Vibe Index
🎯

skill-builder

🎯Skill

from bsamiee/parametric_forge

VibeIndex|
What it does

Generates and refines Claude Code skills with structured workflows, templates, and metadata-driven authoring.

πŸ“¦

Part of

bsamiee/parametric_forge(19 items)

skill-builder

Installation

Install ScriptRun install script
curl --proto '=https' --tlsv1.2 -sSf -L https://install.determinate.systems/nix | sh -s -- install
git cloneClone repository
git clone https://github.com/bsamiee/Parametric_Forge.git ~/Parametric_Forge
πŸ“– Extracted from docs: bsamiee/parametric_forge
Need more details? View full documentation on GitHub β†’
2Installs
-
AddedFeb 4, 2026
View on GitHubBack to Skills

Skill Details

SKILL.md

Creates and edits Claude Code skills with YAML frontmatter, folder structure, and depth-scaled content. Use when building new skills, updating existing skills, designing SKILL.md metadata, organizing skill folders, validating skill structure, or adding Python and TypeScript scripts for deterministic operations.

Overview

# [H1][SKILL-BUILDER]

>Dictum: Structured authoring produces discoverable, maintainable skills.


Create and refine Claude Code skills via structured workflows.

Tasks:

  1. Collect parameters β€” Scope: create | refine, Type: simple | standard | complex, Depth: base | extended | full
  2. Read [frontmatter.md](./references/frontmatter.md) β€” Discovery metadata, trigger patterns
  3. Read [structure.md](./references/structure.md) β€” Folder layout gated by Type
  4. Read [depth.md](./references/depth.md) β€” LOC limits, nesting gated by Depth
  5. (complex) Read [scripting.md](./references/scripting.md) β€” Automation standards
  6. Capture requirements β€” purpose, triggers, outputs
  7. Invoke skill-summarizer with skill style-standards β€” Extract voice, formatting, taxonomy
  8. Invoke deep-research β€” Domain research for skill topic
  9. Plan with 3 agents β€” file inventory, section structure, content framework
  10. Execute per Scope:

- (create) Author new artifacts; select template:

- [simple](./templates/simple.skill.template.md) - DEFAULT

- [standard](./templates/standard.skill.template.md)

- [complex](./templates/complex.skill.template.md)

- (refine) Compare input to existing frontmatter; see [refine.md](./references/workflows/refine.md):

- Input = existing β†’ optimize (density, fixes, quality)

- Input > existing β†’ upgrade (expand structure or depth)

- Input < existing β†’ downsize (combine, refactor, remove low-relevance)

  1. Validate β€” Quality gate, LOC compliance, structure match

Dependencies:

  • deep-research β€” Domain research via parallel agents
  • skill-summarizer β€” Voice and formatting extraction (with skill style-standards)
  • report.md β€” Sub-agent output format

[REFERENCE]: [index.md](./index.md) β€” Complete file listing

---

[1][FRONTMATTER]

>Dictum: Metadata enables discovery before loading.


Frontmatter indexed at session start (~100 tokens). Description is ONLY field parsed for relevanceβ€”quality determines invocation accuracy.

Guidance:

  • Discovery β€” LLM reasoning matches description to user intent. No embeddings, no keyword matching.
  • Trigger Density β€” Include file types, operations, "Use when" clauses. Every word aids matching.
  • Voice β€” Third person, active, present tense. Prohibit: 'could', 'might', 'probably', 'should'.

Best-Practices:

  • Length β€” 1-2 sentences. Concise triggers outperform verbose explanations.
  • Classification β€” Include type and depth fields for refine workflow detection.

---

[2][STRUCTURE]

>Dictum: Type determines breadthβ€”folder existence defines capability scope.


Type gates folder creation. Structure defines WHAT exists; Depth constrains HOW MUCH content.

| [INDEX] | [TYPE] | [FOLDERS] |

| :-----: | -------- | ---------------------------------- |

| [1] | Simple | SKILL.md only |

| [2] | Standard | +index.md, references/, templates/ |

| [3] | Complex | +scripts/ |

Guidance:

  • Naming β€” Skill folder matches frontmatter name exactly. Kebab-case throughout.
  • Index β€” Standard/Complex require index.md at root listing all reference files.
  • Upgrade Path β€” Start with simplest type satisfying requirements.

