Use before delivering work that incorporated content the agent did not author — fetched web pages, PDFs, retrieved or library documents, tool or subagent output — or that performs an outward-facing or irreversible action. Maps trust boundaries and runs an abuse-case and prompt-injection check, delegating to a fresh-context security reviewer.
EnglishRun bounded autonomous research iterations with evidence gates, recovery ledgers, and optional cross-agent handoffs; prefers host-owned multi-agent panel with single-path drive primary; scripted force-loop defaults (Goal Focus enforce, hard goalpriority, notify ON). Use when the user asks to continue research autonomously, run a research loop, integrate autonomous agent loops, or keep improving a research workflow without repeated prompts.
EnglishSearch and query Calibre library databases. Use when the user asks about books, TBR (to-be-read), reading lists, Calibre library queries, book searches, or mentions Calibre. Also use for queries about book ratings, authors, reading status, or library statistics.
EnglishUse when reviewing scientific or technical manuscripts, papers, theses, master's theses, dissertations, LaTeX drafts, thesis chapters, or final submission drafts for scientific correctness, structure, methodology, claim support, reproducibility, notation, citations, writing quality, and concrete revision planning.
EnglishUse when the user wants a local research digest from tracked topics or wants to manage tracked research topics.
EnglishFetch ranked RSS digests by tag; list, search, add, edit, import, export, disable, enable, or remove feeds; and run feed health checks.
EnglishEvidence-gated journal and conference venue selection for scholarly drafts; deliverable rankings require comparator-paper evidence.
EnglishUse when the user asks to draw, refactor, extract, compile, or review a TikZ/PGF figure, especially structural diagrams such as flowcharts, DAGs, trees, commutative diagrams, finite graphs, automata, or research-derived summary figures. Prefer this skill when the output should follow a structure-first workflow like figure brief to spec to render to check to compile to review, and when document-facing output should use adjustbox width fitting.
English
AGENT SKILLS ATLASIncludes Adversarial Boundary Gate, Autonomous Research Loop, Paper Review, 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
Adversarial Boundary Gate
Use before delivering work that incorporated content the agent did not author — fetched web pages, PDFs, retrieved or library documents, tool or subagent output — or that performs an outward-facing or irreversible action. Maps trust boundaries and runs an abuse-case and prompt-injection check, delegating to a fresh-context security reviewer.
Autonomous Research Loop
Run bounded autonomous research iterations with evidence gates, recovery ledgers, and optional cross-agent handoffs; prefers host-owned multi-agent panel with single-path drive primary; scripted force-loop defaults (Goal Focus enforce, hard goalpriority, notify ON). Use when the user asks to continue research autonomously, run a research loop, integrate autonomous agent loops, or keep improving a research workflow without repeated prompts.
Calibre
Search and query Calibre library databases. Use when the user asks about books, TBR (to-be-read), reading lists, Calibre library queries, book searches, or mentions Calibre. Also use for queries about book ratings, authors, reading status, or library statistics.
Paper Review
Use when reviewing scientific or technical manuscripts, papers, theses, master's theses, dissertations, LaTeX drafts, thesis chapters, or final submission drafts for scientific correctness, structure, methodology, claim support, reproducibility, notation, citations, writing quality, and concrete revision planning.
Research Digest Wrapper
Use when the user wants a local research digest from tracked topics or wants to manage tracked research topics.
Rss News Digest
Fetch ranked RSS digests by tag; list, search, add, edit, import, export, disable, enable, or remove feeds; and run feed health checks.
Submission Venue Selector
Evidence-gated journal and conference venue selection for scholarly drafts; deliverable rankings require comparator-paper evidence.
Tikz Draw
Use when the user asks to draw, refactor, extract, compile, or review a TikZ/PGF figure, especially structural diagrams such as flowcharts, DAGs, trees, commutative diagrams, finite graphs, automata, or research-derived summary figures. Prefer this skill when the output should follow a structure-first workflow like figure brief to spec to render to check to compile to review, and when document-facing output should use adjustbox width fitting.
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 Adversarial Boundary Gate 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: MIT. The author’s terms apply.