q00/symposium · Archived

reflect

Compare meaning candidates from Wonder with the user's intended meaning, one pair at a time. In the Socrates loop, Reflect writes only the current cycle's ### Reflect section. Triggers (EN): reflect, compare meanings, surface meaning gap, check what I meant Do NOT use when: expanding meanings (-> wonder), merging meanings into shared meaning (-> refine), restating a goal (-> restate), or running the full Seed loop (-> socrates) vs wonder: Wonder expands candidates; Reflect checks where each can…

First seen Jun 19, 2026

Installation

$ npx skills add q00/symposium --skill reflect

Stronger alternatives

This repository is archived — consider an actively maintained alternative.

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from q00/symposium.

npx skills add q00/symposium

Browse all from q00/symposium

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 30
License LICENSE
Default branch main
Open issues 0
Status Archived

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 1,717 B
  • docs SUMMARY.md 567 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 2 installs

SKILL.md

Reflect

Details

Reflect takes the active cycle's ### Wonder candidates and asks the user whether each one matches what they meant.

Ask one comparison at a time. Do not decide which meaning is correct. Do not invent missing user intent.

Question Style

Prefer multiple-choice checks so the user can classify each meaning quickly. Always allow a free-form correction.

Use this shape:

Does this candidate match what you meant?
Candidate: <meaning candidate>
A. Yes, this is close
B. Partly, but the nuance is different
C. No, this is not what I meant
D. Other / correct the nuance in your own words

Use the user's selected or written nuance in the User's intended nuance field.

Output

Write a comparison list:

- Meaning A
  - User's intended nuance: ...
  - Model's interpreted nuance: ...
  - Same / different: ...

Scratch Contract

Read from .symposium/scratch/socrates.md under the active cycle's ### Wonder.

Write to the same cycle's ### Reflect.

When every meaning candidate has a visible same/different comparison, stop and hand off to refine.