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 interview-transcript-editorgit 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/interview-transcript-editor)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/interview-transcript-editor"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/interview-transcript-editor/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/interview-transcript-editor"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/interview-transcript-editor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Memory Poisoning · line 250 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 | $0.00070 | $0.09348 |
| Opus 5 | $0.00035 | $0.04674 |
| Sonnet 5 | $0.00014 | $0.01870 |
| Haiku 4.5 | $0.00007 | $0.00935 |
Grade A, and why
interview-transcript-editor 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 10d 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 — 496 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interview Transcript Editor
What This Skill Does
Edits raw interview transcripts for publication — from minimal cleanup through full restructuring — across six distinct editing modes, each with its own standards for what to cut, what to keep, and how far to reshape the subject's words. Covers the full range of editorial work that happens between a recorded conversation and a published piece.
When To Use This Skill
- You have a raw transcript and need it publication-ready in any format (print, web, broadcast, podcast)
- You need to tighten a 60-minute conversation into a 1,500-word Q&A without losing the subject's voice
- You are editing someone else's interview and need a consistent, defensible editorial standard
- You need to combine material from two or more interviews with the same subject into one coherent piece
- You want to extract the strongest quotes for sidebars, social media, or promotional copy
- You need a fact-check pass that flags every verifiable claim in the transcript before publication
- You are producing a broadcast segment and need the transcript reshaped for spoken delivery
- Your subject has approval rights and you need transparent editorial notes explaining every change
What You Need To Provide
For any editing mode
Required: The raw transcript (or the section you want edited); the editing mode (verbatim cleanup, print Q&A, broadcast-ready, composite, fact-check pass, or pull-quote extraction); the publication format and outlet type (magazine, newspaper, radio, podcast, web, social) Optional: Target word count or airtime; the publication's house style; which sections are must-keep material; the subject's identity type (see Subject Type table below); whether the subject has approval rights; whether any portion was off-the-record; the interviewer's notes about tone, context, or intent behind specific questions
For composite edits specifically
Required: All transcripts to be combined (minimum two); a note on which interview was conducted first (chronological context matters); whether the subject knew their answers from different sessions would be combined Optional: Which topics overlap between interviews; any contradictions between sessions that need flagging
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.
- 10d ago First seen · 496 lines · 70 tokens per session scan A 91c5344cfa0b
interview-transcript-editor is a skill published in the GitHub repository ur-grue/autopunk-media-skills (32 stars, last pushed 13d ago), licensed MIT. It adds 70 tokens to every session and 9,348 once invoked, about $0.0003 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 2026-09-04.
Other skills, from other repositories
anti-defensive-writing
Reduce defensive writing in drafts and revisions by removing unnecessary caveats, disclaimers, hedges, apology-like framing, negative self-limiting statements, and over-explanations while preserving necessary scope, accuracy, safety, legal, ethical, and methodological limits. Use when drafting or revising academic…
revising-and-editing
Teaches the distinct disciplines of revising (rethinking content and structure) and editing (refining sentences and word choices), with a concrete three-draft evolution showing how a mediocre memo transforms into an excellent one. Covers revision checklists, editing checklists, and the peer feedback process. Use when…
dia-guide
Guides users through the V-Model workflow: takes stock of the project state, recommends the next phase skill, audits handoff state, and runs the Closing Handoff after a green security audit. Explicit user command for "where do I start", "what comes next", "wo bin ich gerade", "was kommt jetzt". Never for individual…
voice-update
Update context/voice-and-style.md or context/about-me.md from one of three sources. Manual (user dictates a single new rule, sample, or career fact). Memory (batch pull from Claude Code's auto-memory in /.claude/projects/ /memory/). Sent-mail (analyze the last 20-50 sent Gmail messages and propose updates from…
requirements-engineering
Transforms business analyses into epics, features, and tech-agnostic success criteria; creates the architect handoff. Use when the user mentions "Requirements", "RE", "Define Features", "Create Epics", "User Stories", "Success Criteria", "NFRs", "ASRs", "Acceptance Criteria", or when a BA exists and needs…
security-audit
Formal full-codebase security audit producing a written report with prioritized findings: SAST, OWASP (incl. LLM Top 10), SCA, supply chain, Zero Trust. Trigger ONLY on explicit requests like "security audit", "OWASP audit", "Sicherheitsaudit", "dependency audit". NOT for PR-level checks, one-off questions, or generic…