Questlog
Maintain an explicit Markdown commitments ledger with a local cockpit for NOW, next actions, deadlines, waiting items, workstream states and inbox capture.
Antreas Antoniou
@antreasantoniou
Install
$ openclaw skills install @antreasantoniou/questlog-agent-skillQuestlog
Resolve the user's explicit QUESTLOG_ROOT before reading or changing commitments. Read README.md for startup and references/ledger-format.md for the grammar. A fresh install is empty; do not seed personal records or infer commitments from general discussion.
Capture only the authorized delta, separating commitments from reference knowledge. Keep NOW bounded, identify the next concrete action, and distinguish deadlines from waiting-on dates. Propose uncertain priorities instead of assigning them silently. Use the ledger's actual evidence; local notes do not establish that an email was sent, a job ran, or a deadline was accepted.
For changes use the bundled CLI or loopback UI so writers share the lock. HTTP ledger writes require If-Match with the current /api/state head; a 409 means reload and reconsider, not overwrite. Inspect diffs when editing a complete ledger. Direct external editors must be stopped or coordinated: the runtime cannot lock an editor that ignores its lock.
The cockpit can capture local instruction drafts, but this package includes no runner: pending means saved, never executed. Mail, calendar, semantic search, archive routing and host scheduling are optional external integrations, not prerequisites. Use an available host-native scheduler only when requested; do not install cron jobs by default. Each external action retains its own authorization boundary.
Top skills in this category
self-improving agent
@pskoettCaptures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude rea
Skill Vetter
@spclaudehomeSecurity-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
Self-Improving + Proactive Agent
@ivangdavilaSelf-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
Proactive Agent
@halthelobsterTransform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack ๐ฆ
Agent Browser
@matrixyHeadless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection