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 ur-grue/autopunk-media-skills --skill audience-feedback-summarisergit clone --depth 1 https://github.com/ur-grue/autopunk-media-skillsWrote 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/ur-grue/autopunk-media-skills/audience-feedback-summariser)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/audience-feedback-summariser"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/audience-feedback-summariser/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/ur-grue/autopunk-media-skills/audience-feedback-summariser"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/audience-feedback-summariser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00046 | $0.01692 |
| Opus 5 | $0.00023 | $0.00846 |
| Sonnet 5 | $0.00009 | $0.00338 |
| Haiku 4.5 | $0.00005 | $0.00169 |
Grade A, and why
audience-feedback-summariser 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 12d ago.
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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audience Feedback Summariser
What This Skill Does
Reads a batch of raw audience comments, emails, or survey responses about a piece of content and produces a structured summary of what readers valued, what confused them, and what they want more of.
When To Use This Skill
- After a story, episode, or video has been live for 48–72 hours and comments have accumulated
- Before a follow-up piece, to understand what questions the original left unanswered
- When an editor needs to report audience sentiment to a commissioning team or sponsor
- After a newsletter campaign, to assess reader reaction before the next issue
What You Need To Provide
Required: A block of raw feedback — comments copied from a platform, email replies pasted together, or survey free-text responses. Minimum 10 responses for meaningful patterns; 30 or more is ideal. Optional: The original headline and a one-sentence description of the content the feedback refers to. The platform the feedback came from (comments section, email, social media, survey). Any specific question you want the summary to answer (e.g. "Did readers understand the data visualisation?").
How the Assistant Approaches This
- Reads all feedback as a single corpus, ignoring obvious spam or off-topic replies, and identifies recurring themes — both positive and critical.
- Groups themes by type: what landed well, what confused or frustrated readers, what follow-up questions they raised, and any notable emotional responses (strong praise, strong anger, surprise).
- Produces a structured summary with counts or proportions where the volume of feedback supports it, and flags any individual comments that are outliers or particularly quotable.
Output Format
A short briefing document of 300–500 words, structured under four headings: What Worked, What Confused or Frustrated, Follow-Up Questions Readers Are Asking, and Standout Responses. Written in plain editorial language — suitable for sharing with a commissioning editor, not a data analyst. No jargon. Bullet points under each heading, with one or two direct quotes from the feedback where they are illustrative.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 123 lines · 46 tokens per session scan A baf3d75c4e42
audience-feedback-summariser is a skill published in the GitHub repository ur-grue/autopunk-media-skills (32 stars, last pushed 12d ago), licensed MIT. It adds 46 tokens to every session and 1,692 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
Other skills, from other repositories
xiaoyuzhou-podcast-notes
A workflow that turns a public Xiaoyuzhou FM podcast episode into structured Markdown notes and a saved transcript. Xiaoyuzhou FM is a Chinese podcast platform.
c-research
Summarize web URLs, PDFs, YouTube videos, and podcasts using the summarize CLI. Instantly extract key points from any content type without manual reading. Useful for research, link digests, and media review.
transcript-ingestion
Transcript ingestion authority — capture, normalize, and prioritize transcripts from YouTube videos, podcast pages, captions, show notes, and transcript-like page content for persona systems, RAG pipelines, and grounded synthesis.
interactive-html
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…
feedback-prioritizer
Triages a backlog of raw customer feedback into a ranked list of opportunities scored on reach, severity, strategic fit, and confidence. Outputs a prioritized list with explicit "do not act" callouts for vocal-minority signals. Use when: triage feedback, prioritize feature requests, customer feedback backlog, what…
youtube-seo-competitor
Advanced YouTube competitor intelligence. Detects direct competitors, extracts winning title/thumbnail/hook patterns from transcripts, infers retention strategies from pacing, correlates posting cadence with performance, and identifies format-market-fit gaps. Use when user says "YouTube competitor analysis", "what are…