LLM Mart Basic

가장 최근 윤문 결과를 2차로 다시 다듬는다 — 특정 카테고리·문단·강도 조정도 가능. humanize-korean strict 윤문(Phase B)을 기존 run_id에 재실행해 잔존 finding을 처리한다. 트리거 — "/humanize-redo".

AI(ChatGPT·Claude·Gemini)가 쓴 한글 텍스트를 사람이 쓴 글처럼 윤문한다. 번역투·영어 인용 과다·기계적 병렬·관용구·피동 남용·접속사 남발·리듬 균일·이모지/불릿 과다 등 10대 카테고리 70개 AI 티 패턴을 탐지·분류해 내용은 한 글자도 건드리지 않고 문체·리듬·표현만 자연스럽게 재작성한다. 트리거 — "AI 티 없애줘", "AI 윤문", "ChatGPT 티 제거", "번역투 고쳐", "사람이 쓴 것처럼", "humanize Korean". 단순 맞춤법 교정·번역·내용 추

정밀(strict) 모드 1단계 진단 에이전트. 글 전체를 한 번에 보고 "가장 지배적인 AI 티 패턴 3~6개"를 taxonomy ID와 함께 진단한다. 불안정한 span 열거(0↔18개로 요동) 대신 "무엇이 이 글을 지배하는가"라는 안정적 판단을 내려, 후속 윤문 콜이 그 진단을 겨냥하게 한다. 산출물은 02_diagnosis.md 1개. 도구 호출 3회 캡(Read 결합입력 + Read taxonomy + Write 진단). 이 진단이 정밀 모드 품질의 결정 변수다.

정밀(strict) 모드 3단계 마무리 에이전트. 원문과 윤문본을 직접 대조해 ①의미 보존(15항 — 각주·제목·없던 주장 주입 포함) ②자연성(잔존 AI 티 + 과윤문 양방향)을 한 콜로 병합 판정하고, 문제 구간만 국소 보정한다. 전체 재작성 금지 — 의미 드리프트(빈 수사를 없던 주장으로 대체)를 막는 게 존재 이유. 은퇴한 content-fidelity-auditor·naturalness-reviewer 2인을 대체한다. 산출물은 final.md + 09_finalize.json. 도구 호

v1.6.1 Fast Path 단일 호출 윤문 에이전트. 한 호출 안에서 탐지·윤문·자체검증을 일괄 수행하여 5,000자 이하 한글 입력을 2~3분 안에 처리한다. 산출물은 final.md 1개(본문 끝에 `<!-- HUMANIZE-SUMMARY -->` HTML 주석 블록으로 메트릭·등급·자체검증 통합). 도구 호출 chain 3회 캡. 깊은 검증이 필요하면 정밀 모드(진단→윤문→finalize 3콜) 사용.

AI가 생성한 한글 글의 "AI 티" 패턴을 체계적으로 분류·확장·버전 관리하는 도메인 전문가. `references/ai-tell-taxonomy.md`를 단일 진실 원천(SSOT)으로 유지하며, 실제 입력에서 관찰된 신규 패턴을 검증해 v1 → v2로 승격한다.

한국 번역학계(이근희·김정우·김도훈·김순영·김혜영·이영옥·곽은주·조의연)와 국제 번역학(Baker·Toury·Laviosa·Chesterman·Toral·Sarti)의 학술 인용 계보를 Humanize KR 본진 SSOT(taxonomy.md)와 외부 references/scholarship.md 양면에 안전하게 안착시키는 학술 정통성 큐레이터. 보고서의 학술 자산을 본진 분류 체계가 검증 가능한 형태로 흡수하되, SSOT 룰북 슬림성을 해치지 않게 메타필드 + 외부 파일로 분리. 본진 패턴에 출

Toral 2019 post-editese 3축(단순화·정규화·간섭)을 한국어 정량 지표로 구체화하고, 보고서 8유형 검출 시그널을 metrics.py에 추가해 회귀 검증 가능 상태로 만드는 정량 엔지니어. 표준 라이브러리만, 형태소 분석은 정규식·접미사 사전으로 근사(konlpy·mecab 금지 — v1.6 정책 보존). monolith 외부 사전 처리(prepare_monolith_input.py)에 결합되어 도구 호출 캡 3회 보존. 신규 metric 추가 또는 metric 회귀 검증 시 호

신규 분류 체계 v2.0과 metrics·playbook 패치를 quick-rules.md(monolith 전용 슬림 룰북, 126줄 → ≤180줄)에 안착하고 monolith 도구 호출 3회 캡(v1.6.1) 회귀를 검증한 뒤, GitHub PR 초안과 CHANGELOG를 작성하는 통합 엔지니어. 본진 룰북 슬림성·monolith 정의 무수정·v1.x 발행 정책(사용자 명시 승인 후 푸시)을 3대 가드로 삼음. v2.0 변경 묶음을 PR로 발행 직전 단계에서 호출.

