propose-mitigations
Skill2 starsChanged 6 months agoApache-2.0View on GitHub
Propose concrete mitigation strategies for severe obstacles. MUST use search tools to validate that proposed mitigations are realistic — no armchair theorizing. Each mitigation must have evidence of feasibility.
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
- direction-narrowingSkill
- 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
- validate-leavesSkill
- warm-startSkill
The file
Files
Propose Mitigations
Concrete, search-validated mitigation strategies for severe obstacles.
Execution
Subagent — spawned via subagent-spawning/spawn-agent skill.
Input
- Obstacles with severity assessments
- ActorProfile
Search
Required — must use imported skills to validate feasibility:
- web-search (web-browsing): Quick discovery of tools, frameworks, courses
- web-research (web-browsing): Deep reading of mitigation resources
- literature-overview (literature-engine): Find papers that solved similar obstacles
- literature-search (literature-engine): Medium-depth search for methodological alternatives
- literature-research (literature-engine): Deep reading for specific evidence
Output
For each severe obstacle: mitigation strategy + evidence of feasibility + estimated effort.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
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.