skillforge

SkillForge 5.2 - Intelligent Skill Router, Advisor & Creator

Analyzes ANY input to find, improve, or create the right skill. It can also proactively surface evidence-backed skill suggestions through the Context Skill Advisor.

Quick Start

Any input works. SkillForge will intelligently route to the right action:

# These all work - SkillForge figures out what you need:

SkillForge: create a skill for automated code review
→ Creates new skill (after checking no duplicates exist)

help me debug this TypeError
→ Recommends ErrorExplainer skill (existing)

improve the testgen skill to handle React components better
→ Enters improvement mode for TestGen

do I have a skill for database migrations?
→ Recommends DBSchema, database-migration skills

TypeError: Cannot read property 'map' of undefined
→ Routes to debugging skills (error detected)

Triggers

Creation Triggers

• SkillForge: {goal} - Full autonomous skill creation
• create skill - Natural language activation
• design skill for {purpose} - Purpose-first creation
• ultimate skill - Emphasize maximum quality
• skillforge --plan-only - Generate specification without execution

Routing Triggers (NEW in v4.0)

• {any input} - Analyzes and routes automatically
• do I have a skill for - Searches existing skills
• which skill / what skill - Recommends matching skills
• improve {skill-name} skill - Enters improvement mode
• help me with / I need to - Detects task and routes

Proactive Advisor Triggers (NEW in v5.2)

• Session start - Show pending suggestions from the Advisory Queue
• Advisor Checkpoint - Evaluate task shifts, repeated friction, and before-final moments
• Scheduled Background Advising - Run local scheduled advisor checks based on Proactivity Level
• SkillForge advice / context advisor - Inspect or manage queued suggestions

| Input | Output | Quality Gate | |-------|--------|--------------| | Any input | Triage → Route → Action | Phase 0 analysis | | Explicit create | New skill | Unanimous panel approval | | Task/question | Skill recommendation | Match confidence ≥60% | | Advisor checkpoint | Evidence-backed suggestion | Proactivity Level threshold |

Process Overview

ANY USER INPUT
(prompt, error, code, URL, question, task request)
    │
    ▼
┌─────────────────────────────────────────────────────┐
│ Phase 0: SKILL TRIAGE (NEW)                         │
│ • Classify input type (create/improve/question/task)│
│ • Scan 250+ skills in ecosystem                     │
│ • Match against existing skills with confidence %   │
│ • Route to: USE | IMPROVE | CREATE | COMPOSE        │
├─────────────────────────────────────────────────────┤
│         ↓ USE_EXISTING    ↓ IMPROVE      ↓ CREATE   │
│      [Recommend]      [Load & Enhance] [Continue]   │
└─────────────────────────────────────────────────────┘
    │ (if CREATE_NEW or IMPROVE_EXISTING)
    ▼
┌─────────────────────────────────────────────────────┐
│ Phase 1: DEEP ANALYSIS                              │
│ • Expand requirements (explicit, implicit, unknown) │
│ • Apply 11 thinking models + Automation Lens        │
│ • Question until no new insights (3 empty rounds)   │
│ • Identify automation/script opportunities          │
├─────────────────────────────────────────────────────┤
│ Phase 2: SPECIFICATION                              │
│ • Generate XML spec with all decisions + WHY        │
│ • Include scripts section (if applicable)           │
│ • Validate timelessness score ≥ 7                   │
├─────────────────────────────────────────────────────┤
│ Phase 3: GENERATION                                 │
│ • Write SKILL.md with fresh context                 │
│ • Generate references/, assets/, and scripts/       │
├─────────────────────────────────────────────────────┤
│ Phase 4: SYNTHESIS PANEL                            │
│ • 3-4 Opus agents review independently              │
│ • Script Agent added when scripts present           │
│ • All agents must approve (unanimous)               │
│ • If rejected → loop back with feedback             │
└─────────────────────────────────────────────────────┘
    │
    ▼
Production-Ready Agentic Skill

Key principles:

• Phase 0 prevents duplicates - Always checks existing skills first
• Evolution/timelessness is the core lens (score ≥ 7 required)
• Every decision includes WHY
• Zero tolerance for errors
• Autonomous execution at maximum depth
• Scripts enable self-verification and agentic operation

Tool Escalation Policy

Start with least privilege (Read, Glob, Grep, Write, Edit).

Only add higher-risk tools when explicitly required:

• Bash for deterministic local scripts that cannot be replaced with file edits
• WebFetch / WebSearch only when external facts are required
• Task only for true parallel sub-agent orchestration

Commands

| Command | Action | |---------|--------| | SkillForge: {goal} | Full autonomous execution | | SkillForge --plan-only {goal} | Generate specification only | | SkillForge --quick {goal} | Reduced depth (not recommended) | | SkillForge --triage {input} | Run Phase 0 triage only | | SkillForge --improve {skill} | Enter improvement mode for existing skill | | python scripts/install_skillforge.py | Configure proactive advising | | bash scripts/install_workshop.sh | Install SkillForge for Claude Code, Codex, and workshop use | | python scripts/context_advisor.py checkpoint --text "<context>" | Run an Advisor Checkpoint | | python scripts/context_advisor.py run | Run Scheduled Background Advising and queue suggestions | | python scripts/context_advisor.py list | List pending suggestions |

Context Skill Advisor (NEW in v5.2)

The Context Skill Advisor produces proactive, evidence-backed suggestions without replacing explicit SkillForge routing.

Proactivity Levels

| Level | Minimum Confidence | Max Surfaced | Schedule | |-------|--------------------|--------------|----------| | off | N/A | 0 | Never | | quiet | 85 | 1 per session/day | Daily | | balanced | 70 | 2 per session, 3 per day | Every 2 hours | | active | 55 | 4 per session, 8 per day | Every 30 minutes |

Install default: balanced.

Context Source Tiers

All three source tiers are enabled by default, but the advisor uses Targeted Content Access: search first, then read only narrow relevant excerpts.

| Tier | Examples | |------|----------| | Session Context | Current prompt, checkpoint text, immediate workspace state | | Project Context | AGENTS.md, README.md, CONTEXT.md, package files, ADRs | | Personal Context | ~/kb, ~/Documents/Work, ~/Projects, GitHub repo metadata |

Suggestion Shape

Every proactive suggestion includes:

• Suggested skill or New Skill Opportunity
• Why now
• 1-3 evidence items
• Confidence band and component scores
• Action: use_existing, compose_skills, improve_existing, or create_new
• User choices: use, snooze, dismiss, never for this project
• Sensitivity note when Personal Context contributed

SkillForge does not auto-invoke suggested skills. Suggestions become Confirmed Skill Use only after user confirmation or explicit host direction.

Advisor Commands

# Configure global defaults and print the checkpoint integration snippet
python scripts/install_skillforge.py

# One-command workshop install for Claude Code and Codex
curl -fsSL https://raw.githubusercontent.com/tripleyak/SkillForge/main/scripts/install_workshop.sh | bash

# Configure a different Proactivity Level
python scripts/install_skillforge.py --proactivity-level quiet

# Add a project override
python scripts/install_skillforge.py --project-override /path/to/project --proactivity-level active

# Run a checkpoint from the active agent session
python scripts/context_advisor.py checkpoint --cwd "$PWD" --text "<brief current context>"

# Run scheduled advising and write to the Advisory Queue
python scripts/context_advisor.