reflect

Review recent sessions to identify repeated workflows and recommend reusable skills, agents, or config changes.

Updated Aug 16, 2026
One-click install
npx skills add https://github.com/Aveer/skills --skill reflect-aveer
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: reflect
Source: https://github.com/Aveer/skills/tree/main/skills/reflect
Command: npx skills add https://github.com/Aveer/skills --skill reflect-aveer

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Teams and individuals repeat the same manual workflows across sessions without realizing which ones deserve to become reusable skills, agents, commands, or configuration rules, leading to wasted effort and inconsistent execution. ## Core Features & Use Cases - Pattern Detection: Scans recent sessions, project notes, and existing agent assets to find repeated workflow friction with at least two occurrences. - Evidence-Driven Recommendations: Scores candidates by frequency, cost, risk, stability, and coverage, then proposes the smallest useful form such as a prompt rule, skill, command, or playbook. - Conservative Guardrails: Inspects existing assets before suggesting new ones, asks before changing config or prompts, and treats "create nothing" as a valid outcome. - Use Case: After noticing you repeatedly run the same release checklist manually, run /reflect release workflow to get a proposal for a reusable command or skill backed by session evidence. ## Quick Start Ask the agent to run /reflect on your recent work to find repeated workflows worth turning into reusable assets.

Frequently Asked Questions about reflect

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

FAQPage Schema
How do I find repeated workflows in my OpenCode sessions?▼

Run /reflect with no arguments to review recent work broadly, or /reflect <focus> to target a specific workflow area. It inspects session history, project notes, and existing assets, then reports repeated patterns with evidence and frequency.

How to decide between creating a skill, command, or custom agent?▼

Reflect scores each candidate and recommends the smallest useful form: a prompt rule for small behavior changes, a skill for reusable task guidance, a command for stable manual triggers, and a custom agent only for distinct specialist lanes.

Does reflect change my config or prompts automatically?▼

No. Reflect presents a concise proposal and asks for confirmation before writing files or changing config, prompts, agents, skills, or MCP permissions, unless you explicitly requested a specific edit.

When should I not use reflect for workflow improvement?▼

Avoid reflect for ordinary implementation work, one-off debugging, broad architecture reviews, or speculative agent creation without workflow evidence. It requires repeated, user-visible friction rather than isolated incidents.

Why does reflect sometimes recommend creating nothing?▼

Reflect treats "create nothing" as a successful result when evidence is weak, such as candidates appearing only once, being ambiguous, or already covered by existing skills, commands, or agents.