kiyoraka/project-ai-memorycore/forge-self-improvement-system

Claude Code and agent skill by kiyoraka/project-ai-memorycore

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

"Auto-triggers when AI detects a repeated pattern handled ad-hoc 3+ times,

Install

npx vskill@latest install kiyoraka/project-ai-memorycore/forge-self-improvement-system

SKILL.md

Forge Skill -- Self-Improvement System

The AI that improves its own abilities through experience.

Overview

Forge is the meta-skill -- the skill that creates and improves other skills. When your AI detects patterns, mistakes, or opportunities for improvement during conversation, Forge activates to propose new skills or level-ups to existing ones. It uses a human-in-the-loop model: AI drafts, user approves.

Activation

When this skill activates, output:

"Forge detected an opportunity for improvement..."

Then present the proposal to the user.

Context Guard

ContextStatus
AI detects repeated ad-hoc pattern (3+ times)ACTIVE -- propose new skill
AI makes preventable mistakeACTIVE -- propose new rule or skill
User says "create skill", "new skill", "forge this"ACTIVE -- manual trigger
User says "level up [skill]", "upgrade [skill]"ACTIVE -- level-up existing
User says "self improve", "improve skill"ACTIVE -- review and propose
Casual conversation (no improvement context)DORMANT

Forge Protocol

Step 1: Detect

Identify the improvement opportunity. Forge recognizes these patterns:

Automatic Detection (AI-initiated):

  1. Repeated Pattern -- AI handles the same type of task ad-hoc 3+ times across sessions
  2. Mistake Prevention -- AI makes an error that a permanent rule would prevent
  3. Workflow Automation -- A multi-step process AI does manually that could be a skill
  4. Level-Up Opportunity -- An existing skill has a gap or could handle more cases

Manual Trigger (User-initiated):

  • "create skill", "new skill", "forge this"
  • "level up [skill]", "upgrade [skill]"
  • "self improve", "improve skill"
Step 2: Analyze

Before proposing, gather evidence:

TYPE: [New Skill / Level-Up / New Rule]
TARGET: [Skill name if level-up, or proposed name if new]
TRIGGER: [What pattern/mistake/workflow was detected]
EVIDENCE: [At least 2 concrete examples from conversation or session history]
IMPACT: [What improves if this is implemented]
Step 3: Propose

Present to user in this format:

Forge Detected an Opportunity
==============================
Type: [New Skill / Level-Up]
Name: [proposed-name]
Purpose: [what it would do]
Trigger: [what activates it]
Evidence:
1. [First concrete example]
2. [Second concrete example]
Impact: [what improves]
Draft ready -- approve to forge?
Step 4: Await Approval
  • User approves -- proceed to Step 5
  • User adjusts -- incorporate feedback, re-propose
  • User rejects -- note the rejection, do NOT create

CRITICAL: NEVER create or modify skill files without explicit user approval.

Step 5: Create or Update

For NEW skill:

  1. Create skill folder: plugins/[plugin-name]/skills/[skill-name]/
  2. Write SKILL.md following the standard skill format:
  • YAML frontmatter with name + description (trigger phrases)
  • Activation section (what the AI says when triggered)
  • Context Guard table (when active vs dormant)
  • Protocol steps (step-by-step execution)
  • Mandatory rules
  • Level History (starting at Lv.1)
  1. Verify file was created successfully

For LEVEL-UP:

  1. Read existing SKILL.md
  2. Add new capability section
  3. Update description in frontmatter if trigger phrases changed
  4. Add new Level History entry with:
  • Level number
  • Capability added
  • Origin (what conversation/incident triggered it)
  1. Save updated file
Step 6: Update System Records

After forging, update relevant system files:

  • master-memory.md -- add new skill command or update existing
  • Skill Plugin System manifest if applicable
  • Note the forge in current session memory
Step 7: Confirm
Forge Complete!
================
[New Skill / Level-Up]: [name] Lv.[X]
Location: skills/[name]/SKILL.md
Capability: [what was added]
Origin: [the moment that triggered this]
Your AI evolved!