Best-Practices:

  • Directory Purpose β€” references/ for domain knowledge, templates/ for output scaffolds, scripts/ for automation.
  • File Limit β€” Max 7 files in references/ (including nested).

---

[3][DEPTH]

>Dictum: Depth determines comprehensivenessβ€”hard caps prevent bloat.


Depth enforces LOC limits and nesting rights. Each level adds +50 SKILL.md, +25 reference files (cumulative).

| [INDEX] | [DEPTH] | [SKILL.MD] | [REF_FILE] | [NESTING] |

| :-----: | -------- | :--------: | :--------: | -------------- |

| [1] | Base | <300 | <150 | Flat only |

| [2] | Extended | <350 | <175 | 1 subfolder |

| [3] | Full | <400 | <200 | 1-3 subfolders |

Guidance:

  • Nesting Gate β€” Subfolder requires 3+ related files OR distinct domain concern.
  • Content Scaling β€” Base: 1-2 items per Guidance/Best-Practices. Extended: 2-4. Full: comprehensive.
  • LOC Optimization β€” Density over deletion; see [depth.mdΒ§LOC_OPTIMIZATION](./references/depth.md).
  • Content Separation β€” SKILL.md = WHY, references = HOW; see [depth.mdΒ§CONTENT_SEPARATION](./references/depth.md).

Best-Practices:

  • Hard Caps β€” Exceeding limits requires refactoring, not justification.
  • No Brute-Force β€” Consolidate β†’ restructure β†’ densify β†’ prune (in order).

---

[4][SCRIPTING]

>Dictum: Deterministic automation extends LLM capabilities.


Complex type enables scripts/ folder for external tool orchestration, artifact generation, validation.

Guidance:

  • Justification β€” Script overhead demands explicit need: tool wrapping, exact reproducibility, schema enforcement.
  • Depth Scaling β€” Base/Extended: single script. Full: multiple when distinct concerns justify.

Best-Practices:

  • Type Selection β€” Standard suffices for most skills. Complex only when automation is core purpose.
  • Augmentation β€” Scripts support workflows; core logic remains in SKILL.md and references.

---

[5][TEMPLATES]

>Dictum: Templates enforce canonical structure.


Templates define output scaffolds. Agent combines user input with template skeleton for consistent artifacts.

Guidance:

  • Purpose β€” Follow template exactly. No improvisation.
  • Composition β€” Input data + template skeleton = generated artifact.

Best-Practices:

  • Placeholder Syntax β€” Use ${variable-name} for insertion points.
  • Structure Match β€” Template complexity matches depth selection.

---

[6][VALIDATION]

>Dictum: Gates prevent incomplete artifacts.


[VERIFY] Completion:

  • [ ] Parameters: Scope, Type, Depth collected and applied.
  • [ ] Research: deep-research completed fully before authoring.
  • [ ] Style: skill-summarizer constraints applied to output.
  • [ ] Workflow: Executed per Scope (create | refine).
  • [ ] Quality: LOC within limits, content separation enforced.

[REFERENCE] Operational checklist: [β†’validation.md](./references/validation.md)

More from this repository10

🎯
n8n-builder🎯Skill

n8n-builder skill from bsamiee/parametric_forge

🎯
hostinger-tools🎯Skill

hostinger-tools skill from bsamiee/parametric_forge

🎯
typescript-effect🎯Skill

typescript-effect skill from bsamiee/parametric_forge

🎯
output-style-builder🎯Skill

output-style-builder skill from bsamiee/parametric_forge

🎯
nx-tools🎯Skill

nx-tools skill from bsamiee/parametric_forge

🎯
hooks-builder🎯Skill

Builds and configures lifecycle hooks for Claude Code, enabling deterministic automation across agent events with precise control and validation.

🎯
mermaid-diagramming🎯Skill

mermaid-diagramming skill from bsamiee/parametric_forge

🎯
tavily-tools🎯Skill

tavily-tools skill from bsamiee/parametric_forge

🎯
perplexity-tools🎯Skill

perplexity-tools skill from bsamiee/parametric_forge

🎯
context7-tools🎯Skill

context7-tools skill from bsamiee/parametric_forge