Humanize KR 본진 v1.6 분류 체계(10대 카테고리·61+ 패턴)와 외부 학술 보고서 후보 풀(translationese-research-distiller 산출물)을 3-축 매트릭스(이미 본진·보강·신규)로 매핑해 분류학자에게 승격 결정 입력을 제공하는 갭 분석가. 사실 발견만 하고 승격 결정은 하지 않는다 — taxonomist가 최종 판정자. 본진 v1.6 → v2.0 업그레이드 회차 또는 외부 보고서를 본진과 합칠 때 호출.

한국어 번역투(translationese) 학술 보고서를 8유형·15항목 PE 체크리스트·post-editese 3축·학술 인용 계보·예문 코퍼스로 분해해 후속 분류·승격 단계가 직접 소비할 수 있는 구조화 JSON으로 증류하는 도메인 추출가. 보고서 본문에 명시된 사실만 추출하고 자체 추정·확장은 금지. 보고서가 한국 번역학계의 8대 번역투 유형(무생물 주어·피동·대명사·-들·관계절·have-make·조사 결합·종결어미)을 다루거나 Toral 2019 post-editese·Baker 1993

Handle ZenTao (禅道) Bugs and Tasks end to end, including updating or writing back an item after code changes, managing Task status and hours, and reading linked Stories. Use for referenced ZenTao items, requirements, status changes, time entries, or post-implementation synchroniza

Generate a Conventional Commits message from staged changes and wait for confirmation before committing. Use when the user asks to commit or generate a commit message.

Summarize each day's Git activity into a concise daily work log, for a single date or a range. Uses the current repository, optional configured work projects, or paths named in conversation; configuration is never required.

Review code changes for bugs, regressions, convention violations, and high-value cleanup opportunities. Use for diffs, commit ranges, hosted PR/MR URLs, branches, paths, staged changes, or working-tree changes.

Summarize a contributor's Git history, a provided work log, or both into a concise, review-friendly self-evaluation for quarterly, semi-annual, or promotion cycles.

Refactor changed code to reduce duplication, complexity, and wasted work. Use for diffs, commit ranges, PRs, paths, staged changes, or working-tree changes.

Query and display the current API provider balance and recent usage.

Inspect screenshots, photos, diagrams, image paths, and image URLs when the task depends on visible content. Use when the prompt lacks actual image content, native inspection fails, or the user requests inspect_image; prefer the MCP tool, then the installed CLI.

Use when working on accessibility, a11y, WCAG, ARIA, screen readers, keyboard nav, focus order, contrast, alt text, captions, reduced motion, or target sizes; not language/culture/device (see inclusive-design).

Fourteen posts of being wrong in production, compressed to checkboxes

Healthy nodes, a quiet network, 300 restarts in three days, and a latency budget measured in milliseconds

Discovery worked. Ping worked. Every TCP connection timed out, and later the tunnel only worked when someone had a terminal open.

Every VM came back. The cluster did not. Declarative systems converge on config, and the datapath isn't config.

A surprising share of AI-in-the-terminal failures aren't the AI. They're zsh, and a version of bash from 2006.

A Claude Code plugin turns standalone project configuration into a namespaced, installable extension that teams and communities can update as one unit.

None of the safety came from the model. It came from six boring habits.

Skills package instructions and references. Subagents run work in a separate context and return results. They solve different problems and can be composed deliberately.

Six hours in, one step left, everything green, and the incident that didn't happen

CLAUDE.md carries persistent project context. Skills load reusable procedures when relevant. Separating stable facts from task-specific workflows keeps both easier to maintain.

Twenty minutes recovering secrets that never existed, and the one sentence from a human that ended it

An API request routing a model's tool call through an approval gate to a remote MCP server

31 config keys, two audits, and why the first one was wrong in both directions

The official MCP Registry stores standardized server metadata rather than package code. Publishers verify a namespace, describe installation or remote access, and submit immutable versions.

Everyone looks at the Dockerfile. The file that actually leaked the key was the project file.

