LLM Mart Basic

Use when checking whether an IronLint adapter still matches its coding harness's current contract — auditing adapter/harness drift, verifying hook payload shapes, plugin manifest schemas, lifecycle events, or tool names are up to date, or doing periodic adapter maintenance. Takes

Authors, modifies, or removes checks in an ironlint .ironlint.yml. Use when the user says "add an ironlint check for X", "ban Y", "tighten <check-id>", "stop checking <check-id>", "remove <check-id>", "change the scope of a check", or asks how to write an ironlint config.

Batch download open-access PDFs by DOI using legitimate OA APIs (Unpaywall, PMC, OpenAlex, Crossref). Optional PDF→Markdown conversion for token-efficient LLM analysis.

Sync research references from .bib files to Zotero library + Obsidian literature notes. Extract cross-cutting concept notes when enough literature accumulates. Works after /search-lit or standalone.

Cross-cutting reference manager for medical manuscripts. Single entry point for citation-key validation, journal-CSL pandoc rendering, manuscript ↔ DOCX cross-reference QC, marker conversion (``[N]`` ↔ ``[@key]``), and native Zotero CWYW field-code injection. Replaces the inline

Turn a folder of research PDFs into an Obsidian knowledge vault — consistently formatted literature notes with frontmatter, PDF embed links, and cross-referenced atomic concept notes. Use whenever the user wants PDFs converted to Obsidian notes, a batch of papers summarized into

Audit-only verification of manuscript references against PubMed and CrossRef. Detects fabricated or mismatched citations and writes qc/reference_audit.json. Does not modify references/ or refs.bib.

Interactive sample size calculator for medical research. Decision-tree guided test selection, reproducible R/Python code, effect size interpretation, and IRB-ready justification text. Supports diagnostic accuracy, agreement, proportions, continuous outcomes, survival, ANOVA, logi

Interactive data profiling and cleaning assistant for medical research. Three-stage workflow (profile, flag, code-generate) with user approval gates at each step. Handles missing values, outliers, duplicates, and type mismatches in CSV/Excel clinical data. Does NOT auto-clean — a

Literature-grounded variable operationalization for observational research. Turns a data dictionary + research question into a citation-backed table of exposure/outcome/covariate definitions, cutoffs, and DB variable mappings. Prevents ad-hoc phenotype definitions that invite rev

De-identify clinical research data before LLM-assisted analysis. Standalone Python CLI detects PHI via regex + heuristics with 10 country locale packs (kr, us, jp, cn, de, uk, fr, ca, au, in). Interactive terminal review. No LLM touches raw data — the script runs locally without

Design and validity review for studies that benchmark one or more AI systems against a human-expert panel as the reference. Covers the evaluation question and arm definition, decoupled multi-dimensional rubrics with anchors, planted calibration probes, reviewer-panel construction

Study design and validity review for radiology and medical AI research. Identifies analysis unit, cohort logic, leakage risks, comparator design, validation strategy, and reporting guideline fit before drafting or submission.

Generate a citable data dictionary / codebook from a tabular dataset (CSV/TSV/Excel/Parquet/Stata/SAS). Profiles every variable — role, type, units placeholder, level frequencies, range/quantiles, missingness — and emits codebook.md + codebook.json. Flags coded variables whose le

Dataset version control for research reproducibility. Builds a deterministic content-hash manifest of a dataset (file SHA-256 + tabular schema + per-column value hashes), verifies a later copy against it to detect drift (schema change, row-count change, value changes), and diffs

Choose a model architecture for a medical-imaging research question before scaffolding. Maps the task (classification, segmentation, detection, transfer), modality and dimensionality, labelled-data scale, and class imbalance to a shortlist of architectures, each grounded in its s

Produce or audit the interpretability/explainability analysis of a medical-imaging model — Grad-CAM / Grad-CAM++ / attention-rollout / saliency / integrated-gradients — so it clears the rigor bar a reviewer expects: mandatory Adebayo sanity checks (model- and data-randomisation),

Design or audit a model-agnostic evaluation harness for an LLM or multimodal LLM on a clinical task (radiology report generation, visual question answering, clinical text extraction/classification) — the adjudicated reference standard, clinical-efficacy metrics (RadGraph-F1 / Che

Generate the documentation an engineer-built medical-imaging model must carry — a Model Card (Mitchell et al. 2019), a Datasheet for its dataset (Gebru et al. 2021), and a METRIC-informed data-quality pass — filled from user-supplied facts, then verify every required section is p

Compute and report task-correct held-out metrics for a trained medical-imaging model — segmentation (Dice plus a boundary metric such as HD95 or NSD, per structure), classification (AUROC plus AUPRC and sensitivity/specificity with bootstrap CIs at the deployment prevalence), det

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.

Treat an AI agent skill as both an instruction package and a software dependency: inspect what it says, what it runs, what it can access, and how it updates.

Add remote HTTP or local stdio MCP servers to Claude Code, choose the right scope, protect credentials, verify the connection, and test with least privilege.

Skills teach Claude a repeatable method, connectors provide governed access to apps and live data, and plugins package related capabilities for installation and sharing.

Use an agent skill to package reusable know-how and workflow instructions. Use an MCP server when an agent needs live, governed access to external data or actions.

Custom commands and skills can both create a slash-invoked workflow in Claude Code. The important choice is how the workflow is discovered, shared, and permissioned.

A useful Claude skill solves one recurring engineering job, is easy to inspect, and saves more time than it creates in setup and review.

