feedback skills

truera/trulens

Skill Claude CodeCodex

Configure feedback functions and selectors for TruLens evaluations.

petergyang/human-review

Skill Claude CodeCodex

Open an HTML file, Markdown file, or localhost page in the browser so the user can edit text directly and leave comments on specific parts, then send all edits and comments back to you. Use after writing or updating something the user will read — specs, plans, reports, newsletter drafts, landing pages, slide decks…

plur-ai/plur

Skill Claude CodeCodex

The essential habits for an AI agent with memory — session bookends, learning triggers, verification, safety, and the operational discipline that turns raw recall into compounding intelligence. Pinned, always-injected.

amanning3390/hermeshub

Skill Claude CodeCodex

Agent-to-agent feedback protocol for HermesHub. Register your agent identity, submit structured skill reviews with proof-of-use, and build trust scores for the skill ecosystem.

jianger666/cursor-feedback-extension

Skill Claude CodeCodexCursor

Release instructions for publishing the cursor-feedback package to npm, Open VSX, and the Visual Studio Code Marketplace.

l1veIn/rambledesk

Skill Claude CodeCodex

Run a human-feedback loop through RambleDesk. Hard trigger: when the user invokes /ramble, $ramble, [$ramble], or says to use RambleDesk/ramble feedback, create a RambleDesk request before answering the substance unless they explicitly say not to send one. Also use when real human judgment, review, approval, or…

leetwito/cc-htmlfeedback

Skill Claude CodeCodex

Visualizing complex material (plans, designs, architectures, data models) as a self-contained HTML page is the preferred, best-practice way to collect the user's feedback - use this tool for EVERY HTML page meant to gather feedback. It serves your page(s) with a comment widget injected, then turns the comments you…

oubakiou/mdxg-redline

Skill Claude CodeCodex

Run the standard markdown review loop end-to-end with the mdxg-redline CLI: send a markdown document to a human reviewer, wait (via Bash polling) for the feedback.json they export, then apply their location-aware inline comments back into the markdown and revise it. Always use this skill when the user wants…

howdeploy/deploychan_mcp

Skill Claude CodeCodex

Use when writing or tuning ElevenLabs speech so it sounds alive, paced, and human; covers text shaping for Eleven Multilingual v2 and Eleven v3, plus API-based voice-setting updates from user feedback.

machbuilds/interactive-html

Skill Claude CodeCodex

Turn a folder of static HTML into a live commenting surface and act as the agent that responds. Inject a client library, start a local server, watch an on-disk inbox; when the user highlights text, picks an element, drags a region, or asks a question, read it and edit the HTML in response. If the user has no HTML yet…

ellmos-ai/build-your-users-mind

Skill Claude CodeCodex

Instructions for any agent model (Claude, Codex, agy/Gemini, Kimi) to build, maintain, and connect an empirical Theory-of-Mind model of ITS user from its own interaction logs to memory/rule files/system prompt. Activates when "build a ToM/decision avatar for my user", "Theory of Mind system user model"…

ellmos-ai/build-your-users-mind

Skill Claude CodeCodex

A method for building a model of how a particular user tends to make decisions from records of past conversations. It keeps that model in files that an AI agent can use alongside its memory or instructions.

ellmos-ai/build-your-users-mind

Skill Claude CodeCodex

Coordination strategies for AI agents working in parallel or hierarchically — 5 multi-agent patterns (Epstein, Hierarchy, Stigmergy, Consensus, Specialist). Bundled dependency of build-your-users-mind; its stage-2 classification uses Hierarchy + Stigmergy.

Autter-dev/agentic-sales-skills

Skill Claude CodeCodex

Reviews sales call transcripts and provides coaching feedback with scoring across 5 performance dimensions.

baskb/feedback-studio

Skill Claude CodeCodex

Instant Feedback Studio playground — serves a bundled sample landing page (a throwaway temp-dir copy) for you to comment on, with a few flaws to find. Starts empty by default (you add the comments); pass --seeded for three worked examples, one per type (fix / change / improve). The fastest way to experience the…

baskb/feedback-studio

Skill Claude CodeCodex

Turn a feedback round into a shareable review digest — what was asked, what changed (file:line), what was refused or left open and why — written to .feedback/REPORT.md, paste-ready for a PR description, commit message, or Slack update.

baskb/feedback-studio

Skill Claude CodeCodex

Close the loop after processing feedback — re-open the page and prove each resolved comment's change actually landed on the right element. Verified comments get a verdict reply on their thread; failed ones are reopened with an explanation instead of staying silently "resolved".

jnMetaCode/skillet

Skill Claude CodeCodex

Make the agent improve with every task — review the run, distill lessons into durable memory, and reinforce what worked. Use at the end of any non-trivial task, or when the user asks the agent to "learn from this".

Paydirt-AI/paydirt-mcp

Skill Claude CodeCodex

Install, configure, place, test, or inspect Paydirt feedback forms in an iOS app. Use for regular feedback, trial cancellation, subscription cancellation, Slack delivery, or raw feedback access.

Rabithua/FeedbackServerPlugin

Skill Claude CodeCodex

Administer FeedbackServer Products, subscription access, primary Product, publishable keys, account roles, audit records, and non-triage attachments. Use for tenant and Product administration; not installation, waitlists, routine feedback triage, or release publishing.

Rabithua/FeedbackServerPlugin

Skill Claude CodeCodex

List, inspect, search, annotate, update, archive, convert, or permanently delete the connected FeedbackServer administrator's waitlist signups. Use for waitlist and early-access follow-up. Do not select a Product or use this for Product feedback.

Rabithua/FeedbackServerPlugin

Skill Claude CodeCodex

Install or upgrade FeedbackKit, establish host OAuth, authenticate an account by email or invitation, create the first Product, integrate the Apple SDK, or diagnose setup. Use for first-use onboarding, unbound connections, connection failures, or setup status; not routine feedback triage.