Remote MCP authorization uses established OAuth standards, but secure integration still requires issuer validation, least-privilege scopes, protected token handling, and server-side enforcement.

"Copy it over and switch the reference" is two steps, and the outage lives in the one nobody checks

stdio fits local processes and prototypes. Streamable HTTP fits hosted services and shared integrations. The right choice follows where the capability runs and who must reach it.

The most important rule wasn't about what I could change. It was about what I was allowed to display.

Tools perform operations, resources expose readable context, and prompts provide reusable templates. Choosing the correct primitive makes an MCP server easier to understand and govern.

Instrument services with structured logging, Prometheus metrics, and OpenTelemetry tracing. Build Grafana dashboards, write Prometheus alerting rules, run k6 load tests, and plan infrastructure capacity.

Generate, test, validate, explain, and debug OPA (Open Policy Agent) Rego policies and Conftest configurations. Covers deny/warn/violation rules, unit tests, regal linting, conftest fmt, namespace design, input shape analysis, and GitHub Actions integration. Use when asked to "write a policy", "test a rego file", "validate policies", "explain this rego", or "why is my policy not firing".

OpenShift SCC diagnosis and hardening, Route TLS patterns, OpenShift GitOps app delivery, and cluster upgrade validation.

Comprehensive PR review across six dimensions — cost impact, environment drift, ownership gaps, SOC 2 compliance, deprecated API / version hygiene, and rollback feasibility. Each mode inspects the diff and current file state, reports findings with severity, and recommends concrete fixes. Use when preparing a PR for merge, conducting a pre-deployment readiness check, or performing a post-merge risk assessment.

Production-readiness preflight check for a directory, repo, or single file. Auto-detects file types (Kubernetes manifests, Terraform, GitHub Actions workflows, Helm values/charts, Flux Kustomizations/HelmReleases, Dockerfiles, shell scripts) and applies type-specific checks across the whole scope. Returns a per-file summary table and aggregated verdict. Use before deploying, merging, or applying a folder of config. For PR diffs spanning multiple files use /platform-skills:pr-review instead. For deep Helm chart work use /platform-skills:helmchart instead.

Apply product thinking to platform work — DevEx audits, friction analysis, RFC/ADR drafting, incident communication, post-mortems, capacity planning, cost optimisation, and platform health review.

Generate renovate.json covering all dependency file types used in a repo, emit a GitHub Actions workflow that validates renovate.json on every PR, or generate a pre-commit hook for local validation.

Detect and respond to in-container threats at the syscall level using Falco (eBPF-based, CNCF, open-source, no license cost). Covers Falco installation on EKS/GKE with eBPF driver, custom rule authoring, alert routing via Falcosidekick, rule debugging, and bridging Falco runtime signals to Kyverno admission enforcement. Use when asked to "detect privilege escalation in containers", "set up runtime threat detection", "write a Falco rule", "route Falco alerts to Slack", or "debug why my Falco rule is not firing".

Secrets strategy, External Secrets Operator scaffolding, Sealed Secrets seal/rotate/backup, rotation runbooks, and Kubernetes-side secrets audit.

Bootstrap and operate a self-improving agent workspace. Scaffolds .learnings/ and memory/ directories, captures errors and learnings during a session, detects recurring patterns, recalls verified lessons, and promotes stable entries to scoped rule files (.claude/rules/ or ~/.claude/rules/). Also implements the Proactive Agent pillars — WAL protocol, working buffer, SESSION-STATE, daily notes, VBR, VFM scoring, ADL decision logic, heartbeat, and reverse prompting. Use when asked to "remember this lesson", "set up agent memory", "log that error", "what did we learn about X", "promote learnings", "revoke that rule", "capture session state", or "enable proactive mode".

Scaffold a multi-agent AI setup for any repo. Scans the codebase, interviews the developer, generates agent configs for whichever AI tools the repo uses (Copilot, Claude Code, Cursor, Codex, Windsurf). Use when asked to "set up agents", "scaffold Copilot agents", or "create an AGENTS.md".

Secure the software supply chain from source to running container. Covers Cosign keyless image signing (Sigstore/Rekor), SBOM generation and attestation (Syft), vulnerability scanning with severity gates (Trivy/Grype), SLSA Level 2 provenance, and Kyverno/OPA admission enforcement. All open-source, no license cost. Use when asked to "sign my image", "generate an SBOM", "scan for CVEs", "attest build provenance", "enforce image signatures in Kubernetes", or "implement SLSA".

