LLM Mart Basic

Optimize an agent's system prompt, developer message, or policy text — the instructions that shape its behavior. Use when the artifact to improve is a prompt or policy file rather than tools or a skill package: the agent lacks a rule, misses the required output format, or applies

Optimize an agent's OWN tool surface (tools it implements, not an external MCP server). Use when the agent mis-selects tools, fills arguments wrong, calls the same tool N times in a row, or has a confusing, redundant, or oversized toolset. Covers tool names and descriptions, para

Drive the entire cap-evolve pipeline end to end, autonomously. Use when the user wants the whole optimization run with minimal hand-holding. Sequences intake → implement-and-check → baseline → the chosen algorithm loop → finalize → report, enforces the cap-evolve-check hard gate

Front door for cap-evolve: routes an optimization request to the right pipeline phase. Use when someone wants an agent, skill, system prompt, tool surface, or MCP toolset to score higher on an eval, benchmark, or task suite — "optimize my skill", "raise the pass rate on these tas

Establish the starting point. Use after implement-and-check and before any algorithm. Creates the run directory, freezes the seeded train/val/test split (written once), scores the unmodified seed capability on val, and records it as the candidate every algorithm must beat. Report

Extract the learning signal from execution traces — the textual analogue of a gradient. Use between evaluation and proposing edits. Reads a candidate's rollouts and traces, separates good signals to keep from bad signals to fix, builds a reflective dataset (per failing task — Inp

Score a candidate on a split with honest, variance-aware evaluation. Use whenever you need a number for a candidate (the algorithm calls it internally; you can also call it directly to inspect). Runs the target via the adapter for each task, scores each rollout, aggregates mean +

Score the best candidate on the held-out TEST split exactly once and seal the run. Use as the last evaluation step, after optimization stops. The run dir enforces the seal — a second finalize raises an error — so the headline number is produced once on data the optimizer never sa

Apply the acceptance decision that keeps optimization honest — always on the val split, by default requiring the improvement to exceed the significance bar (Δ > k·SE) so noise is not mistaken for progress. Use to inspect or reproduce a single accept/reject decision; the algorithm

Runs the hard gate that has to pass before any optimization budget is spent. Use right after intake. Walks the agent through implementing the 3 required adapter methods plus any defaulted hooks that need overriding (and any selected skill's abstract methods), then runs `cap-evolv

Starts a cap-evolve optimization run. Interviews the user to decide what capability to optimize, which runner/optimizer/algorithm to use, and where the tasks and the scoring source live, then scaffolds .capevolve/project/ (adapter stub, capevolve.yaml, PROJECT.md). Use when someo

Summarize a run for a human — baseline val → best val → sealed test, the winning candidate, iterations spent, and pass^k. Use after finalize. Writes report.md and prints a compact JSON summary; the source of truth for "did this optimization actually work, and by how much".

Use when fixing a bug in an open-source repository given a GitHub issue description. Analyzes the problem, locates the relevant code, and produces a minimal unified diff patch.

Use when writing technical documentation that needs to be readable by both humans and AI models, converting existing docs to HADS format, validating a HADS document, or optimizing documentation for token-efficient AI consumption.

Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers. Use when designing new APIs, reviewing API specifications, or establishing API design standards.

Implement proven backend architecture patterns including Clean Architecture, Hexagonal Architecture, and Domain-Driven Design. Use this skill when designing clean architecture for a new microservice, when refactoring a monolith to use bounded contexts, when implementing hexagonal

Implement Command Query Responsibility Segregation for scalable architectures. Use when separating read and write models, optimizing query performance, or building event-sourced systems.

Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.

Design microservices architectures with service boundaries, event-driven communication, and resilience patterns. Use when building distributed systems, decomposing monoliths, or implementing microservices.

Build read models and projections from event streams. Use when implementing CQRS read sides, building materialized views, or optimizing query performance in event-sourced systems.

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.

{{SKILL_ENTRY:refactor}}

{{SKILL_ENTRY:release}}

Review a diff with the reviewer fleet, funneled to one triaged verdict. Targets the current working diff, a path, or an inbound GitHub PR.

Exploratory spike on a throwaway branch — answer a named question with disposable code. Never merges; exits to a findings note or {{CMD:feature}}.

Autonomous sprint — one interactive spec gate, then plan-to-PR execution with every auto-decision SMARTS-scored and logged. Hard gates remain true stops.

