agentleFS
Sign inStart free
VisionaireLabsVisionaireLabs/Visionaire/skills/visionaire-feedback/SKILL.md

visionaire-feedback

Skill4 starsChanged 44 days agoMITView on GitHub

Collect and log feedback from [your name] after delivering significant work. Use after completing any meaningful deliverable — strategy docs, content drafts, brand work, code specs, research, creative briefs. Triggers when work is delivered and a response is received. Ask for a rating and optional comment, then log it. This feeds the self-study feedback-analysis loop.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    After delivering significant work and receiving a response from [your name], collect feedback.

    line 8
  2. Distinctive:

    After delivering: strategy docs, content, brand work, code/specs, research, creative briefs, or any task [your name] asked for explicitly.

    line 11
  3. Distinctive:

    Keep it light — one line at the end of the reply or as a follow-up:

    line 14
  4. Distinctive:

    Never ask for feedback twice on the same deliverable

    line 33
  5. Distinctive:

    If [Your name] rates without a comment, log with empty comment — that's fine

    line 34

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Visionaire Feedback Collection

After delivering significant work and receiving a response from [your name], collect feedback.

When to collect

After delivering: strategy docs, content, brand work, code/specs, research, creative briefs, or any task [your name] asked for explicitly. Skip for quick factual answers, casual chat, or heartbeats.

How to ask

Keep it light — one line at the end of the reply or as a follow-up:

"How'd that land? Rate it 1–5 (and drop a note if something missed)."

or shorter:

"Rate it 1–5?"

Logging feedback

Once [Your name] responds with a rating, run:

node /data/.openclaw/workspace/scripts/log-feedback.mjs <rating> \
  --task "<short task description>" \
  --comment "<their comment if any>" \
  --tags "<relevant tags e.g. strategy,solana,content>"

Notes

  • Never ask for feedback twice on the same deliverable
  • If [Your name] rates without a comment, log with empty comment — that's fine
  • Feedback feeds directly into the self-study feedback-analysis loop (fires once 1+ entries exist)
  • Cap is 100 entries — oldest drop off automatically

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free