direction-narrowing
Skill2 starsChanged 6 months agoApache-2.0View on GitHub
Focus within the user's chosen field(s). Identify specific sub-directions through deep paper and web research, then present ranked candidates. Use after landscape-reconnaissance has identified fields of interest.
In this repository32 other files it gives its agents.
- actor-profilingSkill
- and-or-decomposeSkill
- ask-constraintsSkill
- ask-decomposition-validationSkill
- ask-intentionalitySkill
- ask-obstacle-acceptanceSkill
- assess-obstacle-severitySkill
- broad-paper-searchSkill
- broad-web-searchSkill
- clarify-resourcesSkill
- cold-startSkill
- crystallize-north-starSkill
- deep-web-searchSkill
- explore-resumeSkill
- feasibility-checkSkill
- final-validationSkill
- formulate-top-goalSkill
- generate-candidate-fieldsSkill
- generate-research-briefSkill
- goal-decompositionSkill
- hot-startSkill
- identify-obstaclesSkill
- landscape-reconnaissanceSkill
- landscape-synthesisSkill
- north-star-crystallizationSkill
- north-star-synthesisSkill
- obstacle-analysisSkill
- present-and-askSkill
- present-candidatesSkill
- propose-mitigationsSkill
- validate-leavesSkill
- warm-startSkill
The file
Files
Direction Narrowing
Focus within chosen field(s). Identify specific sub-directions and present ranked candidates.
Available SOPs
| SOP | Purpose | Execution |
| broad-paper-search | Scan papers in the chosen field(s) | import: literature-overview |
| deep-web-search | Deep reading of web resources in the field | subagent |
| present-candidates | Present ranked sub-directions to user | dialogue |
Methodology Guidance
- hot-start may only need partial SOP execution (a few searches for context)
- You decide search depth based on information sufficiency
present-candidatesdepth scales by start mode:- cold-start: broad sub-directions available to pursue
- warm-start: specific sub-problems and research tracks
- hot-start: granular knowledge points, technical details
Hard Constraints
broad-paper-search: at least 80 papers scanneddeep-web-search: at least 30 web pages read in full
Output (Tactic-Level Aggregation)
RankedCandidates[] + user's selection
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.