Openly-Useful
- 6 skills
- 0 followers
- 11 hours ago last updated
- ▌ Runglance · openly-useful bundleShow truthful, low-overhead live progress for any agent, skill, test, workflow, or automation run. Use for a portable RunGlance HUD, workflow/skill/agent accounting, context and quota visibility when hosts report it, explicit lock state, one-second local status watching, host hook normalization, verification commands, and concise or verified final run receipts. Works without model calls, network access, API keys, or the optional read-only RunGlance MCP companion.
- ▌ Project Status · openly-useful bundleInspect, validate, generate, and maintain evidence-backed project readiness. Use for weighted readiness, blockers, active and deferred effort, unknown estimates, provenance checks, one-shot live monitoring, dashboard plan/apply/check workflows, repository attachment for Codex and Claude, or local Project Status plugin packaging and verification. Use the separate RunGlance skill for live agent, workflow, test, usage, lock, HUD, and run-receipt tracking.
- ▌ Pickup Swarm · openly-useful bundleUse when recovering interrupted work, resolving an uncertain handoff, or discovering explicitly requested outstanding workflows. Plain current-status queries use the existing status snapshot rather than a recovery audit.
- ▌ Conductor Swarm · openly-useful bundleUse when coordinating substantive multi-lane execution, integrating independent work, or resolving stalled delivery across agents. A simple status query or isolated small edit does not require swarm orchestration.
- ▌ Loop Improvement · openly-useful bundleCapture authorized milestone outcomes, evaluate a bounded improvement proposal, and retrieve or retire accepted project-local lessons. Use for an explicitly enabled learning loop or requested improvement review; ordinary status stays read-only.
- ▌ Cross Tool Continuity Swarm · openly-useful bundleUse when work must move between AI coding tools, survive a paused session, be resumed from a verified checkpoint, or be prepared as a one-command Claude Code continuation. Capture local-only session lineage, audit portable project state, capture evidence, prepare and review a bounded handoff, record synchronization, generate a launch prompt, and resume only after current verification.