Analyzes past OpenCode sessions to recommend reusable skills, agents, commands, and config changes.
npx skills add https://github.com/adikpb/dotfiles --skill reflect-adikpb
Please help me install this Agent Skill. Skill: reflect Source: https://github.com/adikpb/dotfiles/tree/main/.config/opencode/skills/reflect Command: npx skills add https://github.com/adikpb/dotfiles --skill reflect-adikpb
--sessions, queries the OpenCode SQLite database to analyze historical sessions across repos, aggregating frictions, models, agents, and tools used. - Evidence-Driven Proposals: Scores candidates by frequency, cost, risk, stability, and coverage, then proposes changes before writing anything. - Use Case: After noticing you repeatedly run the same test-fix loop, run /reflect --sessions --last 100 to get a ranked report of recurring patterns and a proposal to add a /test-ci command. ## Quick Start Ask the agent to run /reflect on your recent sessions and suggest which repeated workflows should become reusable skills or commands.High-intent search queries and answers about installing and using this skill.
Run /reflect --sessions to query the OpenCode SQLite database at ~/.local/share/opencode/opencode.db. It loads recent sessions and messages, summarizes goals, frictions, and tools used per session, then aggregates findings across repos into a ranked report.
Reflect scores each candidate on frequency, cost, risk, stability, and existing coverage, then picks the smallest useful form. Prompt rules come before skills, skills before commands, and custom agents only when a distinct specialist lane is clearly needed.
No. Reflect presents a concise proposal and asks before writing files or changing config, prompts, agents, MCP permissions, or skills. When changes are applied, it prefers narrow append-only edits and notes that a restart may be required.
It reports that no strong repeated workflow was found and recommends adding or changing nothing. Treating 'create nothing' as a valid outcome is part of its conservative, evidence-driven contract.
Sessions are skipped when they cannot be loaded from the database or contain no messages. Reflect logs each failure, continues with remaining sessions, and reports the total skipped count at the end.
dlwlrmaxAnalyzes OpenCode session history to recommend reusable skills, agents, and config changes.
CodeAlive-AIGuide updates to coding agent settings files with validation.
gaelic-ghostSync AGENTS.md and repo-maintenance guidance for existing Swift Package repositories.
dpalferyDelegate React, CSS, and HTML tasks to the react-dev agent.