LLM Mart Basic

Merge multiple partial requirements YAML files from different readers into one consolidated req.yaml. Detects field conflicts between sources, identifies critical gaps, and produces a gap report. Run after all readers, before the gap-filling interview in arch-requirements.

Architecture committee review. Evaluates a diagram or design document against enterprise standards with structured scoring per dimension. Produces a gate decision: APPROVED / APPROVED WITH CONDITIONS / REJECTED. Use when: preparing for architecture review board, requesting commit

Deep-dive security audit of a technical architecture diagram. Focused exclusively on authentication, authorization, credential protection, network boundaries, and data classification. Does NOT score overall quality — produces a prioritized security finding list. Use after arch-va

Validate a technical architecture diagram image against enterprise architecture standards. Scores six dimensions (10 pts total), outputs structured JSON + text report. Use when: reviewing a draw.io export, checking a new design before committee review, or running CI validation on

Pipeline gatekeeper that enforces the mandatory ArchHarness stage order (requirements -> design -> draw -> validate -> enforce -> security/review -> optimize -> report). Uses the executable `archharness workflow` state machine — checks recorded manifests and gate decisions before

Use when establishing branching strategies, implementing Conventional Commits, creating or reviewing PRs, resolving PR review comments, merging PRs (including CI verification, auto-merge queues, and post-merge cleanup), managing PR review threads, merging PRs with signed commits,

Set up, evolve, or operate a hraness/wordcell local-first Markdown knowledge base for coding-agent memory. Use when a user asks to design Wordcell conventions or a recurring Wordcell ritual; search or query a Wordcell or Obsidian vault; load or recover repository context, plans,

End-to-end reviewer for a completed multi-phase feature at the end of a phase-orchestrator run. Use after all requested phases are finalized: inspects the whole feature against the plan and PRD/spec, hunting integration bugs across phase boundaries, missing acceptance criteria, s

Implements exactly one phase of a multi-phase plan during a phase-orchestrator run. Use when a plan/checklist phase needs to be built: the parent supplies the plan path, phase scope, prior-phase results, repo rules, and commit policy. Edits files directly; never commits unless co

Orchestrates phase-based implementation plans using the host's todo tracker and subagents for implementation, review, validation, default phase commits, plan finalization, and a final end-to-end review. Delegates work through the companion phase-implementer, phase-reviewer, and p

Reviews and fixes a just-implemented phase of a multi-phase plan during a phase-orchestrator run. Use after a phase's implementation and initial validation: checks the phase against the plan, PRD/spec, repo conventions, security, tenancy/data ownership, migrations, and test cover

Writes or restructures an implementation plan in the format the phase-orchestrator skill consumes: dependency-ordered phases with explicit scope, acceptance criteria, validation commands, and status/log conventions. Use when the user asks to write a plan for phase orchestration,

Build a complete account sheet before a meeting - company, people, news, tech, pains, and talking angles. Use before any important prospect or client interaction.

Produce complete ad creative sets - concepts, hooks, copy, AI-generated images and videos declined per platform and format. Use for Meta, Google, LinkedIn, TikTok campaigns and product launches.

Choose the right depth of reasoning for the task - shallow for routine edits, deep for architecture, security, or ambiguous bugs. Use when work quality depends on thinking harder (or intentionally less).

Read OpenAPI specs, call APIs, validate responses, and draft connectors. Use for integration work, contract testing, and client generation.

Audit the web/API attack surface - authn/authz on endpoints, CORS, CSRF, SSRF, security headers, rate limiting, mass assignment, and OWASP API Top 10. Use for /perimeter, API reviews, or exposed-surface hardening.

Track job applications - statuses, follow-ups, interviews, and reminders - in a structured pipeline. Use to keep a job search organized.

Default Navin skill for architecture and technical diagrams. Create polished, validated architecture, workflow, sequence, data-flow, and lifecycle diagrams as explorable HTML with inline SVG (PNG/SVG/WebM export). Use for system architecture, infrastructure topology, PPT/deck dia

Score CV-to-job-offer match, identify missing keywords, and check ATS parseability. Use before submitting any application.

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.

A systematic AI Agent development tutorial covering LLM agents, RAG, tool use, memory systems, multi-agent systems, LangChain, LangGraph, MCP, and agentic RL.｜从…

Convert Files / Folders / GitHub Repos Into AI / LLM-ready Files

Open-source, local-first conversational AI video editor with a professional multi-track timeline, Agent Skills, MCP integration, and Remotion rendering.

Maintainer-governed agent for evidence-backed open-source contribution proposals

A Claude Code skill by Hao (駱君昊) that learns your Facebook voice and auto-posts to FB / IG / Threads / X with a 14-day content calendar. Mega-viral validated: 8…

Local-first AI agent workspace for coding, writing, design, research, and automation — one runtime for desktop GUI and TUI.

Open-source AI Agent platform for teams. Your agents don't just chat — they read files, run code, call APIs, and deliver results.

Give your AI agent eyes for PDFs — structured text, tables, OCR, visual evidence, and page-level citations via MCP. Native Rust, local-first.

Real-world AI penetration testing engineer for authorized assessments — built-in cloud module covering AWS/Azure/GCP + Aliyun/Tencent/Huawei clouds. Built on Cl…

OpenGUI is an Android GUI agent framework for phone-use AI that can see, plan, and operate real mobile apps through the GUI.

Tinybot is a lightweight personal AI Agent that is constantly evolving

Goink 桌面 AI 小说创作助手，对话式写作 + 自动状态追踪 + 本地语义搜索。跨平台开箱即用。AI Agent Novel Generator.

Pluggable DeepSeek-colored TUI for DeepSeek Harness

Entity-level git merge driver. Resolves false conflicts git invents when independent agents edit the same file. ~95% reduction vs. line-based merge.

Percho: Minimalist desktop GUI for the Pi coding agent — the same engine as the Pi CLI, in a clean visual interface. Multi-session chat, visual tool approvals,…

Run Claude Code, Codex & Gemini in parallel on Windows & macOS — git worktree fan-out with atomic hunk adoption, approval gates, reboot-surviving sessions

A hierarchical memory framework for personalized presentation agents. Try it at memslides.com.

Real-time multimodal desktop agent evolving toward a persistent AI OS interface (0.1 α).

clawdcursor compiles whatever's on screen into one UI map — accessibility tree and OCR fused into stable, addressable elements, with a screenshot only when need…

Repeatable agentic engineering. The workflow layer that turns AI coding agents into a disciplined factory: durable specs, fresh-context workers, adversarial cro…