bikeread/promethos
16 skills
$npx skills add bikeread/promethosSkillInstalls
build-agent-evalsUse when an agent needs the smallest useful eval pack to catch regressions or false confidence early.choose-agent-architectureUse when an agent's job is clear and you need to choose structure, boundaries, or single-agent vs multi-agent.debug-agent-failuresUse proactively when an agent repeats a failure, loops, or degrades and needs a local root-cause check before redesign.define-agent-requirementsUse when an agent idea is still fuzzy and v1 scope, success bar, or operating boundaries are not concrete.design-agent-contextUse when an agent reads too much, misses key files, or needs a clear eager-vs-deferred context plan.design-agent-memoryUse when deciding what an agent should remember across turns or sessions versus fetch on demand.design-agent-permissionsUse after autonomy policy is set and you need permission classes, defaults, approvals, and denial behavior.design-agent-toolsUse when a tool is misused or underspecified because its inputs, errors, or side effects are unclear.evolve-skill-libraryUse when the skill library feels crowded, redundant, stale, or mis-scoped and needs pruning or reshaping.orchestrate-agent-subagentsUse when delegation is already justified and you need safe subagent ownership, context, and merge boundaries.plan-agent-implementationUse when architecture is settled and you need an ordered implementation plan with checkpoints and verification.route-agent-designUse proactively when a user is defining, constraining, debugging, or evaluating an agent system and needs the right PromethOS skill.set-agent-autonomy-boundariesUse proactively when an agent lacks checkpoint policy or risky actions need clear human-review boundaries.trim-agent-scopeUse proactively when a plan, skill, or agent keeps absorbing side quests and needs to return to core scope.turn-postmortem-to-improvementUse after a failure, correction, or standout success to decide what reusable guardrail, eval, skill, or rule should follow.verify-agent-readinessUse proactively before declaring success, shipping, or moving on when an agent or change needs fresh verification evidence.