to pick up.

alirezarezvani/claude-skills

On-demand index of the AI DIAL Chat design docs in docs/. An agent skill from epam/ai-dial-chat.

epam/ai-dial-chat

Author and wire a new Architecture Decision Record under docs/adr/.

rigortype/rigor

UTILITY SKILL — Reusable Azure Terraform patterns: hub-spoke, private endpoints, diagnostics, AVM-TF modules.

jonathan-vella/apex

Consult Claude Fable 5 (Anthropic's most capable model for deep, long-horizon reasoning — or whichever model currently holds that role) for a genuinely hard, novel CoDD architectural design…

yohey-w/codd-dev

The maintainer's three long-horizon research bets for Flowfile (AI-native flow building, visual↔code round-trip, decentralized execution on a centralized catalog) with the verified existing assets…

Edwardvaneechoud/Flowfile

Architecture Decision Record (ADR) management skill. An agent skill from rvdbreemen/OTGW-firmware.

rvdbreemen/OTGW-firmware

Eng manager-mode plan review. An agent skill from mr-daedalium/ostack-saas.

mr-daedalium/ostack-saas

Import memories into MemMesh from an exported file, a native MEMORY.md / CLAUDE.md, an ADR/decision log, or a mem0 export.

ThinkfleetAI/memmesh

A skill your agent uses when raw data exists — Meta, Google, TikTok, GA4, Shopify, a CRM export, or a spreadsheet — and has to become insight and decisions: descriptive, diagnostic, predictive, and…

minhnv0807/ai-business-skills

Run a historical backtest using npx neural-trader with Rust/NAPI engine (8-19x faster) and walk-forward validation; Ed25519-sign the result for paper→live tamper evidence (ADR-126 Phase 4)

ruvnet/ruflo

Regulator-grade feature attribution for any LSTM/Transformer signal — single-entry PageRank ranks the top-K features that drove the prediction (ADR-126 Phase 6, ADR-123 single-entry PR)

ruvnet/ruflo

Mean-variance portfolio optimization via Conjugate Gradient — 40-60× faster than the legacy Neumann path (ADR-126 Phase 3, ADR-123 Wedge 8)

ruvnet/ruflo

Extract knowledge, guidelines, and ADRs from one or more completed spec directories into the project documentation system.

opsmill/infrahub

Assessment: read-only inspection, codebase overview, value analysis, health checks, ADR consultation, decision analysis, multi-perspective critique.

notque/vexjoy-agent

Quotes, fundamentals, insider, analyst ratings, earnings estimates, financial summary, income/balance/cashflow detail y company profile (delayed 15-20min).

gauss314/skills

A skill your agent uses when choosing or evaluating a technology (framework, database, library, cloud tool) — injects Tikal Israeli Tech Radar context (adoption ring, quadrant, opinion, Keep/Start…

tikalk/adlc-team-skills

Node.js OpenTelemetry setup — SDK init, auto-instrumentation packages, and the esbuild ESM silent-failure gotcha (instrumentation- packages produce no spans when bundled with esbuild --format=esm).

mizchi/skills

A skill your agent uses when planning features and need current API docs, library patterns, or external knowledge; when testing hypotheses about technology choices or claims; when verifying…

ed3dai/ed3d-plugins

Keeping a design system in an LLM's context: loading tokens compactly, persisting design decisions across sessions, handling multiple variants, and budgeting the context window.

HermeticOrmus/LibreUIUX-Claude-Code

Enter explore mode to investigate ideas, systems, problems, and requirements before planning.

unxed/f4