Vlog Auto Edit
znyupup/ai-video-editing-skill
AI Agent自动剪辑旅行Vlog的完整工作流。从原始素材到成品视频，系统级只需ffmpeg，其余在Python venv内完成。by nyx研究所 (GitHub @znyupup · B站/小红书 @nyx研究所)
Diagnose and tune erm's output quality. An agent skill from dougcalobrisi/erm.
Install Erm Tune
$ npx skills add dougcalobrisi/erm --skill erm-tune -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install dougcalobrisi/erm erm-tune --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/dougcalobrisi/erm.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/erm-tune .claude/skills/erm-tune && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "erm-tune" agent skill from https://github.com/dougcalobrisi/erm/tree/main/skills/erm-tune into .claude/skills/erm-tune/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "erm-tune", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/dougcalobrisi/erm/tree/main/skills/erm-tuneType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add dougcalobrisi/erm --skill erm-tune -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install dougcalobrisi/erm erm-tune --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dougcalobrisi/erm.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/erm-tune .agents/skills/erm-tune && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "erm-tune" agent skill from https://github.com/dougcalobrisi/erm/tree/main/skills/erm-tune into .agents/skills/erm-tune/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "erm-tune", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add dougcalobrisi/erm --skill erm-tune -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install dougcalobrisi/erm erm-tune --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dougcalobrisi/erm.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/erm-tune .cursor/skills/erm-tune && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "erm-tune" agent skill from https://github.com/dougcalobrisi/erm/tree/main/skills/erm-tune into .cursor/skills/erm-tune/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "erm-tune", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/dougcalobrisi/erm.git --path skills/erm-tune--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add dougcalobrisi/erm --skill erm-tune -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install dougcalobrisi/erm erm-tune --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dougcalobrisi/erm.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/erm-tune .gemini/skills/erm-tune && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "erm-tune" agent skill from https://github.com/dougcalobrisi/erm/tree/main/skills/erm-tune into .gemini/skills/erm-tune/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "erm-tune", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install dougcalobrisi/erm erm-tuneInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add dougcalobrisi/erm --skill erm-tune -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/dougcalobrisi/erm.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/erm-tune .github/skills/erm-tune && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "erm-tune" agent skill from https://github.com/dougcalobrisi/erm/tree/main/skills/erm-tune into .github/skills/erm-tune/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "erm-tune", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add dougcalobrisi/erm --skill erm-tune -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install dougcalobrisi/erm erm-tune --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dougcalobrisi/erm.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/erm-tune .opencode/skills/erm-tune && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "erm-tune" agent skill from https://github.com/dougcalobrisi/erm/tree/main/skills/erm-tune into .opencode/skills/erm-tune/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "erm-tune", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
erm-tune- GitHub stars
- 112
- Token cost
- ~1k tokens
- SKILL.md length
- 407 words
- Files
- 1
- Skills in repo
- 2
- Repo updated
- First seen
- Licence
- MIT
At a glance
Diagnose and tune erm's output quality. An agent skill from dougcalobrisi/erm.
- Works in 3 steps: Diagnose first — ask what's wrong → The five knob clusters → Iterate safely
- An erm run is imperfect
- SKILL.md covers Resolving documentation, 1. Diagnose first — ask what's…, 2. The five knob clusters and 3. Iterate safely
- Calls uvx
What it does
Erm Tune is an agent skill from dougcalobrisi/erm. Diagnose and tune erm's output quality. Use when an erm run is imperfect or the user wants to adjust settings — fillers still audible, real words clipped, splices click or sound smeared/blurry, noise floor pumps or is audible, words run together, detection too aggressive or missing fillers, or questions about crossfade, pause spacing, denoise, room tone, models, or detection thresholds. For first-time install or a basic clean, use the erm skill instead.
Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Media & Creative. It works with FFmpeg and Python. The repository describes itself as: Local CLI that strips disfluencies (um, uh, er, erm, ah, hmm, mhm, mm, uh-huh, etc) from recordings of English speech. The licence is MIT.
