reflect

Analyzes recent OpenCode sessions to recommend reusable skills, agents, commands, and config changes.

Updated Feb 25, 2026
One-click install
npx skills add https://github.com/voiddreamz/dotfiles --skill reflect-voiddreamz
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: reflect
Source: https://github.com/voiddreamz/dotfiles/tree/main/.config/opencode/skills/reflect
Command: npx skills add https://github.com/voiddreamz/dotfiles --skill reflect-voiddreamz

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Repeated manual workflows and recurring friction across coding sessions go unnoticed, so opportunities to turn them into reusable skills, agents, commands, or config rules are missed. ## Core Features & Use Cases - Workflow Pattern Detection: Reviews recent sessions, project notes, and existing agent assets to find repeated friction with evidence and confidence scores. - Session Archaeology Mode: With --sessions, queries the OpenCode SQLite database to analyze historical sessions across repos, caching per-session summaries and aggregating cross-repo patterns. - Conservative Recommendations: Proposes the smallest useful improvement (prompt rule, skill, command, agent, playbook, or no change) and asks before modifying any config. - Use Case: Run /reflect --sessions --last 100 after weeks of work to discover that you repeatedly grep for test files before editing, and get a proposal for a reusable command that encodes that workflow. ## Quick Start Ask the agent to run /reflect on your recent work to identify repeated workflows worth turning into reusable skills or commands.

Frequently Asked Questions about reflect

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I analyze past OpenCode sessions for repeated workflows?▼

Run /reflect --sessions to query the OpenCode SQLite database for recent sessions. The workflow summarizes each session's goal, frictions, and tools used, caches results as JSON, then aggregates patterns across repos into a ranked report.

How does reflect decide whether to create a new skill or agent?▼

It scores candidates on frequency, cost, risk, stability, and coverage by existing assets. It always recommends the smallest useful form, preferring a prompt rule over a skill and a skill over a custom agent, and treats creating nothing as a valid outcome.

Can reflect change my OpenCode config automatically?▼

No. Reflect presents a proposal and asks for approval before editing prompts, skills, commands, agents, MCP permissions, or config. When changes are applied, it notes that a restart of OpenCode may be required for them to take effect.

What happens when session data cannot be loaded?▼

Sessions that fail to load or contain no messages are skipped with a warning, and analysis continues with the remaining sessions. A summary of skipped sessions is reported at the end of the run.

When should I not use the reflect workflow?▼

Avoid it for one-off debugging, ordinary implementation work, broad architecture reviews, or speculative agent creation without workflow evidence. It is designed only for identifying repeated, evidence-backed patterns worth packaging.