LLM Mart Basic
@llm-mart · Joined Jun 2026
Use GitHub Backup when an agent needs to mirror repositories, release assets, and gists into local storage on a schedule, instead of manually exporting GitHub content repo by repo.
Synchronizes service metadata into Spotify Backstage catalog using catalog-info.yaml generation and the Backstage Catalog REST API. Manages component, API, and system entity relationships across teams.
Creates Spotify Backstage software templates using template.yaml definitions with Scaffolder actions including fetch:template, publish:github, and catalog:register. Manages the Backstage Software Catalog via its REST API.
BackstopJS gives agents a repeatable way to capture reference screenshots, compare UI states, and flag visual regressions before changes ship. This skill centers on the real BackstopJS project and turns browser-based layout comparison into a structured QA workflow for web teams.
Generates social media graphics and OG images dynamically via Bannerbear REST API. Manages template modifications, font layers, and signed URL generation for on-the-fly image personalization.
Scan a repository for secrets, keep an auditable baseline, and review only newly introduced findings during commits or CI checks.
Baserow is an open-source no-code platform for databases, automations, internal apps, and API-first workflows. It is useful when teams need spreadsheet-like data management, self-hosting, and programmable access without building a custom admin stack from scratch.
bat is a cat(1) clone written in Rust that adds syntax highlighting for over 200 languages, Git integration showing file modifications, automatic paging, and line numbering. It serves as a drop-in replacement for cat with enhanced readability for code and configuration files.
Analyzes Bazel build dependency graphs to identify bottlenecks and optimize build times. Uses the Bazel Query Language (BQL), Action Graph API, and Build Event Protocol (BEP) for deep build analysis.
Finds and compares 184,900 swimming spots worldwide (beaches, lakes, bathing places) with live water temperature, wind, UV and wave signals, local guides and source-backed activity providers, via the public BeachFinder MCP server.
Bearer CLI is an open-source static application security testing (SAST) tool that scans source code to identify, filter, and prioritize security vulnerabilities and privacy risks. Covers OWASP Top 10 and CWE Top 25 with data flow analysis across multiple languages.
Extracts structured citation data from academic repositories using BeautifulSoup4 with lxml parser. Parses DOI metadata, author affiliations, and reference lists from PubMed, arXiv, and Semantic Scholar HTML.
Bedrock is a WordPress boilerplate with Composer-based dependency management, environment-specific configuration via .env files, and an improved folder structure. It separates WordPress core from application code for cleaner version control and deployment.
A source-backed ASE skill for Beekeeper Studio, the SQL editor and database manager for Linux, macOS, and Windows. It fits workflows that need a real client for querying, browsing tables, and working across PostgreSQL, MySQL, SQLite, SQL Server, and other supported databases.
Manage and tag music libraries with beets, the Python-based CLI tool that auto-tags audio files using MusicBrainz metadata. Import, organize, deduplicate, and query your music collection with a powerful plugin system and flexible query language.
Use MemoryBench to run repeatable conversational memory and RAG benchmarks across providers, datasets, judge models, checkpoints, and structured reports.
Benchmark clean and incremental Xcode builds, surface compile and configuration hotspots, and produce an approval-first optimization plan before changing project files.
Compare browser-agent reliability on a repeatable task and anti-bot suite before choosing a stack or claiming progress.
Run a repeatable evaluation suite for browser agents against static web task snapshots instead of judging them from demos or one-off tests.
Run Claude Code, Codex CLI, Gemini CLI, or OpenCode through bounded H100 post-training tasks and compare how well each agent improves a base LLM.
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.
An MCP server exposes tools, resources, or prompts through a standard protocol so an AI application can discover and use external capabilities.
/refactor
Refactor
{{SKILL_ENTRY:refactor}}
/release
Release
{{SKILL_ENTRY:release}}
/review
Review
Review a diff with the reviewer fleet, funneled to one triaged verdict. Targets the current working diff, a path, or an inbound GitHub PR.
/spike
Spike
Exploratory spike on a throwaway branch — answer a named question with disposable code. Never merges; exits to a findings note or {{CMD:feature}}.
/sprint
Sprint
Autonomous sprint — one interactive spec gate, then plan-to-PR execution with every auto-decision SMARTS-scored and logged. Hard gates remain true stops.
/standup
Standup
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.
/status
Status
Show the project's current state at a glance — stage, open tasks, open questions, overrides since the last checkpoint, current branch. Read-only.
/statusline
Statusline
Wire codeArbiter's statusline into ~/.claude/settings.json, or remove it.
/task
Task
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.
/threat-model
Threat model
{{SKILL_ENTRY:security-architecture}}
/tribunal
Tribunal
{{SKILL_ENTRY:tribunal}}
/watch
Watch
Watch a PR's CI to completion — diagnose on red, notify and offer the merge on green. Never auto-merges.
/sandbox-cp
Sandbox cp
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.
/sandbox-destroy
Sandbox destroy
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.
/sandbox-exec
Sandbox exec
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.
/sandbox-shell
Sandbox shell
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.
/sandbox
Sandbox
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.
/add-dep
Add dep
Vet a new or changed third-party dependency for license, provenance, and supply-chain risk before any install runs.
/adr-status
Adr status
Inspect ADR health read-only; optionally select one ADR with --adr N.
/adr
Adr
Record user-decided ADRs or inspect their health read-only. Preserve attribution and acceptance evidence.
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…
0 views 0 likesAn AI Agent that lives in your pocket. Local-first and privacy focused.
0 views 0 likesUnofficial skill that teaches coding agents to build with TypeSafe AI's Jev: typed decisions, calibrated confidence, and prior art from 150+ community projects.
0 views 0 likesAdaptive Test-time Learning and Autonomous Specialization
0 views 0 likesPrediction-market trading engine — Wang Transform pricing on 291K+ contracts; paper-traded across Kalshi · Polymarket · Solana DFlow (Jito bundles) · 633 tests
0 views 0 likesKnowledge Management for Humans and Agents
0 views 0 likesOpen-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…
0 views 0 likesDeepAgent Code: AI coding agent with persistent memory and control plane
0 views 0 likes