skill-forge — The meta-skill that forges skills

The problem

Three gaps in the skill lifecycle

01 Don't know when to create a skill Auto-detect complex tasks, proactively ask

02 Don't know if a skill is well-written 4-dimension evaluator, threshold before save

03 Don't know if it will actually trigger Eval-driven description optimization

The forge

Ore /scan Discover opportunities in your codebase

Heat /create Research patterns, draft the skill

Strike eval 4-dim scoring, reject below 6/8

Temper /improve Patch content, optimize triggers

Blade SKILL.md Production skill, registry tracked

Commands

claude-code

$ /scan [prompt]

Scan project for skill opportunities.

$ /create <prompt>

Create skill from prompt. Name auto-derived.

$ /improve <prompt>

Iterate skill from prompt. Target matched from registry.

$ /rename <old> <new>

AI-driven rename. Updates dir, SKILL.md body, workspace, registry.

Under the hood

Dual-file isolation

Injection-proof by design

External content lands in low-trust .skill-forge/insights.md. Only validated patterns promote to the high-trust draft that hooks inject.

Attention anchoring

Hooks keep the goal in focus

UserPromptSubmit and PreToolUse hooks re-inject the draft header every turn. Context overflows can't erase the mission.

Session catchup

Nothing slips through the cracks

Missed a complex workflow yesterday? SessionStart parses previous JSONL, surfaces uncaptured 5+ tool-call tasks.

Eval-driven triggers

DSPy-inspired, self-optimized

20-case trigger evals with structured FP/FN failure analysis. All internal prompts are self-optimized via eval-driven variant selection.

Then run /scan to discover your first opportunities.