LLM Mart Basic

Calibration and validation scaffold for EPA SWMM. Use when an agent needs to (1) compare simulated vs observed flow, (2) evaluate candidate parameter sets, (3) rank explicit candidates by an objective, (4) run a bounded random / LHS / adaptive search for the best-fitting paramete

Fetch a ready-to-run SWMM model for any Canadian area from the SWMMCanada upstream service — real published municipal storm pipes where a supported city covers the AOI, synthesized elsewhere in Canada. Input is a bbox or GeoJSON polygon plus a rainfall date window. Use for Canadi

Deterministic rainfall/climate formatting for SWMM. Use when converting timestamped rainfall CSV files into SWMM-ready [TIMESERIES] lines and [RAINGAGES] helper snippets for swmm-builder.

Top-level orchestration skill for agentic SWMM modelling. Use when an agent needs one entrypoint that decides which module tools to run, in what order, and when to stop, for example to build, run, QA, and optionally calibrate a SWMM case from prepared or partially prepared inputs

Consolidate Agentic SWMM run artifacts into auditable provenance, comparison records, and local Obsidian audit notes. Use after any SWMM build/run/QA attempt, successful or failed, when an agent or CLI workflow needs a traceable record of inputs, commands, artifacts, metrics, QA

GIS/DEM preprocessing for SWMM experiments using the user's own QGIS/GRASS layers. Use when the user asks to (1) delineate subcatchments through QGIS/GRASS (standard or entropy-guided), (2) preprocess QGIS-derived subcatchment polygons into builder-ready CSV, (3) identify high-en

Network QA of an existing INP (disconnected nodes, missing outfalls, adverse or zero slopes) is one call, network_qa, so call it first. Also builds, validates and routes SWMM pipe-network models from raw municipal shapefiles or structured GIS/CAD exports. Use when handling juncti

Deterministic mapping from land use and soil texture to SWMM runoff/subarea and Green-Ampt infiltration parameters. Use when generating first-pass subcatchment parameter tables for swmm-builder.

Nature-spec figures from a SWMM run: paired rainfall (inverted) + node/link flow hydrograph (plot_run), network layout map (map_run), study-area map. 89/183 mm columns, 5-7 pt sans-serif, ticks out, no gridlines, Wong colour-blind-safe palette, vector PDF + 450 dpi PNG twin, SI u

Generate a client-deliverable Word (.docx) report from an audited SWMM run directory. Reads manifest.json, experiment_provenance.json, model_diagnostics.json, comparison.json, and any PNG figures — SWMM is never re-run. Supports custom YAML/JSON section templates.

Run EPA SWMM (swmm5) simulations reproducibly and extract key metrics from the report file. Use when an agent needs to (1) run a .inp via swmm5 CLI, (2) generate a run directory with rpt/out + manifest, (3) extract peak flow/time for a node/outfall, (4) parse SWMM continuity (Run

Parameter and forcing uncertainty for EPA SWMM. Without observed flow, call propagate_parameter_ranges (global ranges, one SWMM run per sample, peak spread); the Morris/OAT/Sobol tools need an observed series. Use when an agent needs to (1) propagate parameter uncertainty through

Complete SWMM engine coverage: pollutant buildup/washoff simulation support and load reporting. Validate water-quality config JSON, build INPs with WQ sections, and extract pollutant load summaries from completed runs.

Recall ChatCrystal memories for debugging tasks involving failing tests, compiler errors, runtime exceptions, dependency issues, environment breakage, or performance regressions. Use when historical root causes, fixes, or pitfalls may accelerate diagnosis before proposing a fix.

Recall project-first and global-supplement ChatCrystal memories before substantive implementation, refactoring, migration, configuration, investigation, or optimization work. Use when the task is non-trivial, has repository or project context, and prior fixes, decisions, pitfalls

Write reusable ChatCrystal task memories after substantive work completes. Use when implementation or debugging produced a durable fix, pitfall, pattern, or decision worth preserving, and when the environment can either persist it through `write_task_memory` or emit a structured

Use when the user asks to "set up conversion values so tROAS optimizes profit not orders", "map margin onto my purchase value", "build value rules for lead / phone / signup conversions", or "stop bidding to revenue when I care about profit"; defines and QAs the conversion VALUE m

Use when the user asks to "remember project context", review saved findings, initialize runtime memory, archive stale work, reconcile notes, or erase a subject; manages authorized HOT/WARM/COLD working memory across all disciplines while preserving registry event ownership and pr

Prepare current-session guidance for an independent AI Badger review of recent repository work. Use only when the user wants a Badger review, not for generic review requests or session continuation.

