LLM Mart Basic
@llm-mart · Joined Jun 2026
Create a CHANGELOG.md following keepachangelog.com conventions with version history backfilled from GitHub releases or git tags. Use when the user asks to "create a changelog", "add a changelog", "initialize changelog", "start a changelog", "set up changelog", "generate changelog
Write a handoff file at .turbo/handoff/<YYYY-MM-DD>-<slug>.md capturing current session state — task, status, open decisions, in-flight changes, next step — so a fresh session can continue without re-deriving context. Use when the user asks to "create a handoff", "create handoff"
Create a GitHub issue with a drafted title and body. Use when the user asks to "create an issue", "file an issue", "open an issue", "submit an issue", "report a bug", "file a bug report", "file a feature request", or "file a design proposal".
Create a GitHub pull request with a drafted title and description. Use when the user asks to "create a PR", "create a pull request", "open a PR", or "submit a PR".
Scans an existing codebase and generates project-specific skills that capture inferred conventions such as naming, file organization, framework usage, data access, error handling, and testing style. Writes into the project's chosen skill directory (e.g., `.claude/skills/`, `.agen
Create a new skill or update an existing skill that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations. Use when the user asks to "create a skill", "make a new skill", "build a skill", "scaffold a skill", "write a skill for...", or "new skill
Analyze what changed and generate a structured test plan at .turbo/test-plans/<slug>.md covering four escalating levels: basic functionality, complex operations, adversarial testing, and cross-cutting scenarios. Use when the user asks to "create a test plan", "plan tests", "what
Analyze a codebase and produce a structured threat model at .turbo/threat-model.md covering assets, trust boundaries, attack surfaces with existing mitigations, attacker stories, and calibrated severity. Use when the user asks to "create a threat model", "threat model", "threat m
Align on the shape of a change through an interview, then implement it. Escalates open product decisions and settles the implementation shape in conversation. Use when the user asks to "discuss this change", "align on this change first", "ask me questions first", "interview me th
Produce an implementation plan at .turbo/plans/<slug>.md. Use when the user asks to "draft a plan", "draft the plan", "write an implementation plan", "plan this change", "create an implementation plan", or needs a first-draft plan file before refinement.
Critically assess external feedback (code reviews, AI reviewers, PR comments) and decide which suggestions to apply using adversarial verification. Use when the user asks to "evaluate findings", "assess review comments", "triage review feedback", "evaluate review output", or "fil
Explain whatever the user is pointing at right now in plain language: a pending question, a piece of code, an error, a command output, or an artifact like a plan or findings report. Use when the user asks to "explain this", "what am I being asked", "what's happening right now", "
Execute multi-level exploratory testing of the app covering basic functionality, complex operations, adversarial testing, and cross-cutting scenarios, plus usability observations through a UX lens reported separately from defects. Deeper than $smoke-test. Use when the user asks t
Fetch and summarize review feedback and conversation from a GitHub PR (unresolved review threads, review bodies, and PR conversation comments) without making changes. Use when the user asks to "fetch PR comments", "show PR comments", "check PR for unresolved comments", "list revi
Run the post-implementation quality assurance workflow including tests, code polishing, review, and commit. Use when the user asks to "finalize implementation", "finalize changes", "wrap up implementation", "finish up", "ready to commit", or "run QA workflow".
Find dead code using parallel sub-agent analysis and optional CLI tools, treating code only referenced from tests as dead. Use when the user asks to "find dead code", "find unused code", "find unused exports", "find unreferenced functions", "clean up dead code", or "what code is
Create distinctive, production-grade frontend interfaces with high design quality. Use when the user asks to build landing pages, websites, dashboards, web components, or any frontend UI. Generates creative, polished code that avoids generic AI aesthetics.
Shared writing style rules for GitHub-facing output (PR comments, PR descriptions, PR titles, issues, design proposals). Differentiates insider vs outsider voice based on author association. Not typically invoked directly — loaded by other skills before composing GitHub text.
