LLM Mart Basic

Trigger for: FFP IGCE, firm-fixed-price estimate, FFP cost model, proposed FFP rate validation, wrap-rate analysis, Agency BPA rate comparison, price-reasonableness memo, or fair-and-reasonable analysis. Build auditable Firm-Fixed-Price federal estimates using BLS OEWS wages, lay

Trigger for: Labor-Hour IGCE, LH estimate, Time-and-Materials IGCE, T&M estimate, burdened hourly rate, burden multiplier, labor-category ceiling hours, materials estimate, proposed LH/T&M rate validation, price-reasonableness memo, or fair-and-reasonable analysis. Build auditabl

Trigger for: federal acquisition market research; FAR Part 10 reports; refreshing an existing market research report; analyzing commerciality, competition, small-business availability, contract type, consolidation, prior awards, vendors, or market conditions; or preparing support

Trigger for: Other Transaction or OT should-cost, cost estimate, cost-share analysis, milestone pricing, funding profile, proposed-price comparison, prototype price analysis, research OT budget, production follow-on OT estimate, or OT price-reasonableness support under 10 U.S.C.

Trigger for: OT project description, OTA scope, Research OT under 10 U.S.C. 4021, Prototype OT under 10 U.S.C. 4022, follow-on production scope under 10 U.S.C. 4022(f), milestone-based project scope, prototype objective, phase or go/no-go structure, BAA white-paper conversion, SO

Trigger for: writing, revising, converting, or descoping a federal Statement of Work, Performance Work Statement, SOW, PWS, or SOO; develop executable requirements; define contract scope; create measurable performance standards; or prepare requirements before an IGCE. Produce a c

Suede-affiliated Amazon money-recovery audit for restocking fees, short or denied refunds, and Amazon-billed subscriptions. Use when the user mentions a restocking fee, a short or denied Amazon refund, or a forgotten Prime Video Channel, Audible, Kindle Unlimited, or Prime charge

Suede Labs AI full-stack surface builder that runs design, copy, and visual QA as one pass: landing pages, brand surfaces, product UI, dashboards, campaigns, launch pages, and reference-to-target restyles (suedify). Use when a build needs layout and words together, when a redesig

Suede Labs full writing stack: sharper copy for docs, pages, email, social, headlines, CTAs, product listings, and public explainers, with an SEO/AEO/AI EO pass, persona and framework selection, brand-voice alignment, and a scored ship gate. Use when a writing job spans more than

Suede Labs workflow for turning a website, PWA, dashboard, or marketplace into an iOS app. Use when the user has a live site or web app and asks to put it on the App Store, wrap it in an app, ship an iOS version, or convert a PWA to native — covers URL audit, shell-vs-native stra

Suede-owned recovery discipline for recurring charges billed outside Amazon: App Store, Google Play, PayPal, direct-bill streaming, gyms, news, and SaaS. Use when the user wants to find, audit, cancel, or dispute a subscription they may have forgotten, is being charged for twice,

Suede-owned experimentation discipline for hypotheses, sample sizing, test duration, significance, and repeatable experiment programs. Use when comparing variants, deciding whether a result is reliable, or building an experiment backlog and cadence. NOT FOR: analytics instrumenta

Suede-owned paid-media creative system for hooks, headlines, primary text, static and motion concepts, platform specs, review pages, and test-ready variant batches. Use when producing or iterating ad creative from grounded product and audience inputs. NOT FOR: campaign budgets, b

Suede-owned paid-acquisition operating system for channel choice, campaign structure, audiences, bidding, budget pacing, negative keywords, retargeting, and kill-or-scale decisions. Use when planning, auditing, or optimizing paid campaigns on Google, Meta, LinkedIn, X, or compara

Suede Labs agent-team orchestrator: split complex work into coordinated lanes with explicit file ownership, WIP collision detection, quality gates, escalation thresholds, rollback plans, and handoffs that prove what shipped. Use when one shared change needs safe parallel ownershi

Suede Labs AI eval design and coverage audit: AI-SPEC, failure-mode rubric with severity scoring, concrete pass/fail eval cases, coverage and infrastructure scores, and mechanical acceptance gates. Use when a change ships LLM, RAG, agent, classifier, prompt, or generated-media be

Suede-affiliated AI search optimization discipline. Use when the user wants to optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers. Also use when the user mentions 'AI SEO,' 'AEO,' 'GEO,' 'LLMO,' 'answer engine optimization,' 'generative e

Suede-owned measurement discipline for tracking plans, event and conversion instrumentation, UTM and campaign-parameter hygiene, and verification of what actually fires. Use when setting up, auditing, or repairing analytics across web, product, paid, and lifecycle surfaces. NOT F

Suede-owned app-store optimization discipline for keyword fields, titles, subtitles, descriptions, screenshots, ratings context, and competitor listing audits. Use when improving App Store or Google Play visibility or listing conversion from a live app URL and current console evi

Suede-owned marketing attribution discipline. Use when the user wants to figure out which marketing actually drives conversions and revenue, choose or interpret an attribution model, or reconcile conflicting numbers across tools. Also use when the user mentions 'attribution,' 'at

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.

Build an MCP server in TypeScript with focused tools, validated schemas, local and remote transports, Inspector tests, and production security controls.

`crabbox shard` forks a [checkpoint](checkpoint.md) into `--count` leases

`crabbox share` grants other people access to an existing lease through the

`crabbox ssh` resolves a lease and prints a ready-to-run `ssh` command for it.

`crabbox status` prints the current state of a lease: its slug, provider,

`crabbox stop` ends a single lease. For coordinator-backed and direct cloud

`crabbox sync-plan` prints the local sync manifest and its size hotspots

`crabbox tunnel` opens one foreground SSH local port-forward to a resolved

`crabbox unshare` removes sharing rules from a coordinator-backed lease. It is

`crabbox usage` reports lease cost and usage estimates from the broker, broken down by user, organization, or the whole fleet.

`crabbox verify` checks a signed run receipt produced by `crabbox run --attest`.

`crabbox vnc` prints (or opens) the connection details for a desktop-capable

`crabbox warmup` leases a box and waits until it is ready: it provisions (or

`crabbox watch` runs a command on a warm lease, then watches the local

Linux portal viewers default to **Match window**: only the connected controller

`crabbox whoami` calls the broker's `/v1/whoami` endpoint and prints the

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.

{{SKILL_ENTRY:decision-lifecycle}}

Assemble the governance record for a range — commits, overrides, ADRs, sprint auto-decisions, open questions, checkpoint findings — into one dated audit packet. Read-only.

Lightweight Q&A about the project — answer from context and return, no routing, no state change.

PiG (Pi in Go) is a faithful Go port of upstream Pi, the TypeScript codebase behind the Pi coding agent. It is a parity-bound translation, not a rewrite: upstre…

An AI Agent that lives in your pocket. Local-first and privacy focused.

Unofficial skill that teaches coding agents to build with TypeSafe AI's Jev: typed decisions, calibrated confidence, and prior art from 150+ community projects.

Adaptive Test-time Learning and Autonomous Specialization

Prediction-market trading engine — Wang Transform pricing on 291K+ contracts; paper-traded across Kalshi · Polymarket · Solana DFlow (Jito bundles) · 633 tests

Knowledge Management for Humans and Agents

Open-source Claude Cowork / Codex / WorkBuddy alternative — a local-first AI office agent that turns one request into real PPTX, DOCX, XLSX and HTML files. Runs…

DeepAgent Code: AI coding agent with persistent memory and control plane