Transfer the current coding, debugging, planning, or architecture session to AI Badger. Use for broad session continuation; use badger-review for an independent review.

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.

Implement issues (GitHub/GitLab/Bitbucket) using progressive analyze-specify-plan-implement workflow

Address PR/MR review feedback by reading comments, implementing fixes, and resolving threads. GitHub and GitLab support.

Retrospective analysis and improvement of workflow components with self-evolving patterns

Fix broken functionality from pasted error output, stack traces, or

Summarize recent git history since a baseline with structured analysis of what changed, why, and what to watch for.

Consolidate ephemeral LLM-generated markdown into permanent documentation.

Review pull requests with scope validation, code analysis, and line comments. Supports GitHub PRs and GitLab MRs.

Prepare a PR end-to-end by updating documentation, running tests, dogfooding checks, and validating with code review.

Batch-resolve unresolved PR/MR review threads via GraphQL API (GitHub/GitLab)

Detect and fix drift between plugin.json registrations and capabilities reference documentation

Update pre-commit hooks and CI/CD workflows based on recent project changes

Scan and update dependencies across all ecosystems with conflict detection

Update project documentation with consolidation, debloating, AI slop detection, capabilities sync, and accuracy verification.

Audit and sync plugin.json registrations with actual disk contents. Detects missing or stale skills, commands, agents, hooks.

Review and update test coverage using TDD/BDD methodology with quality validation. Generates tests for changed code.

Generate or update tutorials with VHS and Playwright recordings

Bump project versions using git-workspace-review and version-updates skills.

Generate and self-execute a diff-derived test plan for a PR. Reads

Generate new documentation with human-quality writing.

Clean up AI-generated content and improve documentation quality.

Atom Agent, Open-Source Governed AI Agent Platform for Self-Hosted Automation

The agent engineering intelligence harness, optimized tools, memory system, subagents and mixture of models packages ⚚

Sesori iOS/Android app and the Sesori Bridge CLI — drive Claude, Codex, OpenCode, Cursor, Pi, OMP, Hermes coding sessions from your phone

🧠 RepoBrain (formerly Antigravity) — Give your repo a brain. ChatGPT for your codebase: works in Claude Code, Cursor, Codex, Windsurf & more.

Use ChatGPT (Codex), Claude, and Grok (X Premium) subscriptions as DeepSeek Harness LLM providers — OAuth login in the web UI, no API keys

Latitude is the open-source AI monitoring platform.

Open-source AI browser agent for Chrome and Firefox (monorepo) 🧠

Official Model Studio CLI（阿里云百炼 CLI）built for AI Agent frameworks, exposing models, search, multimodal, and workflow capabilities as structured tool calls.

Curated DeepSeek Harness (DSH) plugins, extensions, tools, skills, clients, runtimes, integrations, and verified references — English and Chinese.

Turn papers, code, and docs into presentation-ready, natively editable PPTX in Codex / Claude Code. Native charts and equations, speaker notes, click-build anim…

Grix : Work with agents like talking to people.

Local First Ai Agent. Optimized for Local Ai models. Long context window. Proper tools callings. Runs privately on your device.

Model Context Protocol server that integrates AgentQL's data extraction capabilities.

AI that ships your tickets.

Metadata-driven CLI for AI Agent Bots — 48 operations across 7 domains, structured JSON envelope I/O, zero interactive prompts.

An open-source, extensible, self-hosted agent workspace with multi-runtime support for Codex, Claude Code, and more, plus reusable local apps for custom interfa…

Open-source Windows desktop client and GUI for DeepSeek Harness — zero-setup installer with Codex, plugins, skills, SSH, mobile remote access, and 11 skins.

The open-source AI workbench for scientific research

DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.

A Fully free agentic browser driver for AI , few tools, full control, real stealth, top-tier token efficiency.