When your agent uses it
- An erm run is imperfect
- The user wants to adjust settings — fillers still audible
- Real words clipped
- Sound smeared/blurry
Example prompts
- “/erm-tune”
Requirements
- Pre-approved tools (allowed-tools): Bash, Read, AskUserQuestion
Workflow steps
3 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit af2fe92. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
BashReadAskUserQuestion
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
uvx
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
doug.sh
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Erm Tune loads about 1k tokens when it runs. Until then it costs about 117 tokens; SKILL.md has 407 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
allowed-tools: Bash, Read, AskUserQuestion
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from dougcalobrisi/erm at commit af2fe92, republished under its MIT licence (© dougcalobrisi). 407 words, ~1,006 tokens.
Download SKILL.mdSave it as
.claude/skills/erm-tune/SKILL.md (or your agent's skills folder).- name
- erm-tune
- description
- Diagnose and tune erm's output quality. Use when an erm run is imperfect or the user wants to adjust settings — fillers still audible, real words clipped, splices click or sound smeared/blurry, noise floor pumps or is audible, words run together, detection too aggressive or missing fillers, or questions about crossfade, pause spacing, denoise, room tone, models, or detection thresholds. For first-time install or a basic clean, use the erm skill instead.
- allowed-tools
- Bash, Read, AskUserQuestion
erm — tune and troubleshoot
erm exposes ~30 flags that cluster into five knob groups. Tune by symptom,
change one cluster at a time, and re-check with --dry-run + validate.
Launcher convention. This skill assumes erm is already runnable (set up by the
erm skill). In the commands below, erm means that launcher: uvx erm … if you
ran it via uv, or plain erm … after activating the venv where it's installed.
Resolving documentation
Resolve detail in this order (broadest compatibility last):
erm --help— definitive flag names, defaults, and units.- Public docs: https://doug.sh/docs/erm/ —
troubleshooting,detection,render-pipeline,denoise-and-room-tone. - Bundled docs (Claude plugin only):
${CLAUDE_PLUGIN_ROOT}/docs/*.md; flag defaults in${CLAUDE_PLUGIN_ROOT}/src/erm/cli.py.
Never guess values — read one of the above before recommending a setting.
1. Diagnose first — ask what's wrong
Use AskUserQuestion to pin the symptom (each maps to a different cluster), unless the user already described it:
- Fillers still audible / missed → detection
- A specific word should also be cut, or a default word is over-matching →
detection word list (
--add-fillers/--remove-fillers) - Real words clipped or chopped → detection (too aggressive) / refinement
- Splices click, pop, or sound smeared/blurry → crossfade / refinement
- Noise floor pumps, audible level changes at edits → denoise / room tone
- Words run together with no breath → splice spacing
- Too slow → detection (
--model/--device)
Then read the troubleshooting doc for the symptom→knob fix.
Show full SKILL.md (192 more words)Show less
2. The five knob clusters
Read the linked doc page for good-value ranges before changing anything.
- Detection aggressiveness (what gets cut) —
--model(biggest lever),--detect-gaps,--confirm-pitch,--gap-min-ms,--gap-min-voiced-ms,--gap-max-voiced-ms,--intraword-min-ms,--fillers. →detectiondoc.- Word list (pass 1):
--add-fillers "word,word"adds words on top of the defaults;--remove-fillers "word"drops a default that over-matches (removal wins). Prefer these over--fillers, which replaces the whole set.
- Word list (pass 1):
- Refinement / merge (clean splice points) —
--search-ms,--merge-gap-ms. →render-pipelinedoc. - Splice spacing (remove mode breathing room) —
--pad-pause-factor,--pad-min-ms,--pad-max-ms,--min-gap-ms. →render-pipelinedoc. - Crossfade (splice smoothness) —
--crossfade-factor,--min-crossfade-ms,--max-crossfade-ms,--crossfade-ms. →render-pipelinedoc. - Denoise / room tone (uniform floor) —
--denoise none|pre|post|hybrid,--denoise-nr,--denoise-nf,--room-tone/--no-room-tone,--room-tone-level-db,--room-tone-source. →denoise-and-room-tonedoc.
3. Iterate safely
- Tune detection against the cut list first:
erm IN.wav --dry-runand inspect the JSON — cheaper than re-rendering audio. - Change one cluster, re-render, and
erm validate IN.wav OUT.wav. - Compare against the previous output before changing anything else.
Optional: parallel A/B (enhancement)
When several settings are plausible, you may render a few variants with different
knob values in parallel, validate each, and compare — instead of serial
guess-and-check. Keep variants labeled by the flag that changed.
© dougcalobrisi, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/erm-tune of dougcalobrisi/erm.
