footstep-eq-tuner
Skill0 starsChanged 24 days agoMITView on GitHub
EQ-Iteration fuer FootstepPro. Nimmt Analyzer-Output + aktuelle EQ-Config, schlaegt 1-3 minimale Pre-EQ/ReaXComp-Aenderungen vor mit erwarteter Score-Delta, inkl. Spatial-Hook-Sanity-Check. Nutze nach jedem v9.x-Test-Recording.
In this repository46 other files it gives its agents.
- a11y-checkSkill
- agent-createSkill
- branch-finishSkill
- changelog-updaterSkill
- code-doc-syncSkill
- codex-msgSkill
- codex-reviewSkill
- csoSkill
- db-exploreSkill
- deploy-preflightSkill
- deps-checkSkill
- design-htmlSkill
- design-shotgunSkill
- design-taste-frontendSkill
- finanzberaterSkill
- full-auditSkill
- gateSkill
- gemini-digestSkill
- graphifySkill
- handygame-botSkill
- hook-createSkill
- instructions-drift-checkSkill
- investigateSkill
- leanreaSkill
- legal-deSkill
- loopmodeSkill
- loopstopSkill
- lyraSkill
- office-hoursSkill
- plan-ceo-reviewSkill
- profileSkill
- python-env-auditSkill
- quick-reviewSkill
- reviewSkill
- security-auditSkill
- seoSkill
- site-anatomySkill
- skill-createSkill
- spatial-pipeline-helperSkill
- state-json-validatorSkill
- test-runSkill
- tool-scoutSkill
- transient-profile-validatorSkill
- ui-critiqueSkill
- wakeup-setupSkill
- websucheSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 32
Default: neueste Analyse aus output/cache/
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
FootstepPro EQ-Tuner
Du hilfst der Nutzer bei der iterativen EQ-Tuning-Schleife: Aufnahme analysieren, gezielt 1-3 Pre-EQ-/ReaXComp-Aenderungen vorschlagen, erwartete Score-Delta abschaetzen.
Vor dem Start
Datenbasis ist (Windows-lokal) — FootstepPro/FootstepAnalyzer liegt nur auf dem PC (EqualizerAPO-Setup, kein Syncthing-Sync, auf netcup nicht vorhanden):
- Aktuelle EQ-Config:
C:\Users\<user>\OneDrive\Dokumente\AudioSetup\FootstepAnalyzer\output\configs\AIW_BO7_v9.*.txt(Windows-lokal) - ReaXComp-Config:
C:\Users\<user>\OneDrive\Dokumente\AudioSetup\FootstepAnalyzer\output\configs\REAXCOMP_v9.*.txt(Windows-lokal) - Plan-Complete-Targets aus Plan v1.5:
- foot_wins ≥ 50%
- competitive_score ≥ 60
- spatial_health in [-3, -8] dB
- kf_ratio ≤ -10 dB
- surface_diversity ≥ 4/7
Workflow
1. Argument auswerten
- WAV-Pfad:
analyzer.py analyze --profile dt770 <wav>ausfuehren, JSON-Output lesen - JSON-Pfad: direkt lesen
- Default: neueste Analyse aus
output/cache/
2. Spatial-Hook-Sanity-Check (Plan v1.6 Pflicht)
Pruefe ob das Recording mit/ohne aktivem Spatial-Hook analysiert wurde:
metrics.json-> Feldersurface_diversity_bonus,voice_clarity_bonus,crate_masking_penalty,distance_balance_bonus- Wenn alle 4 == 0: Spatial-Hook war inaktiv (oder segments=None) -> Score ist v3-Niveau-konsistent
- Wenn aktiv: VORSICHT bei Score-Vergleich gegen v9.195/v9.200 falls H1 noch nicht gefixt (siehe
spatial-pipeline-helper)
3. Score-Delta-Analyse
Vergleiche gegen Vorgaenger (z.B. v9.195):
- Welche Targets noch NICHT erreicht?
- Welche Frequenz-Baender (B1-B12) brauchen Korrektur?
4. Empfehlung (max 3 Aenderungen)
Pro Aenderung:
- Welcher Filter (Pre-EQ Filter N oder ReaXComp Band X)
- Aktueller Wert -> neuer Wert
- Erwartete Score-Delta (qualitativ: +5%, neutral, -2%)
- Begruendung mit Vision-Tabellen-Bezug (z.B. "B7+B8 Schritt-Erhaltung -> KEIN Compressor")
5. Strategie-Hybrid 2+3+6+7 einhalten
- NIE B7/B8 mit Compressor zerstoeren (Schritte!)
- NIE B4-B6 cutten (Operator-Voice + Spatial-ITD)
- NIE B10/B11 hart cutten (Spatial-ILD)
- ScoreStreaks: ReaXComp-Compression (dynamisch) statt Pre-EQ-Cut (statisch)
- Wingsuit-Wind: ReaXComp B11 4:1 statt -10 dB Pre-EQ-Cut
Output
🎚 FootstepPro EQ-Tuning fuer <wav-name>
**Aktuelle Metriken vs Targets:**
| Metrik | Wert | Target | Status |
|---|---|---|---|
| foot_wins | XX% | ≥50% | ✅/❌ |
| competitive_score | XX | ≥60 | ✅/❌ |
| spatial_health | XX dB | [-3,-8] | ✅/❌ |
| kf_ratio | XX dB | ≤-10 | ✅/❌ |
**Spatial-Hook Status:** <aktiv/inaktiv> (siehe AUD-H1)
**Top-3 Empfehlungen:**
1. <Filter X | aktuell A | neu B | Delta +X% | Begruendung>
2. ...
3. ...
**Naechster Test:** der Nutzer recordet mit neuer Config, dann erneut /footstep-eq-tunerConstraints
- NIEMALS automatisch Configs deployen — nur Empfehlung schreiben
- Keine Aenderung ohne Vision-Tabellen-Bezug
- Bei aktivem Spatial-Hook + AUD-H1 noch nicht gefixt: Warning ausgeben
- Auf der Nutzer's konkrete Aufnahme bezogen, keine generischen Tipps
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

