Skip to content
Research
Command

/feedback

Review, capture, and promote curated user-feedback candidates detected from session hooks.

BOOST
From plugin
nvk-llm-wiki
1.4k28 skills28 commands
Install
> /plugin marketplace add nvk/llm-wiki
> /plugin install wiki@llm-wiki

How it fires

How this command gets triggered: by you, by Claude, or both.

  • Fires itselfClaude auto-loads it when your prompt matches the work.
  • You can call itInvoke it directly when you want it.
  • Slash command/feedback

Context preview

What this command does when you run it.

Review, capture, and promote curated user-feedback candidates detected from session hooks.

Command definition

feedback.md
description: "Review, capture, and promote curated user-feedback candidates detected from session hooks."
argument-hint: "list|show|capture|promote [options]"
allowed-tools: Read, Write, Edit, Glob, Grep, Bash(ls:*), Bash(mkdir:*), Bash(python3:*), Bash(scripts/llm-wiki-session:*)

Your task

Manage the feedback-curator layer for llm-wiki sessions. Feedback candidates are small distilled records of user corrections, preferences, approvals, and plan acceptance signals. They live under `HUB/.sessions/feedback/` until explicitly promoted into a topic wiki.

First read `references/feedback.md` and `references/sessions.md`, then resolve HUB by the standard hub-resolution protocol from `references/hub-resolution.md`. Prefer the deterministic helper when available:

scripts/llm-wiki-session --hub "$HUB" feedback <subcommand>

Parse $ARGUMENTS

  • `list [--unpromoted] [--type correction|preference|approval|decision|manual] [--min-confidence low|medium|high]`: show captured candidates.
  • `show <candidate-id>`: display one candidate with its distilled lesson and redacted user-feedback preview.
  • `capture --text "..." [--session-id <id>]`: manually add a feedback candidate.
  • `promote <candidate-id> --topic <slug>`: write the candidate into the target topic's `raw/notes/` layer and append the topic log.

Policy

1. Candidate capture is allowed from trusted hooks, but promotion is explicit. 2. Do not treat generic acknowledgements (`ok`, `thanks`, `cool`) as durable lessons. 3. High-value feedback includes corrections, preferences, `always`/`never` rules, and explicit statements that the agent did the right thing. 4. Approval/decision candidates are validation of the immediately preceding context unless corroborated by a session digest. 5. Store redacted previews and hashes, not full transcripts.

Examples

scripts/llm-wiki-session --hub "$HUB" feedback list --unpromoted
scripts/llm-wiki-session --hub "$HUB" feedback show fb-abc123
scripts/llm-wiki-session --hub "$HUB" feedback capture --text "next time use the release checklist before tagging"
scripts/llm-wiki-session --hub "$HUB" feedback promote fb-abc123 --topic meta-llm-wiki

Report absolute paths for every promoted note. Append topic `log.md` when promoting into a topic wiki.

Read more
Ships withnvk-llm-wiki

LLM-compiled knowledge bases for any AI agent. Parallel multi-agent research, thesis-driven investigation, source ingestion, wiki compilation, querying, and artifact generation.

Get the whole plugin
Stats
1,394
Stars
131
Forks
Active
Maintenance
Python
Language
MIT
License
6d ago
Last commit
6mo ago
Created
1d ago
Added

Repo: nvk/llm-wiki

Other commands on nvk-llm-wiki.