Load code-style and task-specific skills, make the change described by the current context, then run post-implementation QA. Use for ad-hoc changes when no plan file or improvements backlog governs the work, and when the user asks to "just implement", "implement directly", "imple
Validate improvements from .turbo/improvements.md, recommend a working set tailored to what's in the backlog, and run one lane: direct fixes, investigation, or planned work. One lane per session. Use when the user asks to "implement improvements", "work on improvements", "address
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.
Use MCP Inspector to connect to local or remote servers, inspect capabilities, call tools, read resources, test prompts, and diagnose failures before release.
/dashboard-cockpit
Dashboard cockpit
Repeatable pass upgrading an Angular admin dashboard into a compact black-and-cyan developer-cockpit PWA
/drift-check
Drift check
Run the drift-detection checklist (incl. agent-drift signals); report + fix in-turn
/final-review
Final review
Orchestrate the final review fan-out (integration + diversity + risk + release readiness)
/improve-lint
improve-lint
Run the AI-augmented lint self-improvement loop on the current project. Scans `.lint-history/` for recurring violation patterns (≥3 hits in 30d window), drafts a Claude-ready prompt to author a new semgrep rule for the top candidate, and surfaces the proposal under `.lint-history/proposals/<ts>.md`. Non-blocking analysis. See rules/lint-doctrine.md § Self-improving.
/install-lint-stack
install-lint-stack
Bootstrap industry-leading lint+autofix+commit-hygiene stack on the current project. Drops in lefthook, oxlint, ESLint, Prettier, Stylelint, markdownlint, ruff, shellcheck, shfmt, yamllint, hadolint, actionlint, jscpd, knip, semgrep, gitleaks, commitizen + git-cz-emoji (emoji-mandatory commits), and semantic-release. Idempotent — re-runs upgrade safely. See rules/lint-doctrine.md.
/list-arcs
list-arcs
Surface all retrospective documents with key shape metrics; compare arcs deliberately.
/multimedia-enrich
Multimedia enrich
Progressive multimedia enrichment pass — add high-value audio/video/image/interactive to a site, run again and again
/plan-execute-verify-repair
Plan execute verify repair
Run the autonomous-engineering operating loop on a task (plan→implement→verify→repair→report)
/post-arc-retrospective
Post arc retrospective
Capture the cumulative output of a /loop arc into a single auditable retrospective document; scans the heymegabyte-claude-skills plugin for modified files, categorizes by directory, counts LOC delta, extracts tool counts from MCP servers, and writes a timestamped report to retrospectives/
/prepare-multi-file-brief
prepare-multi-file-brief
Turn a comma-separated list of file paths into a fully structured Pattern A agent brief — ordered writes, per-file schemas, and a verification step baked in.
/prepare-skeleton-brief
prepare-skeleton-brief
Turn Pattern B from agent-resilience-discipline into a one-keystroke agent brief for a single-file deliverable < 300 lines.
/process
Process
Chain the full Superpowers process flow — brainstorm → plan → worktree → build → review → finish — on one slash command
/retro
Retro
Generate a timestamped arc retrospective from the past 7 days of git history in `~/.agentskills`.
/review-global-prompts
Review global prompts
Review ~/.claude/CLAUDE.md + rules for contradictions, stale guidance, duplication; consolidate
/run-evals
Run evals
Batch-run all LLM eval cases in tools/evals/cases/*.json; aggregate pass/fail, cost, regression vs last run; exit nonzero in CI mode
/saas
Saas
One-line SaaS — from a description, scaffold a complete CF-native multi-tenant SaaS (Hono + D1 + Drizzle + Better Auth + Stripe + shadcn) deployed to a real URL
/security-supply-chain
security-supply-chain
Unified supply-chain audit. Checks GitHub Actions SHA-pinning (`sha-pin:check`), package.json git+https deps (per `no-gitlab-megabytelabs-deps` semgrep), gitleaks scan, and trufflehog verified-only sweep. Surfaces any tag-mutable, git-URL, or secret-exposed surface. Per rules/ai-agent-security.md § Supply chain.
