One repeatable pass that turns "look at " into scoped, witnessed, license-clean, FILED backlog. When someone drops anything that names a body of code — a GitHub URL, a local checkout, a monorepo subtree, a single file, an npm/pypi/crates package, a paper-with-code / arXiv link, a tarball, a PR/diff, or a bare "study this repo" / "what can we learn from X" / "borrow from " with no URL at all — this drives the whole flow end to end. Acquire the source into scratch (never the tree) and PIN the commit SHA; read the CODE not the pitch, DEEP by default (fan parallel readers across load-bearing modules + tests + recent commits, then a completeness-critic pass — not a README skim); extract MANY candidate borrows, each grounded at a real source path:line@sha; decide borrow-vs-integrate with a license + attribution check; DECOMPOSE into many small independently-shippable tickets (or an epic + child leaves for a track), NEVER one "adopt everything from repo X" monolith; witness each borrow against fak (fakfeaturequery/fak index → PRESENT/PARTIAL/ABSENT), and — the default terminal action — FILE the surviving PARTIAL/ABSENT borrows as gh issues under the right epic. The acquisition/exploration/scoping front-half that FEEDS field-borrow (which witnesses+files a single named capability). Distinct from the automated outward idea-scout and the kernel-only sota-check. Use when handed a specific external repo/codebase/paper to learn from, before filing any "we should adopt X from repo Y" issue, after a competitor open-sources something worth reading, or on a /loop cadence over a watch-list.
Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI
Supported by the Atlas install prompt. Skill-specific requirements vary.
Skill stats
Skills1CategoryScience & researchStars0
About this skill
One repeatable pass that turns "look at " into scoped, witnessed, license-clean, FILED backlog. When someone drops anything that names a body of code — a GitHub URL, a local checkout, a monorepo subtree, a single file, an npm/pypi/crates package, a paper-with-code / arXiv link, a tarball, a PR/diff, or a bare "study this repo" / "what can we learn from X" / "borrow from " with no URL at all — this drives the whole flow end to end. Acquire the source into scratch (never the tree) and PIN the commit SHA; read the CODE not the pitch, DEEP by default (fan parallel readers across load-bearing modules + tests + recent commits, then a completeness-critic pass — not a README skim); extract MANY candidate borrows, each grounded at a real source path:line@sha; decide borrow-vs-integrate with a license + attribution check; DECOMPOSE into many small independently-shippable tickets (or an epic + child leaves for a track), NEVER one "adopt everything from repo X" monolith; witness each borrow against fak (fakfeaturequery/fak index → PRESENT/PARTIAL/ABSENT), and — the default terminal action — FILE the surviving PARTIAL/ABSENT borrows as gh issues under the right epic. The acquisition/exploration/scoping front-half that FEEDS field-borrow (which witnesses+files a single named capability). Distinct from the automated outward idea-scout and the kernel-only sota-check. Use when handed a specific external repo/codebase/paper to learn from, before filing any "we should adopt X from repo Y" issue, after a competitor open-sources something worth reading, or on a /loop cadence over a watch-list.
Quick start
Copy the install prompt. Use the green button above this README.
Send it to your agent. Paste it into your coding agent’s chat and send.
Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.
One repeatable pass that turns "look at <repo>" into scoped, witnessed, license-clean, FILED backlog. When someone drops anything that names a body of code — a GitHub URL, a local checkout, a monorepo subtree, a single file, an npm/pypi/crates package, a paper-with-code / arXiv link, a tarball, a PR/diff, or a bare "study this repo" / "what can we learn from X" / "borrow from <repo>" with no URL at all — this drives the whole flow end to end. Acquire the source into scratch (never the tree) and PIN the commit SHA; read the CODE not the pitch, DEEP by default (fan parallel readers across load-bearing modules + tests + recent commits, then a completeness-critic pass — not a README skim); extract MANY candidate borrows, each grounded at a real source `path:line@sha`; decide borrow-vs-integrate with a license + attribution check; DECOMPOSE into many small independently-shippable tickets (or an epic + child leaves for a track), NEVER one "adopt everything from repo X" monolith; witness each borrow against fak (`fak_feature_query`/`fak index` → PRESENT/PARTIAL/ABSENT), and — the default terminal action — FILE the surviving PARTIAL/ABSENT borrows as gh issues under the right epic. The acquisition/exploration/scoping front-half that FEEDS `field-borrow` (which witnesses+files a single named capability). Distinct from the automated outward `idea-scout` and the kernel-only `sota-check`. Use when handed a specific external repo/codebase/paper to learn from, before filing any "we should adopt X from repo Y" issue, after a competitor open-sources something worth reading, or on a `/loop` cadence over a watch-list.
About this listing
Category
Science & research
Reported license
Apache-2.0
Listing language (estimated)
English
Review status
Not individually reviewed
Agent compatibility
Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLI