skills.rest
NerdBase-by-Stark
NerdBase-by-StarkCOMMUNITY
Explore all skills by this author →
GitHub

skill-forge

Audit, discover, and improve a project's skill library through a 9-phase workflow.

1|Updated Apr 16, 2026
Search Tags:#automation#workflow#auditing#memory#consent#skill-forge
One-click install
npx skills add https://github.com/NerdBase-by-Stark/skill-forge --skill skill-forge-nerdbase-by-stark
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-forge
Source: https://github.com/NerdBase-by-Stark/skill-forge/tree/main/skill-forge
Command: npx skills add https://github.com/NerdBase-by-Stark/skill-forge --skill skill-forge-nerdbase-by-stark

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pyyaml, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Skill libraries drift over time, descriptions become stale, and file-pattern overlaps cause maintenance bottlenecks; skill-forge provides a disciplined 9-phase pipeline to audit, discover, and improve a project's skill library.

Core Features & Use Cases

  • End-to-end workflow: Discover, Audit, Find Candidates, First-Pass Edits, Deep Research, Second-Pass Edits, Structure, QA, Memory.
  • Deterministic scope and safety: validates YAML frontmatter, checks triggers, and records decisions with explicit user consent.
  • Memory and reproducibility: preserves architectural decisions and research outputs for future runs.

Quick Start

Ask for explicit confirmation to begin Phase 1 and follow the guided prompts through all nine phases.

Frequently Asked Questions about skill-forge

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I audit my project's skill library for stale descriptions and file overlaps?▼

Auditing a skill library involves a 9-phase workflow that deterministically inventories skills, validates YAML frontmatter, and checks triggers to prevent maintenance bottlenecks caused by file-pattern overlaps.

What is the best way to automate tuning and discovering improvements for a skill library?▼

Automating skill library tuning uses a pipeline that spawns research agents to discover improvements and applies first-pass and second-pass edits only after explicit user consent.

How does memory and reproducibility work when auditing skill libraries?▼

Memory in skill library auditing preserves architectural decisions and stores research results to guide future runs, ensuring reproducible outcomes across the entire 9-phase workflow.

Do I need explicit user consent before applying changes to my skill library?▼

Yes, explicit user consent is required before applying changes; the workflow validates frontmatter and triggers, then applies edits only after approval to ensure deterministic safety.

Can I use pyyaml to validate frontmatter in an automated skill library workflow?▼

Yes, pyyaml is used to validate YAML frontmatter within the workflow, ensuring that skill triggers and descriptions are correctly formatted before applying any approved changes.

When should I run a full 9-phase pipeline instead of manually editing individual skill files?▼

Run a full 9-phase pipeline when your skill library has drifted significantly with stale descriptions and overlaps, requiring structured discovery, deep research, and QA rather than manual file edits.

Related Skills

Explore More Software Engineering Skills→
CruxExpertsCruxExperts
3

ls-framework-audit

Audit repository documentation, links, skill matrix, and version facts for release readiness.

Community
Advanced
Space-DinosaursSpace-Dinosaurs
12

memory-update

Capture project decisions into MEMORY.md with date-stamped entries.

Official
Intermediate
gtpgg1013gtpgg1013

team-dogfood

Orchestrate parallel dogfood browser QA against a TARGET_URL in team verify.

Community
Advanced
MelvynxMelvynx
223

apex

Orchestrate adaptive agents to plan, execute, and validate feature implementations.

Community
Advanced