The super-loop that closes the research→backlog loop — it chains the outward CRAWLERS (the daily idea-scout arXiv/GitHub feed, the industry scans, the RESEARCH/CONCEPT corpus) into the STUDY pipeline (/study-repo → /field-borrow) and runs the whole thing on a cadence. The crawler surfaces repo-shaped leads into a needs-triage queue and stops; turning any one into scoped, witnessed, license-clean backlog is still a manual pass someone has to remember to run. This skill is that seam, automated: once per pass it CRAWLS the freshest outward signal, SELECTS the single highest-value repo-shaped lead, STUDIES it with /study-repo (clone into scratch, pin the SHA, read the code not the pitch, decompose small), WITNESSES each borrow with /field-borrow (fakfeaturequery/fak index → PRESENT/PARTIAL/ABSENT), FILES the surviving PARTIAL/ABSENT borrows as small independently-shippable leaves under the right epic, and REGISTERS a dated CONCEPT-STUDY- note. It re-implements none of those tools — it orders them, and holds the honesty boundary: a crawl is not a borrow, a study is not a ship. Set it to run unattended with tools/registerscoutloop.ps1 (plan-by-default, -Launch the opt-in). Use when the operator says "keep scouting for new research and turn it into backlog", "run the study loop on new repos", "combine the crawlers with study-repo", "auto-triage the idea-scout queue into real tickets", or "set the research loop running".
Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI
Supported by the Atlas install prompt. Skill-specific requirements vary.
Skill stats
Skills1CategoryScience & researchStars0
About this skill
The super-loop that closes the research→backlog loop — it chains the outward CRAWLERS (the daily idea-scout arXiv/GitHub feed, the industry scans, the RESEARCH/CONCEPT corpus) into the STUDY pipeline (/study-repo → /field-borrow) and runs the whole thing on a cadence. The crawler surfaces repo-shaped leads into a needs-triage queue and stops; turning any one into scoped, witnessed, license-clean backlog is still a manual pass someone has to remember to run. This skill is that seam, automated: once per pass it CRAWLS the freshest outward signal, SELECTS the single highest-value repo-shaped lead, STUDIES it with /study-repo (clone into scratch, pin the SHA, read the code not the pitch, decompose small), WITNESSES each borrow with /field-borrow (fakfeaturequery/fak index → PRESENT/PARTIAL/ABSENT), FILES the surviving PARTIAL/ABSENT borrows as small independently-shippable leaves under the right epic, and REGISTERS a dated CONCEPT-STUDY- note. It re-implements none of those tools — it orders them, and holds the honesty boundary: a crawl is not a borrow, a study is not a ship. Set it to run unattended with tools/registerscoutloop.ps1 (plan-by-default, -Launch the opt-in). Use when the operator says "keep scouting for new research and turn it into backlog", "run the study loop on new repos", "combine the crawlers with study-repo", "auto-triage the idea-scout queue into real tickets", or "set the research loop running".
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.
The super-loop that closes the research→backlog loop — it chains the outward CRAWLERS (the daily `idea-scout` arXiv/GitHub feed, the industry scans, the RESEARCH/CONCEPT corpus) into the STUDY pipeline (`/study-repo` → `/field-borrow`) and runs the whole thing on a cadence. The crawler surfaces repo-shaped leads into a needs-triage queue and stops; turning any one into scoped, witnessed, license-clean backlog is still a manual pass someone has to remember to run. This skill is that seam, automated: once per pass it CRAWLS the freshest outward signal, SELECTS the single highest-value repo-shaped lead, STUDIES it with `/study-repo` (clone into scratch, pin the SHA, read the code not the pitch, decompose small), WITNESSES each borrow with `/field-borrow` (`fak_feature_query`/`fak index` → PRESENT/PARTIAL/ABSENT), FILES the surviving PARTIAL/ABSENT borrows as small independently-shippable leaves under the right epic, and REGISTERS a dated `CONCEPT-STUDY-*` note. It re-implements none of those tools — it orders them, and holds the honesty boundary: a crawl is not a borrow, a study is not a ship. Set it to run unattended with `tools/register_scout_loop.ps1` (plan-by-default, `-Launch` the opt-in). Use when the operator says "keep scouting for new research and turn it into backlog", "run the study loop on new repos", "combine the crawlers with study-repo", "auto-triage the idea-scout queue into real tickets", or "set the research loop running".
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