Daily repo hygiene — review the day's repo state, then perform the cleanups under per-action confirmation. Fast-forward only, never destructive without a yes.

Show the project's current state at a glance — stage, open tasks, open questions, overrides since the last checkpoint, current branch. Read-only.

Wire codeArbiter's statusline into ~/.claude/settings.json, or remove it.

The sanctioned task-board mutator — add a queued task, start one (flips to in-progress and stamps the date, minting a dotted ID on pick-up), or mark an in-progress task done. The only blessed write to open-tasks.md.

{{SKILL_ENTRY:security-architecture}}

{{SKILL_ENTRY:tribunal}}

Watch a PR's CI to completion — diagnose on red, notify and offer the merge on green. Never auto-merges.

Copy a file OUT of a running sandbox box to the host — host-initiated egress only (docker cp). The reverse, a host→container bind, is impossible by construction.

Tear down a sandbox box — remove its container and named volume. --keep-volume leaves the volume; with no id, prune reclaims any leaked ca.sandbox=1-labeled object. Cached images are retained.

Run a single command inside a running sandbox box and capture a JSON result — exitCode, separate stdout/stderr, and a truncated flag past the byte cap. The scriptable exec seam.

Open an interactive shell inside a running sandbox box at /work/repo. Read-only root, non-root user, no host-FS access — explore the untrusted code interactively, then exit.

Pull an untrusted repo into an ephemeral, host-FS-isolated Docker container — clone into a named volume, build a dep-cached image, run under structural isolation. Network defaults to offline. Requires Docker and nixpacks.

Vet a new or changed third-party dependency for license, provenance, and supply-chain risk before any install runs.

Inspect ADR health read-only; optionally select one ADR with --adr N.

Record user-decided ADRs or inspect their health read-only. Preserve attribution and acceptance evidence.

Paper trading simulator for Polymarket — built for AI agents. MCP server, live order books, strategy backtesting. Install: npx clawhub install polymarket-paper-…

An SSH tool dedicated to addressing all pain points · (macOS/Windows/Linux/Android/iOS)

The first AI agent harness native to the browser. A browser extension that runs a full agent loop where you already work: it drives your tabs, spins up sandboxe…

SmartLabel AI 2026: Auto-Annotate Any Object via LLM-Powered Prompt Parsing

Local-first visual generation runtime and studio for people and coding agents, with reproducible image and video workflows across multiple providers.

Scholar All-In-One: A research infrastructure for AI agents

Give your AI agent a real browser — with a human in the loop. Open-source MCP-native browser agent.

同花顺免费开源AI插件FQGate-agent（原插件名 tonghuasun-agent）：为 Codex、Claude Code、DeepSeek 等 AI 工具提供本机 A 股实时行情、K 线、Level-2、资讯、账户查询与可选交易能力。

A non-linear AI agent workbench — session is a tree: branch anytime, and context follows the branch

Production-grade AutoCAD MCP server for AI agents — 122 tools, dual COM (live AutoCAD) + headless ezdxf engines, ISO GD&T and dimension-tolerance validation for…

A DeepSeek coding agent harness: persistent shell, Ultra subagents, auto approval, Chrome MCP and session telemetry

Waku Waku! Waku Agent is a local-first AI agent harness you actually own, including loop, memory, eval, all in code built to stay legible as it grows.

Remote control for Claude Code, Codex, Grok, and Cursor on Mac or PC. View sessions, send tasks, and drive them remotely from your phone, PIN, or Ring. OpenClaw…

Next-gen AI-native server ops panel with an in-workspace SRE agent. Crash self-healing, safe rollbacks, Docker/game servers, and local Ollama support.

Professional cloud architecture diagrams with official AWS, Azure and GCP icons, from Terraform code or a plain JSON graph. MCP server + agent skill.

A ready-to-use self-growing desktop AI assistant for long-running tasks, memory, agents, tool reviews, MCP, and high-concurrency workspace automation. / 开箱即用的自我…

Collection of templates using the Alchemyst AI Platform for your next big AI app.

Fast, exact LLM decoding on Apple Silicon (MLX) behind an OpenAI-compatible endpoint

The open source AI research agent.

Open-source agent-native visual production workspace where humans and coding agents edit the same live canvas — local-first, BYOK image/video models.