LLM Mart Basic

Research State of the Art (SOTA) literature for an Artificial Intelligence / Machine Learning (AI/ML) topic, method, or architecture. Finds relevant papers, builds a comparison table, recommends the best implementation strategy for the current codebase, and optionally produces a

Paper-vs-code consistency audit. After research:scientist implements a method from a paper, verify the implementation matches paper claims across five dimensions — formula matching [F], hyperparameter parity [H], eval protocol [E], notation consistency [N], and citation chain [C]

Read local codemap telemetry logs and produce a diagnostic/usage report. Supports date filtering, session filtering, and optional anonymization before sharing. TRIGGER when: analyse recent codemap usage, debug query patterns, investigate errors, or prepare a shareable anonymized

Adapter over `codemap-py integrate` — audit, plan, source-wire, locally sync, and demonstrate the codemap-py integration with its supported consumers. Trigger with `/codemap-py:integration audit|plan|apply|sync|demo [--runtime {claude,codex,both}] ...`. Default (no args) is `audi

Query Codemap's Python structural index for dependencies, callers, paths, symbols, blast radius, test impact, mocks, fixtures, subprocesses, and static gaps. Trigger for "what depends on", "who calls", "imports of", "dependency graph", or "blast radius". Skip for renames, text se

Atomic rename of Python symbols or modules via the structural index — static callers, import sites, __all__ re-exports, Sphinx cross-refs; optional deprecated alias (--deprecate) or hard-delete (--remove-if-no-callers). TRIGGER: "rename X to Y" (function/class/method/module), "mo

Scan the Python codebase and build a structural JSON index (import graph + blast-radius metrics). TRIGGER when: user asks to build, refresh, or rebuild the codemap index; user mentions stale index, missing symbols, or re-indexing after significant project changes; phrases: "build

Identify which tests need rerunning after a code change — traces static call graph (function-level) or import graph (module-level) to find affected test files, then emits a ready-to-run pytest command. TRIGGER when: user asks which tests are affected by a change; phrases: "which

Telemetry report: `$codemap-py:debrief-coding [flags]`; skip integration/index/query.

Codemap integration: audit|plan|apply|sync|demo; skip query/index rebuilds.

Query Codemap.

`$codemap-py:rename-refs`: rename Python names; skip non-Python/unbuilt/local/grep/split/pkg-dir.

`$codemap-py:scan-codebase [flags]` only: Python index; never auto-invoke; skip query/integration.

`$codemap-py:test-impact <qname> [--no-mocks]`: affected tests; skip caller/dependency query/exec.

Ask Codex a read-only question with explicit model, effort, budget, and compact results.

Request cancellation of a running detached Codex bridge job.

Ask Codex for one bounded write-capable change with compact results.

Read a completed detached Codex bridge job's compact result.

Request a read-only adversarial Codex review with explicit model, effort, budget, and compact findings.

Configure, authenticate, repair, and verify the Claude Code to Codex Bridge; safe stages run by default and sensitive stages require separate approval.

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.

Chart a big legal matter as a wayfinder decision map — grill the attorney breadth-first, create the map and decision tickets, fire research tickets in parallel. Planning only: charting resolves no decisions itself.

Define a checkable legal success condition for /legal-loop. Accepts a named profile (citations-clean, draft-passes-gate, adversarial-converge, nda-batch-clean, reg-watch, timeline-sourced) or free-text objective. Produces a persisted Goal Record — never starts work itself.

Iterate a worker-evaluator cycle against a Goal Record until the success condition is met or a stop limit is reached. The evaluator (a different agent than the worker) judges each iteration using MCP verification tools. Produces an auditable verdict trail and a final MET / NOT MET status.

Build a sourced legal chronology from case documents — every event with mandatory provenance, undisputed/alleged/contested status, explicit date conflicts, evidentiary gaps, and optional deadline markers. Outputs table, interactive HTML, and docx under bcc-output/timeline/.

Work one ticket from a legal-wayfinder decision map — claim a frontier ticket, resolve it by type (research / grilling / prototype / task), record the decision, graduate newly-sharp fog, and emit the handoff pack when the map is clear.

Primary entry point for all BetterCallClaude requests — classifies intent, resolves jurisdiction (via swiss-legal-research), runs inline briefing for complexity 4–6, activates full briefing session when complexity ≥ 7 (via legal-intake skill), and routes to specialist agents or workflow pipelines. Invoked explicitly as /bettercallclaude:legal or as the default when no other command matches. Supports --refine, --briefing, --skip-briefing/--direct, --no-framework flags.

