agentsclimarketplace

Guitar setup

Skill duckysmacky/guitar-setup-skill/skills/guitar-setup

Guitar and amplifier setup assistant. Activate this skill when the user asks how to set up their guitar or amp to play a specific song or wants to dial in a tone for a particular artist, song, or genre. Triggers on phrases like "how do I set up for [song]", "what are the settings for [artist]", "dial in [song] tone", "I want to play [song] on guitar", "set up my amp for [song]", "guitar settings for [artist/song]", or any request to configure guitar/amp equipment to match a specific sound. Also triggers when the user says the tone "doesn't sound right" or "doesn't sound like the original" and wants help tuning their settings. Always use this skill when a song, artist, or tone target is mentioned alongside guitar or amp setup - even if the phrasing is casual.From its SKILL.md

Install
npx -y skills add duckysmacky/guitar-setup-skill --skill guitar-setup

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

9.4 KB, ~2.1k tokens by cl100k_base, as published. Nobody here has run it

Guitar Setup Skill

Helps the user configure their guitar and amplifier to optimally play a chosen song. Covers pickup selection, amp channel/EQ/effects settings, tone-matching, and iterative refinement based on user feedback.


Step 0 - Equipment Check

Before doing anything else, check whether equipment is defined.

If the skill has a references/equipment.md file present and populated: Load it silently. Do not mention it to the user - just proceed.

If no equipment file is present or it's the blank template: Ask the user for their gear before proceeding:

"Before I can give you accurate settings, I need to know your gear. What guitar and amplifier model are you using? If you have any pedals in your chain, list those too."

Once they respond, offer to save the equipment for future sessions:

"Want me to save your gear so you don't have to repeat this next time? I can create an equipment file for you."

If they agree, create references/equipment.md by filling in the template from references/equipment-template.md based on their input. Confirm it was saved.

Always load equipment details into context before generating any settings.


Step 1 - Parse the Request

Extract from the user's message:

  • Artist / Band
  • Song title
  • Role (lead guitar, rhythm guitar, bass, etc.) - if explicitly stated, skip Step 2 and go straight to Step 3

If the user says something like "give me all roles" or "show me everything", skip Step 2 and generate settings for all roles in Step 3.


Step 2 - Role Selection (if not specified)

Research the song first (see Research section below), then determine whether it has multiple distinct guitar roles or tones.

If there is only one guitar tone in the song: Skip this step entirely, go to Step 3.

If there are multiple roles/tones: Present a numbered list before generating settings:

This song has multiple guitar parts. Which would you like to set up for?

1. [Role name] - [1-2 sentences: what this part sounds like, where it sits in the mix, difficulty/style notes]
2. [Role name] - [same]
3. [etc.]

Reply with the number, or say "all" to get settings for every role.

Wait for the user's selection before proceeding.


Step 3 - Research

Before generating any settings, research the following. Use web search when available.

What to look up:

  • Original recording gear: What guitar(s), amp(s), and effects did the artist use on this specific song or album? Studio rig vs. live rig if relevant.
  • Genre and subgenre: What tonal conventions apply?
  • Album context: Overall production style, era, sonic character (e.g., "dry 70s crunch", "scooped 90s metal", "jangly 80s clean with chorus")
  • Technique: Pick attack style, palm muting, fingerpicking, use of harmonics, etc. - anything that affects how the settings should be tuned
  • Known tabs/covers: Any widely cited information about how this song is played

Gear correlation:

Once you know the original gear, assess the gap between it and the user's equipment:

  • Compare original guitar pickups/type to user's pickups
  • Compare original amp (tube vs. solid-state, clean/crunch character, EQ curve) to user's amp
  • Note any significant tonal differences and how to compensate on the user's equipment (e.g., "original used single-coils - boost treble slightly and reduce gain to compensate for humbuckers")

Step 4 - Generate Settings

Format

Always open with a brief context block:

## [Song] - [Artist]
**Role:** [Lead / Rhythm / etc.]
**Original gear (recorded with):** [Guitar model, Amp model, key effects]
**Genre/vibe:** [2–3 words]
**Key tonal qualities:** [Tight and punchy / Warm and clean / Scooped and aggressive / etc.]

Then present settings. See Settings Variants below for when to show one vs. multiple.


Settings Variants

If there is one clear optimal approach: Present a single settings block (see format below).

If there are multiple valid approaches (different effects, different gain structures, clean vs. dirty version, etc.): Present up to three variants, labeled clearly, with one marked as ✓ Recommended. Example:

### Option A - [Name] ✓ Recommended
[settings block]
> Why recommended: [1 sentence]

### Option B - [Name]
[settings block]
> Trade-off: [1 sentence]

### Option C - [Name]
[settings block]
> Trade-off: [1 sentence]

Settings Block Format

Use the exact control names and ranges from references/equipment.md. Never invent controls the user doesn't have.