Forge Principles

  1. Human-in-the-loop -- AI proposes, user approves. Always
  2. Evidence-based -- never propose without at least 2 concrete examples
  3. Origin stories -- every skill and level-up traces back to a real moment
  4. Minimal viable skill -- start at Lv.1, evolve organically through use
  5. No over-engineering -- only forge what is genuinely needed
  6. Respect existing skills -- level-up before creating duplicates. Check if an existing skill could handle the case first
  7. Level history is permanent -- append-only record of how the skill evolved

Skill File Template

When Forge creates a new skill, use this structure:

markdown
---
name: [skill-name]
description: "[When this skill should auto-trigger -- include trigger phrases
and context descriptions]"
---
# [Skill Name] -- [One-line description]
*[Thematic tagline]*
## Activation
When this skill activates, output:
"[Activation message]"
## Context Guard
| Context | Status |
|---------|--------|
| **[Trigger condition 1]** | ACTIVE -- [action] |
| **[Trigger condition 2]** | ACTIVE -- [action] |
| **[Non-trigger context]** | DORMANT |
## Protocol
### Step 1: [First action]
-[ ] [Substep]
-[ ] [Substep]
### Step 2: [Second action]
-[ ] [Substep]
## Mandatory Rules
1.[Rule 1]
2.[Rule 2]
## Level History
-**Lv.1** -- Base: [description of initial capabilities]. (Origin: [what triggered creation])

What Makes a Good Skill

Before forging, evaluate against these criteria:

CriteriaQuestion
RepeatableWill this trigger more than once in future sessions?
SpecificIs the trigger condition clear and unambiguous?
ValuableDoes automating this save meaningful time or prevent real errors?
IndependentCan this skill work without requiring other skills?
TestableCan the user verify it works by triggering it?

If 4 out of 5 criteria are met, the skill is worth forging.

Level-Up Guidelines

Skills evolve through levels as they gain capabilities:

LevelMeaningTypical Addition
Lv.1Base skillCore functionality, basic triggers, simple protocol
Lv.2EnhancedAdditional trigger conditions, edge case handling
Lv.3ProactiveAuto-detection without explicit commands
Lv.4IntegratedSynergy with other skills, cross-referencing
Lv.5+MasteredContext-aware, domain-specific intelligence

Each level should add one meaningful capability -- not multiple changes bundled together.

Mandatory Rules

  1. Human-in-the-loop -- NEVER create or modify skill files without user's explicit approval
  2. Evidence-based -- at least 2 concrete examples before proposing
  3. Origin stories -- every level-up must trace back to a real moment
  4. Minimal viable skill -- start simple at Lv.1, add complexity only when proven needed
  5. No over-engineering -- only forge what is genuinely needed right now
  6. Respect existing skills -- always check if an existing skill covers the case before creating a new one
  7. Level history is append-only -- never edit past level entries, only add new ones
  8. Standard format -- all skills follow the template structure (frontmatter, activation, context guard, protocol, rules, level history)

Edge Cases

SituationBehavior
No Skill Plugin System installedInform user that forged skills work best with the plugin; offer to create as standalone protocol
Proposed skill overlaps existingSuggest level-up to existing skill instead of creating duplicate
User rejects proposalNote rejection reason, do not re-propose same skill in current session
Insufficient evidence (< 2 examples)Wait for more evidence before proposing -- don't force it
Skill file already exists at targetTreat as level-up, not overwrite

Synergy with Other Features

FeatureIntegration
Skill Plugin SystemForge creates skills in the plugin's skill folder structure
Auto-Commit SystemAfter forging, commit the new/updated skill file
Decision Log SystemLog the decision to create/level-up a skill with rationale
Save Diary SystemDocument the forge event in the session diary

Level History

  • Lv.1 -- Base: detect repeated patterns (3+ ad-hoc), mistake prevention, workflow automation, level-up opportunities. Human-in-the-loop approval. Standard skill template. Level-up guidelines with Lv.1-5+ progression. (Origin: Adapted from production AI companion self-improvement system with 23 skills forged over 7 months)

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
375
Repository forks
111
7-day trend score
30

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/kiyoraka/project-ai-memorycore/forge-self-improvement-system/badge)](https://verified-skill.com/skills/kiyoraka/project-ai-memorycore/forge-self-improvement-system)

Something wrong with this skill or its page? Tell us.