Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add joao-aires/agent-skills-public --skill learn-from-product-feedbackgit clone --depth 1 https://github.com/joao-aires/agent-skills-publicWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/joao-aires/agent-skills-public/learn-from-product-feedback)<a href="https://agentmods.dev/skills/joao-aires/agent-skills-public/learn-from-product-feedback"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/learn-from-product-feedback/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/joao-aires/agent-skills-public/learn-from-product-feedback"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/learn-from-product-feedback.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00054 | $0.00956 |
| Opus 5.5 | $0.00022 | $0.00382 |
| Sonnet 5.5 | $0.00011 | $0.00191 |
| Haiku 4.5 | $0.00005 | $0.00096 |
Grade A, and why
learn-from-product-feedback scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Learn from product feedback
Read composition guidance for optional expertise, fallback and scope.
Ask a decision question
Start with the intended user outcome and the decision this evidence should inform: improve an interaction, investigate a problem, continue an experiment, change scope or stop. Read the product's assumptions and existing feedback. A shipped feature is an output; whether people can achieve the intended outcome is the question. Keep the activity small enough to change a real decision.
Use available evidence before adding tools: support reports, user-provided interviews, usability observations, reviews and existing usage data.
- Identify source, period, segment and collection limitations.
- Analyze only data the project is authorized to access.
- Sending questionnaires, contacting users, adding tracking or running experiments requires a request that includes that activity.
Combine what users say and do
| Evidence | Helps explain | Interpretation limit |
|---|---|---|
| Qualitative feedback | Context and friction | The loudest customer or an AI-generated sentiment score does not establish a representative population. |
| Quantitative usage | Prevalence and outcomes | Check missing events, definitions and selection bias before interpreting the population. |
Group repeated reports by underlying problem, preserve representative evidence, deduplicate repeated contacts and distinguish people/accounts from mentions.
Choose a small number of meaningful measures when data exists: reaching the intended outcome, drop-off between relevant steps, repeat use or retention.
- State denominator, time window, segment and event definitions.
- Check missing events and selection bias before interpreting a funnel.
- Counts of page views or feature clicks alone do not prove usefulness.
For a saved-search feature, ask whether users can save and later reuse a search. Compare available save/reopen behavior with reports of confusing names, missing searches or poor discoverability. If only a few users exist, examining their journeys and asking focused usability questions can be more useful than proposing an underpowered A/B test.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday Changed · +17 lines c7312510bfb8
- 2d ago Changed · +2 lines 655c739d7832
- 7d ago Changed · +1 lines 49af698269ef
- 10d ago Changed · +6 lines 825319dffea6
- 11d ago First seen · 35 lines · 54 tokens per session scan A 0aa58f6b6361
learn-from-product-feedback is a skill published in the GitHub repository joao-aires/agent-skills-public (2 stars, last pushed yesterday), licensed MIT. It adds 54 tokens to every session and 956 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-11.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…