Scaffold and audit documentation for open source projects.

> **Quick Ref:** Decompose goal into trackable issues with waves. Output: `.agents/plans/*.md` + bd issues.

> **Purpose:** Wrap up completed work — validate it shipped correctly, extract learnings, process the knowledge backlog, activate high-value insights, and retire stale knowledge.

Strategic planning for open source contributions.

Systematic PR preparation that validates tests and generates high-quality PR bodies.

Systematic exploration of upstream repositories before contributing.

Learn from PR outcomes by analyzing accept/reject patterns.

PR-specific validation that ensures changes are clean, focused, and ready.

> **Purpose:** Is this plan/spec good enough to implement?

> **Purpose:** Guide the user through creating a `PRODUCT.md` that unlocks product-aware reviews in `/pre-mortem` and `/vibe`, including the default quick-mode inline paths.

Trace knowledge artifact lineage to sources.

'Test, commit, and push in one atomic workflow. Runs Go and Python tests, commits with conventional message, pushes to current branch.'

> **One job:** Tell a new user what AgentOps does and what to do first. Fast.

Track progress through the RPI workflow with permanent gates.

> **Purpose:** Generate a README that converts skimmers into users and satisfies deep readers — then validate it with a council.

>-

> **Quick Ref:** Safe, incremental refactoring with test verification at every step. One transformation, one test run, one commit. Never batch.

> **Purpose:** Take a project from "code is ready" to "tagged and ready to push."

'Deep codebase exploration. Triggers: research, explore, investigate, understand, deep dive, current state.'

'Reverse-engineer a product into a feature catalog, code map, and specs. Uses RPI-style loop with verification gates. Triggers: “reverse engineer”, “catalog features”, “feature inventory”, “code map”, “docs to code mapping”, “binary analysis”.'

> **Quick Ref:** `/review <PR>` reviews a PR, `/review --diff` reviews local changes, `/review --agent <path>` reviews agent output with extra scrutiny.

Author and manage holdout scenarios for behavioral validation. Scenarios are stored outside the codebase in .agents/holdout/ where implementing agents cannot see them. Triggers: scenario, holdout, behavioral scenario, create scenario, list scenarios.

> **Purpose:** Provide composable, repeatable security/internal-testing primitives for authorized binaries and repo-managed prompt surfaces.

> **Purpose:** Run repeatable security checks across code, scripts, hooks, and release gates.

Shared reference documents for multi-agent skills (not directly invocable)

'Language-specific coding standards and validation rules. Provides Python, Go, Rust, TypeScript, Shell, YAML, JSON, and Markdown standards. Auto-loaded by /vibe, /implement, /doc, /bug-hunt, /complexity based on file types.'

Spawn isolated agents to execute tasks in parallel. Fresh context per agent (Ralph Wiggum pattern).

> **Quick Ref:** Trace design decisions through CASS sessions, handoffs, git, and artifacts. Output: `.agents/research/YYYY-MM-DD-trace-*.md`

**YOU MUST EXECUTE THIS WORKFLOW. Do not just describe it.**

> **Purpose:** Is this code ready to ship?

Transform lengthy academic papers into concise, structured 250-word abstracts.

Generate interactive anatomy quizzes for medical education with multiple.

Adapt abstracts to meet specific conference word limits and formats.

Generates professional cover letters for journal submissions and job.

Draft Diversity, Equity, and Inclusion statements for academic applications.

Generate hospital discharge summaries from admission data, hospital course.

Simulates NIH study section peer review for grant proposals. Triggers.

Draft IACUC protocol applications with focus on the 3Rs principles justification.

Analyzes forest plots for meta-analysis, generating detailed descriptions and formatting figure legends in Chinese or English. Use when the user wants to interpret a forest plot image, describe its statistical significance (heterogeneity, p-value), and format the output with specific figure legends.

> **Source**: [https://github.com/aipoch/medical-research-skills](https://github.com/aipoch/medical-research-skills)

Generates academic reviews for molecules in diseases using PubMed research. Invoke when user needs biomedical literature review with Vancouver citation format.

Assist in drafting professional peer review response letters. Trigger.

Generate graphical abstract layout recommendations based on paper abstracts.

Generates scientifically sound inclusion and exclusion criteria for Meta-Analysis based on a given title or keywords. Use when user wants to design eligibility criteria for a systematic review or meta-analysis.

Generate meta-analysis forest plots for binary classification data. Input is a CSV file containing study names, event counts and sample sizes for experimental and control groups. Output includes forest plot PNG and data table CSV.

Generate forest plots for meta-analysis of survival data. Input is a CSV file containing study names, HR and 95% confidence intervals, output forest plot PNG and data table CSV. Supports both R and Python scripts.

Generates PI(E)COS structure (Population, Intervention, Comparator, Outcomes, Study Design) from Meta-analysis or study titles. Use when the user wants to extract these elements from a title.

Draw ROB2 risk-of-bias plots, including a Traffic Light Plot and a Summary Bar Plot. Input is a CSV file with ROB2 assessments for each study; output are two PNG plot files.

A full-featured computational pathology toolkit for advanced WSI analysis, including multiplexed immunofluorescence (CODEX, Vectra), nuclei segmentation, tissue graph construction, and machine learning model training on pathology data. Supports over 160 slide formats. For simple tile extraction from H&E slides, histolab may be simpler.

Cloud-based quantum chemistry platform providing a Python API. Preferred for computational chemistry workflows including pKa prediction, geometry optimization, conformational search, molecular property calculations, protein-ligand docking (AutoDock Vina), and AI protein cofolding (Chai-1, Boltz-1/2). Suitable for tasks involving quantum chemistry calculations, molecular property prediction, DFT or semi-empirical methods, neural network potentials (AIMNet2), protein-ligand binding prediction, or automated computational chemistry pipelines. Provides cloud computing resources without local installation.