This entry duplicates reflect, which is the one we list in search.

reflect

Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill.

Skill by n3m6

IndexedGPL-3.0★ 19

Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/n3m6-reflect

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill. Use when the user says reflect.

Use cases: writing, agent-building

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions: not checked yet.

What's inside

Skill name: reflect
Description: Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill. Use when the user says reflect.
License: GPL-3.0
Metadata: opencode/autoinvoke: false
Instructions: 12 lines in SKILL.md · view on GitHub

Files (5)

SKILL.md
divergent-reviewer.md · references/
judgment-reviewer.md · references/
synthesizer.md · references/
tooling-reviewer.md · references/

SKILL.md (first lines)

# Reflect

Turn evidence from the active task into focused improvements to existing skills.

1. Scope the evidence to this task. Read [OpenCode runtime](../../references/opencode-runtime.md) and obtain the active session record through available tools or a supplied transcript. If only summaries are available, mark that limitation and use observable artifacts; do not invent tool traces.
2. Read the existing skills the task actually used. Identify repeated friction, missed judgment, or reliable shortcuts. Prefer an existing skill as the home for a lesson.
3. When permitted, use three independent read-only reviewers with [tooling](references/tooling-reviewer.md), [judgment](references/judgment-reviewer.md), and [divergent](references/divergent-reviewer.md) briefs. Use `reflect-tooling` and `reflect-judgment` preferences, inherited by default. Queue within runtime limits. Otherwise apply the three lenses directly and disclose the lack of independent review.
4. Synthesize with [the synthesis contract](references/synthesizer.md). Separate accepted lessons, rejected suggestions, and backlog. Ground each accepted lesson in an observed failure or useful behavior rather than personal preference inferred from one example.
5. Make the requested skill edits. Preserve scope, invocation policy, and unrelated guidance. Use the available skill-creator for substantial authoring and validate the resulting frontmatter, links, helpers, and relevant behavior. A new skill is warranted only when no existing skill fits and the capability deserves its own entry point.
6. Return the lesson, its evidence, the file changed, validation, and any unresolved gap. Do not turn reflection into unrelated repository cleanup.

From n3m6/opencode-config, GPL-3.0.

Signals

Stars: 19
Forks: 2
Open issues: 1
Last commit (this folder): Oct 6, 2026 (22 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License: GPL-3.0
Repository: github.com/n3m6/opencode-config
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

Same skill elsewhere

Copies of this SKILL.md published by others; search shows only one of them.

More from n3m6

Cite this page

reflect skill. Agent Mart. https://agentmart.dev/skills/n3m6-reflect (last updated 2026-10-24)