Medical-education exam-prep toolkit. Bundles medical-acquisition (21 backends, USyd OpenAthens), examiner-feedback-mining (RACGP / ACRRM / AMC patterns), distractor-design (72-entry taxonomy plus 5 KFP buckets), kfp-failure-bucket (8-bucket failure router). Slash commands: /smp-kat-tools:acquire, /smp-kat-tools:kfp-stem, /smp-kat-tools:refresh-capabilities. Subagents: acquisition-fetcher, exam-stem-author.
Fetch a medical reference via the unified acquisition framework. Argument is a DOI, PMID, PMC ID, URL, or JSON spec. Routes through ~/tools/bin/acquisition.
Author a KFP-style practice stem on a named topic, with marking key at the AU specificity bar. Pre-loads distractor-design, examiner-feedback-mining, and kfp-failure-bucket. Routes the work through the exam-stem-author subagent.
Run the fleet capability-check script and report what is current, missing, or out of date. Drives ~/claude-library/scripts/capability-check.py with --fix.
Specialised subagent for medical-reference fetching. Pre-loads the medical-acquisition skill so it does not fall back to MCP scrape habits. Invoke when a parent agent needs a DOI, PMID, PMC ID, RACGP exam report, AJGP article, AIHW report, or any USyd-OpenAthens-brokered publisher pull, and wants the standardised AcquisitionResult contract back.
Specialised subagent for authoring KFP and MCQ practice stems in RACGP / ACRRM / AMC style. Pre-loads distractor-design, examiner-feedback-mining, and kfp-failure-bucket so it produces stems that match the AU specificity bar without being told. Invoke when the caller wants a new stem, a stem rewrite, or a stem-plus-marking-key for a named topic.
Author or evaluate MCQ and KFP distractors against a 72-entry taxonomy plus the 5 KFP failure buckets. Use when the user asks to write a stem with distractors, evaluate whether existing distractors discriminate, classify a wrong-answer pattern, or stress-test an option set for tautology, give-aways, or examiner-flagged sloppiness. Returns taxonomy class, discrimination notes, and a rewrite suggestion when the option fails.
Surface examiner-flagged failure patterns from RACGP, ACRRM, AMC, and PESCI exam reports. Use when the user asks "what do RACGP examiners flag", "common KFP errors", "AMC clinical exam pitfalls", or wants to map a candidate's wrong answer onto a recognised examiner-criticism class. Returns the wave-1 findings catalogue (16-class AU misconception taxonomy) plus per-college style notes.
Route a candidate's wrong KFP answer into one of 8 named failure buckets and map it onto the distractor-design 12-category taxonomy. Use when the user asks "why is this answer wrong", "which examiner class does this fall into", or wants a structured failure-mode label for a model-vs-candidate diff. Returns bucket label, candidate-perspective explanation, and the corrective specificity bar examiners want.
Fetch medical references (PubMed, PMC, EuropePMC, RACGP/ACRRM/AMC exam reports, AJGP, AIHW, ClinicalKey, UpToDate, AMH, eTG, Murtagh, plus 8 generic publishers via USyd OpenAthens) using a unified Python framework. Use when the user provides a DOI, PMID, PMC ID, RACGP exam cycle, AU clinical reference, or asks to fetch any academic / examiner-feedback / clinical-guideline content. Returns standardised AcquisitionResult with tier-tagged content. Single auth gateway (USyd OpenAthens) prompts fresh per run; graceful OA fallback on no-subscription.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Personal Claude Code plugin marketplace for the fw16 plus gx10 fleet. Hosts plugins shared across 35-plus projects under ~/projects/personal/.
claude-fleet-marketplace/
.claude-plugin/
marketplace.json # marketplace manifest (Anthropic spec)
plugins/
smp-kat-tools/ # the first published plugin
.claude-plugin/
plugin.json
skills/ # 4 skills
agents/ # 2 specialised subagents
commands/ # 3 slash commands
docs/
installation.md
skills-reference.md
changelog.md
Version 0.1.0. Bundles:
medical-acquisition, examiner-feedback-mining, distractor-design, kfp-failure-bucketacquisition-fetcher, exam-stem-author/smp-kat-tools:acquire, /smp-kat-tools:kfp-stem, /smp-kat-tools:refresh-capabilities~/claude-library/hooks/ and stay at user level so they apply to every project, not just plugin installs.See plugins/smp-kat-tools/README.md for the per-plugin docs.
In any Claude Code session:
/plugin marketplace add anon2023-Halmoni/claude-fleet-marketplace
/plugin install smp-kat-tools@fleet
Or declare it in ~/.claude/settings.json (user scope) so every session loads it:
{
"extraKnownMarketplaces": {
"fleet": {
"source": {
"source": "github",
"repo": "anon2023-Halmoni/claude-fleet-marketplace"
}
}
}
}
For project-scope distribution (auto-prompts teammates to install when they trust the project folder), use .claude/settings.json at the project root with the same shape.
version in plugin.json bumps on any change to public API: skill description, command surface, agent contract.The git commit SHA is the fallback identifier when version is absent. With version set, users only get an update when the field bumps.
claude --plugin-dir ./plugins/smp-kat-tools
Inside the session: /smp-kat-tools:acquire 10.31128/AJGP-04-23-6803 to smoke-test.
Validate before pushing:
claude plugin validate plugins/smp-kat-tools
claude plugin validate .
GitHub issue #15897 documents that PreToolUse updatedInput is broken when multiple hooks match the same tool. This marketplace deliberately does not bundle plugin-level hooks. Fleet hooks live at the user level and are scoped per-project as needed. If a future plugin needs a hook, it will be a single matcher per tool, no stacking.
| In this marketplace | Mirrors in claude-library |
|---|---|
plugins/smp-kat-tools/skills/medical-acquisition/ | ~/.claude/skills/medical-acquisition/ (standalone copy) |
plugins/smp-kat-tools/skills/examiner-feedback-mining/ | new, plugin-only |
plugins/smp-kat-tools/skills/distractor-design/ | new, plugin-only |
plugins/smp-kat-tools/skills/kfp-failure-bucket/ | new, plugin-only |
plugins/smp-kat-tools/agents/ | new, plugin-only |
plugins/smp-kat-tools/commands/ | new, plugin-only |
The standalone ~/.claude/skills/medical-acquisition/ copy is kept so projects without the plugin still get the skill from user scope.
Personal fleet under anon2023-Halmoni. HTTPS only. No external contributors expected.
npx claudepluginhub anon2023-halmoni/claude-fleet-marketplace --plugin smp-kat-toolsHarness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows