Platform Engineering
sickn33/agentic-awesome-skills
Build internal developer platforms (IDPs) with self-service infrastructure, golden paths, and developer portals using Backstage, Crossplane, and score.
Guides audio mastering for streaming platforms including loudness optimization and tonal balance.
$ npx skills add bitwize-music-studio/claude-ai-music-skills --skill mastering-engineer -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install bitwize-music-studio/claude-ai-music-skills mastering-engineer --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/bitwize-music-studio/claude-ai-music-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/mastering-engineer .claude/skills/mastering-engineer && 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 "mastering-engineer" agent skill from https://github.com/bitwize-music-studio/claude-ai-music-skills/tree/main/skills/mastering-engineer into .claude/skills/mastering-engineer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mastering-engineer", 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/bitwize-music-studio/claude-ai-music-skills/tree/main/skills/mastering-engineerType 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 bitwize-music-studio/claude-ai-music-skills --skill mastering-engineer -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install bitwize-music-studio/claude-ai-music-skills mastering-engineer --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bitwize-music-studio/claude-ai-music-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/mastering-engineer .agents/skills/mastering-engineer && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "mastering-engineer" agent skill from https://github.com/bitwize-music-studio/claude-ai-music-skills/tree/main/skills/mastering-engineer into .agents/skills/mastering-engineer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mastering-engineer", 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 bitwize-music-studio/claude-ai-music-skills --skill mastering-engineer -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install bitwize-music-studio/claude-ai-music-skills mastering-engineer --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bitwize-music-studio/claude-ai-music-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/mastering-engineer .cursor/skills/mastering-engineer && 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 "mastering-engineer" agent skill from https://github.com/bitwize-music-studio/claude-ai-music-skills/tree/main/skills/mastering-engineer into .cursor/skills/mastering-engineer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mastering-engineer", 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/bitwize-music-studio/claude-ai-music-skills.git --path skills/mastering-engineer--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 bitwize-music-studio/claude-ai-music-skills --skill mastering-engineer -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install bitwize-music-studio/claude-ai-music-skills mastering-engineer --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bitwize-music-studio/claude-ai-music-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/mastering-engineer .gemini/skills/mastering-engineer && 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 "mastering-engineer" agent skill from https://github.com/bitwize-music-studio/claude-ai-music-skills/tree/main/skills/mastering-engineer into .gemini/skills/mastering-engineer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mastering-engineer", 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 bitwize-music-studio/claude-ai-music-skills mastering-engineerInstalls 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 bitwize-music-studio/claude-ai-music-skills --skill mastering-engineer -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/bitwize-music-studio/claude-ai-music-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/mastering-engineer .github/skills/mastering-engineer && 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 "mastering-engineer" agent skill from https://github.com/bitwize-music-studio/claude-ai-music-skills/tree/main/skills/mastering-engineer into .github/skills/mastering-engineer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mastering-engineer", 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 bitwize-music-studio/claude-ai-music-skills --skill mastering-engineer -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install bitwize-music-studio/claude-ai-music-skills mastering-engineer --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bitwize-music-studio/claude-ai-music-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/mastering-engineer .opencode/skills/mastering-engineer && 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 "mastering-engineer" agent skill from https://github.com/bitwize-music-studio/claude-ai-music-skills/tree/main/skills/mastering-engineer into .opencode/skills/mastering-engineer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mastering-engineer", 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.
mastering-engineerGuides audio mastering for streaming platforms including loudness optimization and tonal balance.
Mastering Engineer is an agent skill from bitwize-music-studio/claude-ai-music-skills. Guides audio mastering for streaming platforms including loudness optimization and tonal balance. Use when the user has approved tracks and wants to master audio files.
Its SKILL.md is about 3.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `genre-presets.md`).
The repository describes itself as: Human + AI music production workflow for Suno - skills, templates, and tools. The licence is CC0-1.0.
9 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 58f32c2. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
ReadEditWriteGrepGlobBashbitwize-music-mcpFrom allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
python3From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Mastering Engineer loads about 3.9k tokens when it runs. Until then it costs about 47 tokens; SKILL.md has 1,524 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.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
allowed-tools: Read, Edit, Write, Grep, Glob, Bash, bitwize-music-mcpAutomated 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.
The full file from bitwize-music-studio/claude-ai-music-skills at commit 58f32c2, republished under its CC0-1.0 licence (© bitwize-music-studio). 1,524 words, ~3,856 tokens.
.claude/skills/mastering-engineer/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.Input: $ARGUMENTS
When invoked with a folder:
When invoked for guidance:
You are an audio mastering specialist for AI-generated music. You guide loudness optimization, platform delivery standards, and final audio preparation.
Your role: Mastering guidance, quality control, platform optimization
Not your role: Audio editing (trimming, fades), mixing, creative production
Master to -14 LUFS, -1.0 dBTP = works everywhere
For streaming: -14 LUFS works across all genres
See genre-presets.md for detailed genre settings.
Mastering is loudness, dynamics and tonal balance. Suno's Terms of Service (effective 2026-09-03) prohibit removing, altering, obscuring or circumventing the fingerprint, watermark or metadata Suno appends to an output. No step in this workflow does that, and no step may be described that way.
Check for custom mastering presets:
load_override("mastering-presets.yaml") — returns override content if found (auto-resolves path from config){overrides}/mastering-presets.yaml:
# Custom Mastering Presets
genres:
dark-electronic:
cut_highmid: -3 # More aggressive cut
target_lufs: -12 # Louder master
compress_ratio: 2.0 # Heavier compression
compress_attack: 15.0 # Faster attack
ambient:
cut_highmid: -1 # Gentle cut
target_lufs: -16 # Quieter, more dynamic
compress_ratio: 1.2 # Very light compression
defaults:
dither_bits: 24 # 24-bit output for archivalAvailable preset fields:
| Category | Fields |
|---|---|
| Loudness | target_lufs, target_lra |
| EQ cuts | cut_highmid, cut_highs |
| EQ high-mid | eq_highmid_freq, eq_highmid_q |
| EQ highs | eq_highs_freq, eq_highs_q |
| EQ low shelf | eq_low_freq, eq_low_gain, eq_low_q |
| EQ sub-bass | eq_sub_cut_freq |
| EQ options | eq_linear_phase |
| Compression | compress_ratio, compress_threshold, compress_attack, compress_release, compress_mix, compress_makeup |
| Multiband | multiband_enabled, multiband_low_crossover, multiband_high_crossover, multiband_low_ratio, multiband_mid_ratio, multiband_high_ratio, multiband_low_threshold, multiband_mid_threshold, multiband_high_threshold |
| Mid/side EQ | midside_low_gain, midside_low_freq, midside_high_gain, midside_high_freq |
| Stereo | stereo_width, stereo_bass_mono_freq |
| De-essing | deess_enabled, deess_freq, deess_bandwidth, deess_threshold, deess_ratio |
| Limiting | limiter_lookahead_ms, limiter_release_ms |
| Processing | dc_filter_freq, processing_oversample |
| Output | output_bits, dither_bits, output_sample_rate, track_gap |
Example:
Before mastering, resolve audio path via MCP:
resolve_path("audio", album_slug) — returns the full audio directory pathExample: For album "my-album", returns ~/bitwize-music/audio/artists/bitwize/albums/electronic/my-album/.
Do not use placeholder paths or assume audio locations — always resolve via MCP.
Before mastering, verify:
resolve_path("audio", album_slug) to confirm.wav file in the folderdelivery_sample_rate asks for it.Before analyzing or mastering, confirm genre settings with the user:
find_album(album_slug) to get the genre from album statePer-track override workflow:
master_audio again with the different genre
and copying the re-mastered output over the previous version in mastered/analyze_audio(album_slug)What to check:
Red flags:
Run technical QC before mastering to catch source issues, and after to verify mastered output:
# Pre-mastering: check raw files
qc_audio(album_slug, "")
# Post-mastering: check mastered output
qc_audio(album_slug, "mastered")7 checks: mono compatibility, phase correlation, clipping, clicks/pops, silence, format validation, spectral balance.
Blocking issues (FAIL): Out-of-phase audio, clipping regions, internal silence gaps, wrong format/sample rate, major spectral holes. Fix these before proceeding.
Warnings (WARN): Weak mono fold, minor spectral imbalance, trailing silence. Note in mastering report but don't block.
Include QC verdicts in the mastering report handoff (see "Handoff to Release Director" section).
Use the master_album MCP tool to run Steps 2–7 in a single call:
master_album(album_slug, genre="country", cut_highmid=-2.0)This executes: analyze → pre-QC → master → verify → post-QC → update statuses. Stops on any failure and returns per-stage results. Use individual steps below only when manual intervention is needed between stages.
Note: master_album applies one genre to all tracks. If Step 1.5 identified per-track genre overrides, use the manual step-by-step workflow instead — master the main batch first, then re-master override tracks individually with the different genre.
Standard (most cases):
master_audio(album_slug, cut_highmid=-2.0)Genre-specific:
master_audio(album_slug, genre="country")Reference-based (advanced):
master_with_reference(album_slug, reference_filename="reference.wav")master_audio(album_slug, cut_highmid=-2.0, dry_run=True)Shows what will happen without modifying files.
master_audio(album_slug, cut_highmid=-2.0)Creates mastered/ subdirectory in audio folder with processed files.
# Analyze the mastered output
analyze_audio(album_slug, subfolder="mastered")Quality check:
If a track has excessive dynamic range and won't reach target LUFS:
fix_dynamic_track(album_slug, track_filename="05-problem-track.wav")mastering_samples/)After verification, master_album writes operator-listening artifacts to a
sibling directory so mastered/ stays byte-identical to what gets uploaded
to streaming platforms:
{audio_root}/.../[album]/
├── mastered/ # Final masters — UPLOAD THIS
│ ├── 01-track.wav
│ └── ...
└── mastering_samples/ # Operator QA only — DO NOT UPLOAD
├── 01-track.aac.m4a # 128 kbps AAC for Bluetooth listening
├── 01-track.mono.wav # Mono fold-down sample
└── 01-track.MONO_FOLD.md # Per-band delta report + verdictTwo automated checks run here:
.mono.wav on a phone speaker or single Echo
to confirm which elements disappear in mono playback.Standalone tools (run independently of the full pipeline):
render_codec_preview(album_slug) # writes .aac.m4a files
mono_fold_check(album_slug) # writes .MONO_FOLD.md + .mono.wavRe-run cleanup (regenerable artifacts):
reset_mastering(album_slug, subfolders=["mastering_samples"], dry_run=False)Configurable thresholds live in tools/mastering/genre-presets.yaml
under defaults: (mono_fold_band_drop_fail_db, etc.) — override per-user
in ~/.bitwize-music/overrides/mastering-presets.yaml.
All mastering operations are available as MCP tools. Use these instead of running Python scripts via bash.
| MCP Tool | Purpose |
|---|---|
analyze_audio | Measure LUFS, true peak, dynamic range |
qc_audio | Technical QC (mono, phase, clipping, clicks, silence, format, spectral) |
master_audio | Master tracks to target LUFS with EQ options |
master_with_reference | Match mastering to a reference track |
fix_dynamic_track | Fix tracks with extreme dynamic range |
master_album | End-to-end pipeline — all steps in one call |
render_codec_preview | Render 128 kbps AAC previews to mastering_samples/ |
mono_fold_check | Mono fold-down QC: per-band deltas, sample audio, MD report |
Suno outputs vary in loudness - some at -8 LUFS, some at -18 LUFS.
Master when:
Don't distribute until:
Test on:
Wrong:
python3 "$PLUGIN_DIR/tools/mastering/analyze_tracks.py" ~/audio/my-albumRight:
analyze_audio("my-album")Why it matters: Bash hits system Python which lacks dependencies. MCP tools run inside the venv automatically.
Wrong:
analyze_audio("my-album") # Checks originals, not mastered outputRight:
analyze_audio("my-album", subfolder="mastered")Why it matters: master_audio creates a mastered/ subdirectory. Verify that output, not the originals.
Wrong:
master_audio("my-album", cut_highmid=-3.0) # Writes files immediatelyRight:
master_audio("my-album", cut_highmid=-3.0, dry_run=True) # Preview first
master_audio("my-album", cut_highmid=-3.0) # Then commitWhy it matters: Dry run shows gain changes without writing files. Catches bad settings before they hit disk.
After all tracks mastered and verified:
## Mastering Complete - Ready for Release
**Album**: [Album Name]
**Mastered Files Location**: [path to mastered/ directory]
**Track Count**: [N]
**Mastering Report**:
- All tracks: -14.0 LUFS ± 0.5 dB ✓
- True peak: < -1.0 dBTP on all tracks ✓
- Album consistency: [X] dB range (< 1 dB) ✓
- No clipping or distortion ✓
**Next Step**: release-director can begin pre-release QAload_override("mastering-presets.yaml") at invocationYour deliverable: Mastered WAV files at consistent loudness, optimized for streaming (with user preferences applied) → release-director handles release workflow.
© bitwize-music-studio, CC0-1.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file in skills/mastering-engineer of bitwize-music-studio/claude-ai-music-skills.
Open the folder on GitHubat commit 58f32c2
Mastering Engineer 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 |
|---|---|---|---|---|---|---|
| Mastering Engineer this skillbitwize-music-studio/claude-ai-music-skills | 540 | — | ~3.9k | Automated safety check: Notes | CC0-1.0 | |
| Platform Engineeringsickn33/agentic-awesome-skills | 47k | 2 repos | ~2.6k | Automated safety check: Pass | MIT | |
| Llmops Platform Engineeringsickn33/agentic-awesome-skills | 47k | 2 repos | ~3.5k | Automated safety check: Pass | MIT | |
| Agent Platform RAG Engine Managementgoogle/skills | 21k | — | ~2.4k | Automated safety check: Pass | Apache-2.0 | |
| AI Engineering Course Guiderohitg00/ai-engineering-from-scratch | 66k | — | ~1.7k | Automated safety check: Pass | MIT | |
| Platform Engineeringancoleman/ai-design-components | 526 | — | ~4.3k | Automated safety check: Pass | MIT |
sickn33/agentic-awesome-skills
Build internal developer platforms (IDPs) with self-service infrastructure, golden paths, and developer portals using Backstage, Crossplane, and score.
sickn33/agentic-awesome-skills
Build production LLMOps platforms with CI/CD, model promotion workflows, evaluation gates, rollback, and governance across cloud and self-hosted inference.
google/skills
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK.
rohitg00/ai-engineering-from-scratch
Routes a topic, question or bug to the exact lessons in the AI Engineering from Scratch curriculum and suggests the next command to run.
ancoleman/ai-design-components
Design and implement Internal Developer Platforms (IDPs) with self-service capabilities, golden paths, and developer experience optimization.
davila7/claude-code-templates
Expert guide on prompt engineering patterns, best practices, and optimization techniques.
bitwize-music-studio/claude-ai-music-skills
Designs album concepts, tracklist architecture, and thematic planning through 7 structured phases.
bitwize-music-studio/claude-ai-music-skills
Shows a structured progress dashboard for an album with percentage complete per phase, blocking items, and status breakdown.
bitwize-music-studio/claude-ai-music-skills
Tracks and manages album ideas including brainstorming, planning, and status updates.
bitwize-music-studio/claude-ai-music-skills
Copies track content (lyrics, style prompts, streaming lyrics) to the system clipboard.
bitwize-music-studio/claude-ai-music-skills
Uploads promo videos and content to Cloudflare R2 or AWS S3.
bitwize-music-studio/claude-ai-music-skills
Sets up or edits the plugin configuration file interactively.
Guides audio mastering for streaming platforms including loudness optimization and tonal balance. Mastering Engineer is an agent skill from bitwize-music-studio/claude-ai-music-skills. Guides audio mastering for streaming platforms including loudness optimization and tonal balance.
Mastering Engineer fits situations like: the user has approved tracks and wants to master audio files.
Run `npx skills add bitwize-music-studio/claude-ai-music-skills --skill mastering-engineer -a claude-code`. Or copy the skill folder (skills/mastering-engineer in bitwize-music-studio/claude-ai-music-skills) into .claude/skills/mastering-engineer in your project. Claude Code loads it when a task matches its description.
Run `npx skills add bitwize-music-studio/claude-ai-music-skills --skill mastering-engineer -a codex`. Or copy the skill folder (skills/mastering-engineer in bitwize-music-studio/claude-ai-music-skills) into .agents/skills/mastering-engineer in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add bitwize-music-studio/claude-ai-music-skills --skill mastering-engineer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mastering-engineer, .gemini/skills/mastering-engineer, .github/skills/mastering-engineer and .opencode/skills/mastering-engineer in your project.
Going by SKILL.md and its folder, Mastering Engineer needs the command-line tools its instructions call (python3). Our summary lists: Python 3. Its frontmatter pre-approves these tools: Read, Edit, Write, Grep, Glob, Bash, bitwize-music-mcp.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
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.
Mastering Engineer is published under the CC0-1.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.9k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Mastering Engineer: Platform Engineering (sickn33/agentic-awesome-skills, 47k stars), Llmops Platform Engineering (sickn33/agentic-awesome-skills, 47k stars), Agent Platform RAG Engine Management (google/skills, 21k stars) and AI Engineering Course Guide (rohitg00/ai-engineering-from-scratch, 66k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
bitwize-music-studio (a GitHub organization) maintains it in bitwize-music-studio/claude-ai-music-skills, which has 540 GitHub stars. The repository holds 51 skills in this directory. The repository was last updated on October 7, 2026.
Source: bitwize-music-studio/claude-ai-music-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.