Triage NDAs against Swiss law — classify as GREEN (standard) / YELLOW (review) / RED (issues) using playbook thresholds and Swiss legal criteria. Supports single file or batch (folder) mode.

Search and analyze Swiss BGE/ATF/DTF precedents with precedent chain tracking and evolution analysis

View or change the BetterCallClaude privacy mode (strict/balanced/cloud)

Refine vague legal queries into structured prompts through Socratic dialogue, with workflow recommendations and multi-lingual terminology guidance

Search Swiss legal precedents (BGE/ATF/DTF), analyze statutes, and verify citations with multi-lingual support

Check MCP server connectivity

Welcome and first-use onboarding — checks MCP connectivity, guides playbook creation, shows usage examples tailored to your profile. Replaces /setup.

Develop litigation strategy with risk assessment, procedural analysis, cost-benefit calculation, and settlement evaluation for Swiss courts

Summarize and consolidate multi-agent pipeline output -- deduplicate disclaimers, terminology, and citations with length control (--short, --medium, --long)

Translate Swiss legal documents between DE, FR, IT, and EN while preserving legal terminology precision

Validate Swiss legal citations in bulk -- check format, existence, and cross-language consistency

Display BetterCallClaude plugin version, installed components, and system status

Define and execute multi-agent legal workflows -- due diligence, litigation prep, contract lifecycle, real estate closing

Audit web accessibility for WCAG compliance with automated axe-core tests, keyboard and screen reader checks, and remediation guidance

AI agent orchestration kit for Windows, Linux/MacOS with Codex skills, hooks, routing rules and profiles for Claude, OpenCode, Cursor, Gemini and Windsurf.

Skills & reviewer agents for AI-first climate science — built and used by a PhD atmospheric scientist

出行路书工作流 skill：联网实查 + 多源交叉验证，产出可核验、能执行的旅行攻略。覆盖吃住行游拍避全维度，附美食情报卡、基准骨架与校验工具，支持一键部署在线版。

Self-hosted AI code reviewer with indexed PR reviews, walkthroughs, vulnerability scanning, dependency graphs, custom rules, and a learning loop.

🧬 Extend EvoScientist with Installable Skill & Knowledge Packs

Give the agent a machine. Just not yours. Each AI coding agent gets its own isolated machine with root, Docker, and systemd - active defense detects and stops t…

Automatic memory consolidation for OpenClaw agents — like sleep for your AI. Powered by MyClaw.ai

🗂 The essential checklist for modern web development, for humans and AI agents

Distribb CLI, Claude, Codex, Hermes, OpenClaw skill for AI-powered SEO. Write content with your own AI, publish through Distribb's backlink network.

Open-source AI browser agent — type plain-language commands and Bah operates the web for you. Works with cloud AI (DeepSeek, Mistral, NVIDIA) or local Ollama mo…

DeepSeek Harness Desktop (dsh-desktop). EAC: Embracing All Creation (揽尽万象). Bundled Node.js runtime with full dsh-CLI kernel, one-click startup, 10 built-in UI…

Use your ChatGPT / Codex subscription with DeepSeek Harness via OAuth, with model access, usage quotas, search, and image generation — no API key or Codex CLI r…

Local-first A-share research workbench for DeepSeek Harness: market dashboards, watchlists, valuation, four investor agents, versioned reports, and continuous p…

Open-source video pipeline (clipper, AI video & more) — scout trends, clip long videos, generate captioned shorts, design motion graphics. Local-first, BYOK. AG…

Desktop app for the pi coding agent: streaming timeline, Git review with hunk staging, session tree, native UI for pi extensions. Windows · macOS · Linux. pi 编程…

Zero-dependency browser video editor that AI agents can drive — JSON timeline, MCP + REST, live-reloading UI

Personal Context Manager for Claude Code. Your life in walnuts.

Fast way to switch between Claude Code configuration profiles

AutoClip｜一个链接，一键出片。开源 AI 视频剪辑桌面工具，将播客、访谈、课程等长视频自动剪成短视频，生成字幕、封面和发布文案，适配抖音、小红书、TikTok、Reels 与 YouTube Shorts。Open-source AI video clipping & content repurposing.