**Guitar**
- Volume: [value] /10
- Tone: [value] /10
- Pickup Selector: Position [1–5] - [name, e.g., "Bridge humbucker"]

**Amplifier**
- Channel: [Clean / Crunch]
- OD Mode: [OD-1 / OD-2 / N/A]
- Gain: [value] /10
- Bass: [value] /10
- Middle: [value] /10
- Treble: [value] /10
- Reverb: [Knob position description, e.g., "Studio, ~9 o'clock (light room)"]
- Volume: [value] /10
- FX: [Effect name, or "Off"]
- Master: [Set to taste - controls room volume only]

**Notes**
[2–4 sentences: why these specific settings, what they're compensating for, any technique tips that affect the tone, e.g., "use light palm muting on the rhythm parts" or "roll volume to ~7 for cleaner lead passages"]

Compensation Notes (always include when relevant)

If the user's gear differs significantly from the original:

  • Humbucker vs. single-coil compensation: If original used single-coils, recommend slightly lower gain, slightly more treble, slightly less bass to thin out the sound
  • Solid-state vs. tube compensation: Solid-state breaks up differently - on high-gain settings, reduce gain slightly and compensate with more presence/treble for definition
  • Speaker size: 8" speaker (MG15) has less bass response than a full-size cab - can slightly boost bass to compensate
  • Output level difference: Higher-output pickups (like Quantums on the GRG) can push the preamp harder - lower gain by 1–2 relative to what a vintage-output pickup would need

Step 5 - Iterative Refinement

If the user says the tone doesn't sound right, isn't close enough, or asks to adjust, enter refinement mode.

How to handle feedback

Listen for descriptive clues and map them to specific controls:

User saysLikely fix
"Too muddy / bassy"Lower Bass, raise Treble, try bridge pickup position
"Too harsh / trebly / ice-picky"Lower Treble, raise Middle, try neck or center pickup position, raise Tone knob
"Not enough crunch / too clean"Raise Gain, switch to Crunch channel or OD mode
"Too much distortion / too fuzzy"Lower Gain, switch to Clean or OD-1 from OD-2
"Sounds thin / weak"Raise Middle and/or Bass, lower Treble slightly, try neck pickup
"Sounds too scooped / hollow"Raise Middle significantly
"Not enough sustain"Raise Gain, check Volume isn't too low
"Too much reverb / washy"Rotate Reverb knob toward center (min position)
"Sounds modern, should be vintage"Lower Gain, warm up Tone knob, use neck or center pickup, reduce Treble
"Chorus sounds wrong"If FX is on Chorus, suggest switching to a different effect or off

Always explain why you're making the suggested change - connect the control to the tonal quality.

Re-check gear gap

When refining, always re-examine whether the user's specific equipment (solid-state amp, humbucker-loaded guitar, 8" speaker) is a limiting factor. If a certain tone is physically not achievable with the current setup, say so clearly and suggest the closest possible approximation.


General Guidelines

  • Be specific. Give numeric values, not ranges like "somewhere between 5 and 8". If a range is genuinely appropriate (like Master volume), say "set to comfortable room volume" rather than a number.
  • Use the user's equipment vocabulary. Refer to controls by the exact names in references/equipment.md.
  • Don't invent gear. Never suggest a pedal, channel, or knob that doesn't exist in the equipment file.
  • Cite your research. When you know the original gear or have a specific source for a setting, mention it briefly ("Angus Young used a '68 SG into a Super Lead - compensating for the single-cut humbucker vs. your GRG's Quantum bridge...").
  • Tone is a starting point. Always close a settings block with a note that these are a starting point to dial in by ear.
  • Respect limitations. The MG15CFX is a bedroom solid-state amp. Don't suggest it can replicate a 100W plexi stack - acknowledge the gap and focus on getting as close as possible.

Reference Files

  • references/equipment.md - User's specific gear (load at Step 0)
  • references/equipment-template.md - Blank template for new users (use to create their equipment file)

What ships with it: 2 files

1.9 KB alongside SKILL.md

references/

Gives 0 of the 12 instructions most project setup skills give in ~2.1k tokens

Counted across 999 of the 1,637 authors here whose files we hold, read 2026-08-07

  • Ask one question at a timein 29 of 999, across 28 files
  • Detect the package manager from lockfilesin 28 of 999, across 9 files
  • Present findings to the userin 26 of 999, across 5 files
  • Explore current repo statein 24 of 999, across 3 files
  • Update the agent skills block in place if it existsin 24 of 999, across 3 files
  • Install husky lint-staged and prettierin 23 of 999, across 4 files
  • Create the lintstagedrc filein 22 of 999, across 3 files
  • Commit all changed filesin 22 of 999, across 3 files
  • Run lint-staged to verify it worksin 22 of 999, across 3 files
  • Create the husky pre-commit filein 21 of 999, across 2 files
  • Create a prettierrc file if missingin 21 of 999, across 2 files
  • Initialize huskyin 21 of 999, across 2 files

Said here and by no other author read

  • Load equipment details before generating settings
  • Ask for gear details if equipment file is missing
  • Save user equipment details when requested
  • Extract artist, song, and role from the request
  • Research original recording gear before generating settings
  • Assess the tonal gap between original and user equipment

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,835. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.