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

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.

Analyze git diffs or staged changes and generate conventional commit messages that explain WHY a change was made. Supports auto-detecting type and scope, intelligent file staging, and interactive overrides. Use when asked to "write a commit message", "generate a commit", "describe my changes", "commit this", "summarize my diff", or "/commit".

SOC 2 compliance for Terraform — gap analysis, control implementation, evidence collection, and remediation guidance mapped to SOC 2 Trust Services Criteria.

Generate, review, secure, and test composite GitHub Actions following best practices — full repo scaffold, interview-driven generation, PR creation on existing repos, SHA pinning, secrets-as-inputs, job summaries, and actionlint validation.

Set up and troubleshoot Datadog — Agent deployment on Kubernetes, APM instrumentation, Log Management, Monitors, Dashboards, SLOs, Synthetic tests, and live incident investigation using the Datadog MCP server. Covers Terraform-managed Datadog resources.

Structured platform troubleshooting — classifies the problem layer, collects evidence, forms a root-cause hypothesis, and proposes a fix with validation and rollback steps.

Generate, format, and validate code documentation — docstrings, JSDoc, OpenAPI/Swagger specs, documentation sites, and developer guides.

Measure, benchmark, instrument, and debug DORA metrics (Deployment Frequency, Lead Time for Changes, Change Failure Rate, MTTR) for production engineering teams. Covers GitHub Actions instrumentation, Prometheus recording rules, Grafana dashboards, incident source integration, SaaS tool selection, and anti-pattern detection. Use when asked to "instrument DORA metrics", "benchmark our deployment frequency", "why is my MTTR data missing", or "generate a DORA dashboard".

Deploy and configure Dynatrace — OneAgent Kubernetes Operator, code-level instrumentation, Log Monitoring, custom metrics, SLOs, Dashboards, anomaly detection, Davis AI, and live incident investigation using the Dynatrace MCP server. Covers Terraform-managed Dynatrace resources.

FluxCD entry point — routes to the right workflow based on what you need. Live cluster issue → structured 5-workflow debug trace. Repo health check → 6-phase audit (discovery, validation, API compliance, best practices, security). Helm chart review → helmchart. Starts by asking one question to confirm the right mode.

Design, review, secure, and debug GitHub Actions workflows — reusable workflows, OIDC federation, SHA pinning, token scoping, promotion orchestration, and CI failure diagnosis.

Flux CD and Argo CD — two modes. debug: five structured debug workflows for live clusters (installation, source, HelmRelease, Kustomization, ResourceSet) producing a five-section report. audit: six-phase read-only repo analysis (discovery, validation, API compliance, best practices, security) producing a prioritised Critical/Warning/Info report.

Scaffold, lint, review, security-audit, test, and upgrade-verify Helm charts. Runs an interactive interview to build production-ready charts from scratch. Covers chart structure, values design, schema validation, kubeconform, helm diff, and multi-environment scaffolding. Use when asked to "create a helm chart", "lint my chart", "review my helm chart", "check helm security", "generate values schema", "run helm diff", or "add helm tests".

Design, install, debug, review, plan capacity, audit scaling history, migrate from Cluster Autoscaler, and upgrade Karpenter v1.x on EKS. Covers NodePool, EC2NodeClass, NodeClaim, Spot diversity, disruption strategy, Pod Identity/IRSA, interruption queue, private clusters, AMI rotation, and GitOps integration. Use when asked to "set up Karpenter", "debug why nodes aren't provisioning", "review my NodePool", "what would Karpenter provision for this workload", "why did this node terminate", "migrate from CA", or "upgrade Karpenter".

Design, debug, and review KEDA ScaledObject/ScaledJob autoscaling. Covers all major scalers (Prometheus, SQS, Kafka, Redis, Cron, HTTP Add-on, Azure Service Bus), TriggerAuthentication, scaling lifecycle tuning, GitOps integration, and troubleshooting. Use when asked to "add KEDA autoscaling", "debug why my ScaledObject isn't scaling", "review my KEDA config", or "generate a ScaledObject for <trigger>".

Find, live-validate, map the blast radius of, and revoke leaked secrets with Kingfisher (MongoDB) — across a local repo, Git history, a GitHub/GitLab/Bitbucket org, S3/GCS, Docker images, Slack, Jira, Confluence, Teams, or Postman. Covers local CLI scanning, direct validate/revoke without a scan, baseline management (track only new secrets), kingfisher.yaml policy, CI diff-scan gates, and pre-commit/Husky hooks. Use when asked to "scan for secrets", "is this key still live", "what can this credential reach", "revoke this token", "did we leak a secret", or "block new secrets in CI". Pattern-only secret scan bundled with a CVE pass → /platform-skills:trivy. Secrets-context safety in workflow YAML → /platform-skills:zizmor. Storing/rotating secrets inside the cluster → /platform-skills:secrets.

Cluster baseline scaffolding, RBAC diagnosis and generation, workload hardening, and structured pod/scheduling debug for plain Kubernetes across all distributions.

Generate, test, audit, debug, and migrate Kyverno policies using the new CEL-based policy types (ValidatingPolicy, MutatingPolicy, GeneratingPolicy, ImageValidatingPolicy — all apiVersion policies.kyverno.io/v1). Covers matchConstraints, matchConditions, CEL validations/mutations, generator.Apply(), Audit→Deny promotion, PolicyException, kyverno-cli testing, and migration from legacy ClusterPolicy or PodSecurityPolicy. Use when asked to "write a Kyverno policy", "test a ValidatingPolicy", "audit my cluster for violations", "why is my policy not firing", or "migrate from ClusterPolicy".

Linkerd-specific diagnostics — mTLS verification, proxy injection issues, authorization policy debugging, traffic management, and multi-cluster connectivity problems.

Linux administration and networking diagnostics — DNS, load balancing, VPCs, kernel tuning, and connectivity troubleshooting.

MCP server and client development — scaffold, implement tools/resources/prompts, validate schemas, debug protocol compliance, and deploy with auth and rate limiting.

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