Open the folder on GitHubat commit af2fe92
Compare with similar skills
Erm Tune next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Erm Tune this skilldougcalobrisi/erm | 112 | — | ~1k | Automated safety check: Notes | MIT | |
| Vlog Auto Editznyupup/ai-video-editing-skill | 150 | — | ~6.8k | Automated safety check: Pass | MIT | |
| Watchmathiaschu/watch | 142 | — | ~4k | Automated safety check: Warn | MIT | |
| Render Myth Vs Factgooseworks-ai/goose-skills | 1.2k | — | ~2.2k | Automated safety check: Pass | MIT | |
| Watch Video Q&Abradautomates/claude-video | 18k | — | ~4.3k | Automated safety check: Notes | MIT | |
| Vox DirectorAlisa0808/vox-director | 2.2k | — | ~5.6k | Automated safety check: Pass | MIT |
Similar skills
Watch
mathiaschu/watch
Watch a video from YouTube, Instagram, X/Twitter, Vimeo, TikTok or any of ~1800 yt-dlp sites (or a local path).
Render Myth Vs Fact
gooseworks-ai/goose-skills
Assemble a myth-vs-fact kinetic-typography explainer video ad (≈29.5s, 9:16) from N myth/fact pairs + hook / turn / punch copy + palette + a brand end-card PNG + a VO track — a hook, 3 red-strike…
Watch Video Q&A
bradautomates/claude-video
Lets the agent answer questions about a video from a URL or local file by downloading it, extracting frames and a transcript, or by sending it to Gemini's video model.
Vox Director
Alisa0808/vox-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all…
Youtube Clipper
op7418/Youtube-clipper-skill
YouTube 视频智能剪辑工具。下载视频和字幕，AI 分析生成精细章节（几分钟级别）， 用户选择片段后自动剪辑、翻译字幕为中英双语、烧录字幕到视频，并生成总结文案。
More from dougcalobrisi/erm
Erm
dougcalobrisi/erm
Install and run erm, the local CLI that removes filler words / disfluencies (um, uh, er, erm, ah, hmm, mhm, mm, uh-huh and elongations) from spoken-audio recordings.
Related
Categories
Questions about Erm Tune
What does Erm Tune do?
Diagnose and tune erm's output quality. An agent skill from dougcalobrisi/erm. Erm Tune is an agent skill from dougcalobrisi/erm. Diagnose and tune erm's output quality.
When should I use Erm Tune?
Erm Tune fits situations like: an erm run is imperfect; the user wants to adjust settings — fillers still audible; real words clipped; sound smeared/blurry.
How do I install Erm Tune in Claude Code?
Run `npx skills add dougcalobrisi/erm --skill erm-tune -a claude-code`. Or copy the skill folder (skills/erm-tune in dougcalobrisi/erm) into .claude/skills/erm-tune in your project. Claude Code loads it when a task matches its description.
How do I install Erm Tune in Codex?
Run `npx skills add dougcalobrisi/erm --skill erm-tune -a codex`. Or copy the skill folder (skills/erm-tune in dougcalobrisi/erm) into .agents/skills/erm-tune in your project. Codex loads it when a task matches its description.
Can I use Erm Tune in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add dougcalobrisi/erm --skill erm-tune -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/erm-tune, .gemini/skills/erm-tune, .github/skills/erm-tune and .opencode/skills/erm-tune in your project.
What does Erm Tune need to run?
Going by SKILL.md and its folder, Erm Tune needs the command-line tools its instructions call (uvx). Its frontmatter pre-approves these tools: Bash, Read, AskUserQuestion.
Does Erm Tune access the network?
SKILL.md names 1 domain. As links in the text: doug.sh. This is read from the text; nothing was executed.
Is Erm Tune safe to install?
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does Erm Tune use?
Erm Tune is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Erm Tune use?
About 1k tokens (SKILL.md is roughly 4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Erm Tune?
Skills that share tags, products or a category with Erm Tune: Vlog Auto Edit (znyupup/ai-video-editing-skill, 150 stars), Watch (mathiaschu/watch, 142 stars), Render Myth Vs Fact (gooseworks-ai/goose-skills, 1.2k stars) and Watch Video Q&A (bradautomates/claude-video, 18k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Erm Tune?
dougcalobrisi (a GitHub user) maintains it in dougcalobrisi/erm, which has 112 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on August 23, 2026.
Source: dougcalobrisi/erm on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.