Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Auto-learns to prioritize tasks by urgency, impact, and user patterns. Grows smarter with each decision.
Auto-learns to prioritize tasks by urgency, impact, and user patterns. Grows smarter with each decision.
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
This skill auto-evolves. Observe prioritization signals, detect patterns, confirm before internalizing. Core Loop: Assess β When tasks arrive, evaluate urgency + importance Classify β Assign priority level (P0-P3) Route β P0 immediately, P1-P3 into queue Learn β Notice when user overrides priority β propose pattern Confirm β After 2+ corrections, ask: "Should X always be P[n]?" Check signals.md for urgency indicators. Check patterns.md for learned priority rules.
LevelResponseExamplesP0Interrupt immediatelyServer down, security breach, deadline todayP1Next available slotBlocking work, waiting users, same-day tasksP2Scheduled queueImportant but not urgent, planning, reviewsP3BacklogIdeas, "someday", low-impact optimizations Default: When uncertain, ask. Start conservative, learn boundaries.
Automatic P0 triggers: Words: "urgent", "ASAP", "down", "broken", "emergency" Context: External deadlines, blocked team members Pattern: User previously escalated similar tasks Automatic P3 triggers: Words: "when you have time", "no rush", "idea for later" Context: No deadline mentioned, exploratory
One line: pattern: priority (level) [context] Examples: deploy-issues: P0 (confirmed) [always urgent] refactoring: P2 (pattern) [user deprioritized 3x] docs-updates: P3 (confirmed) [explicit "low priority"]
When multiple tasks compete: Group by priority β P0 first, always Within same priority β Order by arrival or explicit sequence Report queue β "3 P1 tasks queued, handling X first" Re-triage on change β New P0 interrupts P1 work
Phrases that signal priority pattern: "This should be higher priority" "Drop everything and..." "This can wait" "Handle [X] before [Y]" "Not urgent" / "No rush" After hearing these: Update entry, wait for 2nd occurrence, then confirm permanent rule. Empty sections = still learning. Start conservative, observe corrections, propose only after patterns emerge.
Agent frameworks, memory systems, reasoning layers, and model-native orchestration.
Largest current source with strong distribution and engagement signals.