Claude skills can live in your Claude account, your local Claude Code setup, or a repository. Install them where the sessions that need them can load them.

Build a portable AI agent skill from one repeatable job: a precise description, concise instructions, focused resources, and tests that prove it works.

AI agent skills package instructions, scripts, references, and templates into portable folders an agent loads only when the task calls for them.

AI made publishing cheap, which is exactly the problem. What separates a page worth ranking from a competent summary of the first ten results.

A prompt that works once isn't a quality system. Five cases, an observable rubric, and a regression set will tell you whether a change helped.

One character of YAML, four pods that never started, and two safety nets I didn't know were holding. Every restart is an audit. Schedule them before they schedule you.

"Verify your work" isn't an instruction. It's a mood. Here's the version that's an instruction. Verify with a different mechanism than the one that made the claim.

A prompt that works once may still fail in production. A lightweight eval set gives you repeatable cases, a clear rubric, and a way to see whether a prompt change actually improved the workflow.

The best AI tool is not the one with the longest feature list. It is the one that solves a defined job reliably, fits the workflow, handles data appropriately, and remains useful after the novelty wears off.

Use AI to speed research without losing trust. Learn to find primary sources, verify claims, preserve uncertainty, and keep an auditable source trail.

Better prompts aren't magic wording. They're short briefs that hand the model a task, the context it can't infer, the limits, and a quality bar.

Discover testnet↔mainnet subnet lineage from repo configs and open a PR for review (pass --dry-run to report only)

Triage raw inbox notes into reviewed repository destinations without deleting their sources.

Audit and rewrite content to remove AI writing patterns

Log a completed piece of content to content/log.md after the user confirms it was published.

Validate a dream artifact, review each proposal, and apply only individually accepted changes.

Run a curator pass against the validated memory directory and produce a proposal artifact.

End a session — log what happened, update state and the decision log, propose memory updates, and check for uncommitted or unpushed work

Find relevant context files by topic. Use when you need to load files for a topic without a slash command, or when a task spans multiple domains.

Inventory and migrate selected Gemini CLI workflows with dry-run review and parity checks.

Find repeated workflows in selected Gemini CLI sessions and draft portable skills after review.

Scan multi-session drift and offer individually reviewed fixes only after explicit approval.

Scan orphaned worktrees and stale branches, then offer explicit approval-gated cleanup.

Guided onboarding or import for durable workspace context

Start a session — load state files, flag staleness, and give a briefing on current priorities, deadlines, and blockers

Create a morning heartbeat from repository state and update the local heartbeat log.

Mid-session checkpoint — append progress to today's session log and update state files if a priority shifted, without ending the session

Maintainer-only. Find every file that would newly ship to adopters, classify each one against the written distribution-boundary categories, default to withhold on no clean match, and ask the maintainer only where the taxonomy does not settle it. Drives the release CLI, which refuses to produce a manifest until every shipping file has an answer.

Audit memory, wiki, and auto-loaded files for duplication, conflicting instructions, and stale content. The default path researches, then asks you a single Apply / Discuss / Decline question; on Apply it applies the report, files any out-of-scope problem as a tech-debt issue, then commits, opens a PR, and merges it on a main-branch run like /update-deps. Pass --apply to re-run the apply-and-publish stage against the most recent report.

Fix the tech-debt backlog, a single issue or a recommended related batch, highest severity then oldest first, on a fresh isolated branch through the audit gate, closing the issue(s) on merge. Pass `list` to see the ordered backlog, `why <issue-number>` to explain the recommendation, or a bare `<issue-number>` to fix that issue directly.

Health-check and auto-heal this project's Claude integration, triage, heal, verify, and report an F-to-A+ grade.

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

Agent OS: the agent gets smarter on its own. We just hold the line: the grading command and expected result never make it into the success contract we hand it.…

Curated systems, benchmarks, and papers etc. on memory for LLMs/MLLMs --- long-term context, retrieval, and reasoning.

:memo: Vimlike Modal Text Editor in Rust

CI-native security testing for MCP servers. Attack simulation, schema drift detection, and health scoring before agents depend on them.

Hermes Agent memory plugin/provider for scope-aware recall, SQLite truth, LanceDB semantic search, and hybrid retrieval.

For You Agent——AI 时代的个人随身数字人格。把你的模型、AI 账号、技能、提示词和工作方式，带到每一个 AI 工具里。

A coding agent: give it a prompt and it reads, writes, runs commands, and searches code in a loop until the work is done, using native tool-calling across OpenA…

A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord, Teams, and…

Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

DeepSeek Harness Desktop (dsh-desktop). EAC: Embracing All Creation (揽尽万象). Bundled Node.js runtime with full dsh-CLI kernel, one-click startup, 10 built-in UI…

See your agent think. Zero-config observability & governance for 26 AI agent runtimes: Claude Code, Cursor, OpenAI Codex, GitHub Copilot, Gemini CLI, Cline, Ope…

Save 94% on AI coding tokens. Index your codebase, agents search instead of reading files. Works with Claude Code, Codex, Copilot, Cursor, Gemini CLI. Local MCP…

Yet another coding agent harness, lightweight and written in go.

a coding Agent from pi. ∞ providers, sub-agents, hashline edits, and a permission gate

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting…

🧠 Leon is your open-source personal assistant.

The Station, an open-world multi-agent environment that models a miniature scientific ecosystem.

The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol

VelaTerm = iTerm2 + Codex, The Best Terminal for AI Coding