Unified PR feedback workflow - collect, triage, and fix review comments in a single command.
EnglishPerforms tracked, evidence-bounded security posture assessment for a project, sub-directory, module, concept, or feature topic with standards mapping and registered report output.
EnglishStructured guidance for agents to read, classify, and act on user feedback (annotations and direct file edits) from the Arcade.
EnglishAgent-only reference providing canonical output templates for all rp1 artifacts (requirements, design, tasks, reports, KB docs). Load when producing any structured markdown artifact to ensure format consistency and correct routing metadata. Not user-invocable -- agents read the index to find the right template, then read the template file via the Read tool.
EnglishArchives a completed PRD to the archives directory with associated features and closure summary.
EnglishQuick-iteration development for small/medium scope changes with persistent artifacts and optional review.
EnglishBuild a governed prompt or skill through the six-stage prompt-writer pipeline with budgeted governance.
EnglishFast code hygiene validation (lints, formatters, tests, coverage) for quick development loop feedback.
EnglishSystematically removes unnecessary comments from a user scope by first resolving it into a durable change manifest.
EnglishExtract comment locations from code files for analysis. Use when cleaning comments, auditing code documentation, or analyzing comment patterns. Supports Python, JavaScript, TypeScript, Go, Rust, Java, C/C++, Ruby, PHP, Shell scripts. Trigger terms - comments, extract comments, code comments, comment analysis, documentation audit, comment cleanup.
EnglishDual-perspective code investigation. Claude explores independently, then Codex explores independently (no feeding), finally integrate both conclusions.
EnglishArchives a completed feature to the archives directory with optional documentation validation.
EnglishRestores an archived feature from the archives directory back to the active features directory.
EnglishValidates and repairs mermaid diagrams in markdown files. Scans for mermaid blocks, validates syntax, and auto-repairs common errors.
EnglishSynchronizes user-facing documentation with the current knowledge base through validate -> stale gate -> scan -> approval -> process orchestration.
EnglishOrchestrates parallel KB generation using spatial analysis and a map-reduce architecture with incremental and feature-learning modes.
EnglishIngests and prepares codebase documentation, builds internal knowledge graphs, and creates optimized context representations for downstream analysis tasks.
EnglishGenerate browser-viewable HTML previews from markdown, plain text, and Mermaid diagrams. Auto-validates diagrams, applies professional styling, and opens in default browser. Use when agents need to preview documentation, visualizations, or formatted content.
EnglishPlan and execute splitting a large PR or branch into a reviewable stacked PR sequence.
EnglishTransform pull request diffs into Mermaid diagrams for visual code review and change understanding.
English
AGENT SKILLS ATLASIncludes Address PR Feedback, Analyse Security, Arcade Collab, and other workflows.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLISupported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Address PR Feedback
Unified PR feedback workflow - collect, triage, and fix review comments in a single command.
Analyse Security
Performs tracked, evidence-bounded security posture assessment for a project, sub-directory, module, concept, or feature topic with standards mapping and registered report output.
Arcade Collab
Structured guidance for agents to read, classify, and act on user feedback (annotations and direct file edits) from the Arcade.
Artifact Templates
Agent-only reference providing canonical output templates for all rp1 artifacts (requirements, design, tasks, reports, KB docs). Load when producing any structured markdown artifact to ensure format consistency and correct routing metadata. Not user-invocable -- agents read the index to find the right template, then read the template file via the Read tool.
Blueprint Archive
Archives a completed PRD to the archives directory with associated features and closure summary.
Blueprint Audit
Audits a PRD against implementation status and guides lifecycle decisions.
Build Fast
Quick-iteration development for small/medium scope changes with persistent artifacts and optional review.
Build Prompt
Build a governed prompt or skill through the six-stage prompt-writer pipeline with budgeted governance.
Code Check
Fast code hygiene validation (lints, formatters, tests, coverage) for quick development loop feedback.
Code Clean Comments
Systematically removes unnecessary comments from a user scope by first resolving it into a durable change manifest.
Code Comments
Extract comment locations from code files for analysis. Use when cleaning comments, auditing code documentation, or analyzing comment patterns. Supports Python, JavaScript, TypeScript, Go, Rust, Java, C/C++, Ruby, PHP, Shell scripts. Trigger terms - comments, extract comments, code comments, comment analysis, documentation audit, comment cleanup.
Code Investigate
Dual-perspective code investigation. Claude explores independently, then Codex explores independently (no feeding), finally integrate both conclusions.
Echo Test
Validates skill invocation, parameter passing, and shell execution on Copilot CLI
Feature Archive
Archives a completed feature to the archives directory with optional documentation validation.
Feature Unarchive
Restores an archived feature from the archives directory back to the active features directory.
Fix Mermaid
Validates and repairs mermaid diagrams in markdown files. Scans for mermaid blocks, validates syntax, and auto-repairs common errors.
Generate User Docs
Synchronizes user-facing documentation with the current knowledge base through validate -> stale gate -> scan -> approval -> process orchestration.
Knowledge Build
Orchestrates parallel KB generation using spatial analysis and a map-reduce architecture with incremental and feature-learning modes.
Knowledge Load
Ingests and prepares codebase documentation, builds internal knowledge graphs, and creates optimized context representations for downstream analysis tasks.
Markdown Preview
Generate browser-viewable HTML previews from markdown, plain text, and Mermaid diagrams. Auto-validates diagrams, applies professional styling, and opens in default browser. Use when agents need to preview documentation, visualizations, or formatted content.
Multi Agent Workflow
Validates parallel sub-agent execution with file-backed JSON artifact handoff
PR Stack
Plan and execute splitting a large PR or branch into a reviewable stacked PR sequence.
PR Visual
Transform pull request diffs into Mermaid diagrams for visual code review and change understanding.
PR Walkthrough
Generate an evidence-grounded markdown walkthrough for a pull request.
Showing 24 of 34 skills. Use the list’s page controls above to explore the rest.
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Address PR Feedback skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- Reported license for the skills shown: Apache-2.0. The author’s terms apply.