SKILL_TEMPLATE
[1-2 sentence description of what this skill does]. Triggers on [specific phrases/contexts that should activate this skill]. Outputs [what the skill produces].
Creates new Source of Truth (SoT) files when existing templates don't fit your needs. Triggers on requests to create a new SoT file, add a new artifact type, or when user says "I need to track [X] but there's no SoT for it", "create SoT", "new source of truth". Outputs a
$ npx -y skills add mattgierhart/PRD-driven-context-engineering --skill ghm-sot-builder --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/ghm-sot-builderContext preview
The summary Claude sees to decide when to auto-load this skill.
Creates new Source of Truth (SoT) files when existing templates don't fit your needs. Triggers on requests to create a new SoT file, add a new artifact type, or when user says "I need to track [X] but there's no SoT for it", "create SoT", "new source of truth". Outputs a
name: ghm-sot-builder description: > Creates new Source of Truth (SoT) files when existing templates don't fit your needs. Triggers on requests to create a new SoT file, add a new artifact type, or when user says "I need to track [X] but there's no SoT for it", "create SoT", "new source of truth". Outputs a properly structured SoT.*.md file with ID prefix, frontmatter, and update protocol. context: fork allowed-tools: - Read - Write - Edit - Glob - Grep
Create new Source of Truth files that fit your product's unique needs while maintaining template purity.
This skill is for **rare occasions** (3-4 times per product lifecycle) when:
**Do NOT use** when:
1. **Identify Need** → Confirm no existing SoT fits 2. **Design Schema** → Define ID prefix, categories, required fields 3. **Draft Template** → Create pure structure (no methodology teaching) 4. **Validate Purity** → Apply the litmus test 5. **Register & Integrate** → Update SoT.README.md and ID system
See `assets/sot-template.md` for the copy-paste starter template.
| Element | Definition | Required | |---------|------------|----------| | **YAML Frontmatter** | version, purpose, id_prefix, authority | Yes | | **Purpose Block** | Single paragraph explaining what this tracks | Yes | | **Navigation Section** | Category links for quick access | Yes | | **Entry Template** | Repeatable structure for each ID | Yes | | **Cross-Reference Index** | Bidirectional links to other SoT files | Yes | | **Update Protocol** | When/how to add new entries | Yes |
Before creating a new SoT, verify:
1. **What artifact type does this track?**
2. **Why can't existing SoT files handle this?**
3. **What ID prefix will you use?**
Define the structure before writing:
Format: [PREFIX]-[XXX] Examples: PIC-001, INT-042, MIG-003
**Rules**:
Reserve ID ranges for logical groupings:
**Category A** (XXX-001 to XXX-099): **Category B** (XXX-101 to XXX-199): **Category C** (XXX-201 to XXX-299):
Define the minimum fields every entry needs:
| Field | Purpose | Example | |-------|---------|---------| | **ID** | Unique identifier | `PIC-001` | | **Title** | Human-readable name | "Stripe Payment Integration" | | **Status** | Current state | Active / Deprecated / Planned | | **Created** | Origin date | 2025-01-10 | | **Last Updated** | Last modification | 2025-01-15 | | **Related IDs** | Cross-references | BR-101, API-045 |
Add domain-specific fields as needed, but keep them structural (not methodology):
Use `assets/sot-template.md` as your starting point.
1. **YAML Frontmatter** - Metadata for the file 2. **Title & Purpose Block** - What this SoT tracks 3. **Navigation by Category** - Quick links to entries 4. **Entry Template** - Repeatable structure (copy for each new entry) 5. **Deprecated Section** - Where old entries go 6. **Cross-Reference Index** - Bidirectional links 7. **Update Protocol** - When/how to maintain
**KEEP in the template** (self-documentation):
**MOVE to skill references** (methodology teaching):
For each section, ask:
> "Is this teaching me how to maintain the FILE STRUCTURE, or teaching me DOMAIN KNOWLEDGE about what makes good content?"
Before finalizing, run this checklist:
PRD-Led Context Engineering — Memory as Infrastructure. An ontology layer for product teams building products that solve real problems — with AI agents that remember. Gated PRD, typed IDs, markdown knowledge graph, Claude Code skills & hooks.
Repo: mattgierhart/PRD-driven-context-engineering
[1-2 sentence description of what this skill does]. Triggers on [specific phrases/contexts that should activate this skill]. Outputs [what the skill produces].
Validates gate criteria before PRD lifecycle advancement by delegating to the readiness scoring pipeline (scripts/readiness.py). Returns a graduated PASS /…
Extracts durable insights from temp/ files to SoT during EPIC Phase E. Triggers at EPIC completion or explicit `/ghm-harvest` invocation. Outputs new SoT…
Validates and registers new SoT IDs with cross-reference integrity. Triggers when creating BR-XXX, UJ-XXX, API-XXX, or CFD-XXX entries. Outputs formatted SoT…
Install the PRD-Driven Context Engineering methodology into a fresh OR existing repository — the subscription-native alternative to forking the whole repo.…
Synchronizes README.md Command Center with current project state. Triggers on gate changes, EPIC status changes, or explicit `/ghm-status-sync` invocation.…