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].
Seed a fresh (greenfield) repository with the PRD-Driven Context Engineering scaffold — PRD.md, SoT/ knowledge files, EPIC templates, domain-profile config, and agent MEMORY starters. Invoked as /prd-ce:init when the plugin is installed. The framework itself (skills, agents,
$ npx -y skills add mattgierhart/PRD-driven-context-engineering --skill init --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/initContext preview
The summary Claude sees to decide when to auto-load this skill.
Seed a fresh (greenfield) repository with the PRD-Driven Context Engineering scaffold — PRD.md, SoT/ knowledge files, EPIC templates, domain-profile config, and agent MEMORY starters. Invoked as /prd-ce:init when the plugin is installed. The framework itself (skills, agents,
name: init description: > Seed a fresh (greenfield) repository with the PRD-Driven Context Engineering scaffold — PRD.md, SoT/ knowledge files, EPIC templates, domain-profile config, and agent MEMORY starters. Invoked as /prd-ce:init when the plugin is installed. The framework itself (skills, agents, hooks, scripts) ships LIVE in the plugin; this skill only plants the consumer-owned files the plugin cannot carry as behavior. Triggers on "/prd-ce:init", "set up PRD lifecycle here", "scaffold a new PRD-CE project", "initialize the methodology". Outputs a seeded scaffold + a verification report. disable-model-invocation: true execution_modes: default: standard supports: [quick, standard, deep] allowed-tools: - Read - Write - Edit - Glob - Grep - Bash
Plant the consumer-owned scaffold for a fresh PRD-CE project. The methodology engine (lifecycle skills, the agent squad, governance hooks, `readiness.py`) is delivered **live** by the installed `prd-ce` plugin — it never gets copied into your repo. This skill seeds only what is yours to own and edit: `PRD.md`, the `SoT/` graph, `epics/` templates, your `.claude/domain-profile.yaml`, and per-agent `MEMORY.md` starters.
> **One manifest, no drift.** The seed list comes from `install-manifest.yaml`'s > `template_seed` section — the same list `install.sh` (fork path) and `ghm-template-sync` > (update path) read. This skill drives the deterministic `prd-ce-init.sh` so behavior is > identical no matter who invokes it.
> **Scope (v1): greenfield only.** This seeds an *empty* structure into a fresh repo. > Mid-build and live-codebase on-ramps (entry-mode branching, graph extraction) are > backlogged — see `temp/plugin-conversion-plan.md`. If the target already has `PRD.md` or > `SoT/` content, the seeder keeps it (non-destructive) rather than adapting to it.
paths) the packager ships with the plugin.
does not author specs).
1. Confirm `git`, `python3`, `bash` are present. Warn (don't block) if the target isn't a git repo. 2. Confirm **greenfield**: if `PRD.md` or non-empty `SoT/` already exist, say so and stop — the seeder will keep them untouched, so there is nothing for init to do. (Point the user at the lifecycle skills to keep building, not at re-seeding.)
Ask only what changes the outcome (honor the execution mode's budget):
Quick mode skips this and takes the default.
Run the deterministic seeder so behavior matches every other path:
bash "${CLAUDE_PLUGIN_ROOT}/scripts/prd-ce-init.sh" --target <DIR> --dry-run # preview
bash "${CLAUDE_PLUGIN_ROOT}/scripts/prd-ce-init.sh" --target <DIR> # seedseeded `PRD.md` frontmatter to v0.1.
`profile:` key in the seeded `.claude/domain-profile.yaml` `[standard+]`.
1. Run each plugin hook against the target; assert valid JSON on stdout. 2. Run `python "${CLAUDE_PLUGIN_ROOT}/scripts/readiness.py" run` — a BLOCK on an empty scaffold is the **gate working** (no content yet), not a failure. Report the score. 3. Print next steps: customize `README.md` + `PRD.md`, then "Let's frame the problem" (v0.1).
| Pattern | Fix | |---------|-----| | Hardcoding the seed file list in the skill | Drive `prd-ce-init.sh`; it reads `template_seed` | | Copying the framework (skills/hooks) into the consumer repo | The plugin provides those live — seed only consumer-owned files | | Overwriting an existing `PRD.md`/`SoT/` | Greenfield-only; the seeder skips what exists | | Leaving `PRD.md` at the example's version header | Frontmatter reset to v0.1 happens automatically on a fresh seed | | Treating a readiness BLOCK on a fresh scaffold as a bug | It's the gate working — report the score |
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.…
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,…