/self-improve
Self improve
Run a learning pass after a major run; fold reusable lessons into global config
/session-recap
session-recap
Summarize recent CHANGELOG.md entries for context restoration. Parses the canonical heading shape `## YYYY-MM-DD — pass-N — summary`. Filters: last N (default 10), YYYY-MM date prefix, or "today". Supports --json for machine-readable output.
/skill-health
Skill health
Run quality-scores + token-budget + dep-graph, interpret results, flag missing budgets, orphans, and oversize skills
MCP server for reusable prompt templates, multi-step workflow chains, and quality gates. Compose agentic workflows with an operator syntax; export as native ski…
16 views 0 likes中国股票数据基础设施,覆盖行情、研报、资金面、筹码、公告、龙虎榜、ETF/期权、舆情互动、基本面、行业板块、宏观与风险事件等核心数据。42+A股数据集,日更、自托管、MCP 原生,零注册、零 API Token
15 views 0 likesOKF (Open Knowledge Format): Durable, structured memory for AI agents. Author, validate, consume, and maintain portable knowledge bundles through an ecosystem o…
32 views 0 likes토스증권을 AI 에이전트와 터미널에서 다루는 도구. CLI 와 MCP 서버로 계좌·시세·주문은 물론 웹앱 전용 기능(수급·AI 시그널·스크리너·배당)까지, JSON·CSV 구조화 출력으로 AI 도구·자동화에 바로 연동.
30 views 0 likesClaude skills for LinkedIn. 11 Claude Code and Codex skills that write human-sounding LinkedIn posts, craft comments that get noticed, analyze your feed, and bu…
27 views 0 likesMCP server connecting AI agents to ITASCA engines (PFC, FLAC, 3DEC, MPoint, MassFlow) — run geotechnical & geomechanics simulations through natural conversation
18 views 0 likesA curated list of amazingly awesome articles, people, applications, software libraries and projects related to the knowledge management space
16 views 0 likesOne local dashboard for every Claude Code, Codex, Cursor, Antigravity, and Kilo Code session on your Mac. Spawn in parallel, ship in parallel. Open source, MIT.
30 views 0 likesBuilding blocks for frontier OpenAI agents in Rust. Nanocodex empowers you with Codex-level performance anywhere.
29 views 0 likesThe AI agent that lives in your framework/browser
28 views 0 likesSelf-Programming AI Assistant. Capture, automate, and refine all your workflows.
18 views 0 likesConsider it done. The open-source AI agent that works out of the box · 想到,就能做到。开源、开箱即用的 AI Agent。
15 views 0 likesMake Any Website into CLI & Use your logged-in browser by AI agent.
32 views 0 likesISO 24495 Plain Language skills and Claude Code plugin
16 views 0 likesDeterministic, fail-open tool routing for Hermes Agent with an optional local-model fallback.
15 views 0 likes1인 사업가 생산성 키트 — 직원 없이 49개를 자동화했고, 그중 바로 쓸 수 있는 AI 에이전트 스킬 26개(+실행 스크립트)를 공개합니다
12 views 0 likesAI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agent…
28 views 0 likesThe open-source, self-hosted video conferencing software. Scalable, customizable, and with a powerful AI Meeting Agent.
27 views 0 likesBusiness operating system for Claude Code — 57 skills, 21 agents, smart daemon. Unified inbox (WhatsApp/Email/Slack/Telegram), autonomous PR merge, full-AWS mon…
18 views 0 likesA local-first, cross-platform Electron desktop workspace for Pi Coding Agent, with sessions, project files, browser tools, skills, plugins, and messaging integr…
17 views 0 likes