Runs through the full Terraform validation pipeline — fmt, validate, tflint, security scan — and reviews a module or plan for blast radius, IAM risk, and state impact.

Triages a PR comment — from a bot (Copilot, CI) or a human reviewer. Routes to the `triage_helper.py` helper for identity checks, thread snapshotting, isolated-worktree fixes, and publish/reply/resolve mechanics; you classify the finding and apply a justified fix. `--dry-run` is fully read-only (investigation and a printed plan, zero mutations). `--no-resolve` runs the full fix/reply workflow but never resolves a thread. Run from inside the repo.

Scan container images, filesystems, git repos, and existing SBOMs for CVEs, secrets, and license violations using Trivy. Covers local CLI, CI severity gates with SARIF upload, and continuous monitoring via Trivy Operator (Flux HelmRelease). Use when asked to "scan my image", "check for CVEs", "scan this repo for secrets", "scan an SBOM", or "set up continuous cluster vulnerability monitoring". IaC misconfig → /platform-skills:checkov. Admission posture → /platform-skills:kyverno. Image signing/SBOM generation → /platform-skills:supply-chain.

Audit GitHub Actions workflows, composite actions, Dependabot configs, and pre-commit configs for security findings using zizmor — template injection, credential persistence, unpinned uses, over-broad permissions, impostor commits. Covers local CLI, auto-fix, zizmor.yml policy, severity-based CI gates, SARIF upload, and pre-commit. Use when asked to "audit my workflows", "run zizmor", "is this workflow safe", "check for template injection", "pin my actions", or "set up a zizmor CI gate". Workflow syntax and shell errors → /platform-skills:github-actions (actionlint). IaC misconfig → /platform-skills:checkov. Image and dependency CVEs → /platform-skills:trivy. Keeping SHA pins fresh → /platform-skills:renovate.

반복 작업을 `/이름` 으로 호출. 파일명 = 커맨드 이름(`fix-issue.md` → `/fix-issue`).

이슈 #$ARGUMENTS 를 처리한다(이슈 우선 워크플로):

AGENTS.md 생태계(rules·memory·agents·skills·commands·workflows)의 연결 구조를

이슈/기획서 기준 SDLC 한 사이클(이슈→개발→테스트→검증→PR/MR)을 사람 개입 없이 자동 실행.

AI coding platform for teams

AI Multi-Agent Framework in .NET

Production-ready code examples for Telnyx AI Communications Infrastructure — Voice AI, SMS, SIP, and IoT APIs

UltraGameStudio - AI coding agent for game development: engine workflows, gameplay code, and asset generation.

🦞 ResearchClawBench: Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery

The context-aware model router that learns & adapts to your long-horizon coding agent workflows. Lightweight & extensible, works with any harnesses, any models,…

Open-source sandboxes where coding agents build and deploy. Spin up isolated environments where Claude Code, Cursor, and other agents code and deploy software.

Native desktop UI for Claude Code with orchestration, streaming, background agents, and multi-provider support. Built with Tauri + React.

OpenCode mobile client via Telegram: run and monitor AI coding tasks from your phone while everything runs locally on your machine. Scheduled tasks support.

Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.

Exposes internet search tools for use by LLM-backed Assist in Home Assistant

Templates and workflow for generating PRDs, Tech Designs, and MVP and more using LLMs for AI IDEs

Versus Incident is the self-hosted AI SRE agent. It learns what your system normally look like and escalates only what is new or unexpected issues — routing to…

Browser-native side panel for Hermes Agent — connect web context to your local Hermes runtime.

Agentic-friendly CLI generator for APIs: turn Swagger, OpenAPI, and google.api.http protos into single-binary CLIs with catalogs and generated Skills.

Open-source agent platform for Global × China enterprises — wire every system through one agent core. Self-hosted, any LLM.

Official python implementation of UTCP. UTCP is an open standard that lets AI agents call any API directly, without extra middleware.

An agent small enough to run anywhere. A minimal agentic runtime in C — ~380 lines, 54KB binary, ~2MB RAM. A skill file + an LLM + a shell loop, no framework.

AgentiLoop Agent! An Autonomous Agentic Agent for Mac, and exclusive Apple only harnesss. Suppprtd automation, scripting, coding, build anything and more. Power…

微信公众号 AI 运营助手 | 选题、写稿、审稿、排版、配图、发布全流程 Skill，支持 OpenClaw / Claude Code / Cursor / Codex