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 gutierrezje

IndexedMIT

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/gutierrezje-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

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: MIT
Instructions: 17 lines in SKILL.md · view on GitHub

Files (6)

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

SKILL.md (first lines)

# Reflect

Extract durable lessons from the current completed task and route each accepted lesson to structure.

Read [the global routing table](../jesus-mode/references/routes.md) before dispatching. Inspect the current subagent tool's supported model and effort overrides; never silently inherit the parent after a pinned-model rejection.

1. Establish the evidence set: current task, plan, diffs, test output, decision log, and linked artifacts. Do not scan guessed transcript paths.
2. Use the Reflect tooling and judgment routes for two read-only reviewers. Add a divergent reviewer only for long or high-stakes work.
3. Ask each reviewer for evidence-backed Keep, Change, and Backlog findings with exact destinations.
4. Have the parent synthesize duplicates and reject findings unsupported by task evidence. Use the Reflect synthesizer route for one advisor only when the parent needs stronger judgment.
5. Present Accepted, Rejected, and Backlog items. Obtain approval before editing global skills or instructions.
6. Route approved edits through `$skill-creator` and `$writing-for-agents`; route recurring tooling gaps into checks, scripts, or tracked backlog.
7. Validate every edited skill and report applied, rejected, and deferred lessons.

Completion means every accepted lesson has one durable destination and every rejected lesson has an evidence-based reason.

From gutierrezje/jstack, MIT.

Signals

Stars: 0
Forks: 0
Open issues: 0
Last commit (this folder): Oct 4, 2026 (24 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License: MIT
Repository: github.com/gutierrezje/jstack
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 gutierrezje

Cite this page

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