By cbenjamin23
MOOS-IvP skills for apps, IvP behaviors, missions, test harnesses, documentation, and alog analysis.
Build or modify user-owned IvP helm behaviors outside the core MOOS-IvP source tree. Use when an AI coding agent needs to create a C++ BHV_* behavior, implement IvPBehavior lifecycle methods, build a behavior shared library, make pHelmIvP find behavior libraries through IVP_BEHAVIOR_DIRS, or add .bhv mission configuration for a custom helm behavior.
Analyze existing MOOS .alog files to reconstruct a mission or debug a specific incident. Run `alog*` commands directly in the current shell. If you already know the variable names or a specific variable set, go straight to targeted `aloggrep` queries; use `aloghelm` for helm context; use the compact `alogvars.sh` wrapper for discovery only when names are still unknown; read raw log lines only when exact payload format or source ambiguity matters.
Build or modify user-owned MOOS applications outside the core MOOS-IvP source tree. Use when an AI coding agent needs to create a new C++ MOOS app, wire it into an extension/project build, implement MOOS mail/config/iterate logic, update app help/interface text, or add mission config for a custom MOOS process.
Consult the live MIT MOOS-IvP PDF index and cite the most relevant upstream documentation for MOOS-IvP apps, behaviors, parameters, and concepts. Use when the user explicitly asks for documentation-backed answers, when upstream MOOS-IvP semantics are uncertain, or when an AI coding agent needs to compare MIT docs against a local moos-ivp checkout under ivp/src.
Build or repair one self-evaluating MOOS-IvP mission. Use when creating headless-capable mission folders with explicit startup initialization, pMissionEval pass/fail checks, results.txt output, uMayFinish completion through xlaunch.sh, zlaunch.sh automation, scoped teardown, and validation for a single test scenario. Do not use for ordinary operator missions or multi-case harness orchestration.
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.
Portable SKILL.md workflows for MOOS-IvP development, mission work, CI harnesses,
documentation lookup, and post-mission analysis.
The canonical skill source lives under skills/. Codex and Claude Code adapters
carry self-contained copies generated from that source for distribution.
moos-app-builder - build or modify user-owned MOOS apps.ivp-behavior-builder - build or modify user-owned IvP helm behaviors.moos-ivp-docs - consult upstream MOOS-IvP docs and local source.moos-alog-analysis - analyze existing .alog files with MOOS log tools.moos-ivp-mission-builder - build ordinary MOOS-IvP mission folders from canonical examples.moos-ivp-eval-mission-builder - build self-evaluating test missions.moos-ivp-harness-builder - build multi-case harnesses and regression suites, including nspatch variants.This repo is both the maintainer workspace and the marketplace source. Only the adapter directories below are installed as plugins; root-level docs and scripts are for maintaining and validating the release.
Codex:
.agents/plugins/marketplace.json
plugins/codex/moos-ivp-skills/
Claude Code:
.claude-plugin/marketplace.json
plugins/claude/moos-ivp-skills/
For install commands, see INSTALL.md.
skills/ Canonical, agent-neutral skill folders.
plugins/<product>/... Product adapters around the skills.
.agents/plugins/ Codex marketplace metadata.
.claude-plugin/ Claude Code marketplace metadata.
scripts/ Setup, validation, and packaging helpers.
docs/ Distribution notes.
test-runs/ Ignored local validation output, not distribution source.
See docs/distribution-adapters.md for Codex and Claude Code distribution
notes.
After editing canonical skills, refresh both plugin copies:
./scripts/sync_codex_plugin.sh
./scripts/sync_claude_plugin.sh
./scripts/check_plugin_integrity.sh
Direct validators:
python3 ~/.codex/skills/.system/plugin-creator/scripts/validate_plugin.py \
plugins/codex/moos-ivp-skills
claude plugin validate . --strict
claude plugin validate plugins/claude/moos-ivp-skills --strict
This public GitHub repository is distributable as both a Codex marketplace and a Claude Code marketplace. Marketplace manifests and plugin adapter payloads are validated locally with the commands above before release.
npx claudepluginhub cbenjamin23/moos-ivp-skills --plugin moos-ivp-skillsComprehensive 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.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Create new skills, improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, or benchmark skill performance with variance analysis.