create-pmos 0.6.0 → 0.6.1

package/README.md

@@ -333,6 +333,19 @@ Refreshes the skills, concepts, and scripts only. Your records — `state/`, `pl
 `okf/product/` — are yours, and an update never touches them. `pmos/KIT-VERSION` always says
 exactly what you're running.
 
+## What's new in 0.6.1
+
+A completeness fix: two skills the kit already *pointed at* but didn't *ship*.
+
+- **`strategic-brief` and `source-to-concept` now ride in the kit.** The shipped `pmos-router` and
+  `prd` skills recommend `strategic-brief` (make the go/no-go case before a PRD — D61, optional and
+  router-recommended for new-bet feature work), and `ingest-repo` cites `source-to-concept` as its
+  extraction discipline — but neither skill was in the bundle, so those were dangling references.
+  Both are now included. They're file-mode-clean (no backend, no network).
+
+**Upgrade note:** `npx create-pmos@latest --update` brings both in and never touches your `state/`,
+`planning/`, or `okf/product/` records. Purely additive.
+
 ## What's new in 0.6.0
 
 0.5.0 made the kit provider- and model-agnostic. 0.6.0 adds a **face** to the file-mode loop: the

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "create-pmos",
-  "version": "0.6.0",
+  "version": "0.6.1",
   "description": "Scaffold the PMOS portable kit — run the PMOS product-management workflow (initiative → lane-fit spec → contract → build → three gates, with work-type lanes for features, research, maintenance, incidents, and content) entirely inside your own repo, with all state as git-versioned files. `create-pmos workspace` also installs + launches the local Terminal Workspace GUI. No database, no network, no telemetry.",
   "license": "MIT",
   "bin": {

package/payload/KIT-VERSION

@@ -1,3 +1,3 @@
-kernel-source: pmos@58bb72a
-assembled: 2026-07-26
+kernel-source: pmos@005408d
+assembled: 2026-07-27
 mode: vendor

package/payload/skills/source-to-concept.skill

@@ -0,0 +1,67 @@
+---
+name: source-to-concept
+description: Extract a durable OKF concept from a raw ingested source, with situating context, and promote it into the knowledge bundle. SPEC-ONLY in P0; not executable yet.
+maturity_mode: bootstrap
+version: 0.1.0
+owner: wawan
+risk: medium
+category: knowledge
+scope: read:okf/sources, write:okf
+---
+
+> ⚠️ **SPEC-ONLY — NON-EXECUTABLE IN P0.** `maturity_mode: bootstrap`. This file specifies a skill
+> that does **not** run in P0. Seed concepts are authored by hand in P0; automated source→concept
+> extraction activates in a later phase by a PM decision.
+
+# source-to-concept — Extract a Concept from a Source (spec)
+
+This skill (once active) turns a raw artifact in [`/okf/sources/`](/okf/core/concepts/okf-governance.md)
+into a curated OKF concept in `core/concepts/` or `products/<product_slug>/`, preserving provenance
+and conforming to the [OKF spec](/okf/core/concepts/okf-governance.md).
+
+> **Format note:** three-level progressive disclosure
+> ([SKILL-FORMAT](/skills/core/SKILL-FORMAT.md)). Level 1 is the trigger; this body is the spec of
+> the procedure; Level 3 holds rare extraction variants.
+
+## Intended procedure (specification)
+
+1. **Read the source immutably.** Sources in `/okf/sources/` are provenance and are **never edited
+   in place**. Extraction reads from them; it does not modify them.
+2. **Distill one concept per document.** A concept is a single unit of knowledge
+   ([okf-governance](/okf/core/concepts/okf-governance.md)). If a source yields several, produce
+   several concept files, each focused.
+3. **Write spec-conformant frontmatter.** `type` required; `title`, `description`, `tags`,
+   `timestamp` recommended. Do not reintroduce dropped custom fields.
+4. **Add situating context (quality gate — see below).**
+5. **Cross-link.** Bundle-relative links to related concepts; broken links to not-yet-written
+   concepts are tolerated.
+6. **Place by scope.** Core if true across products; under `products/<product_slug>/` if
+   product-specific ([product-slug-convention](/okf/core/concepts/product-slug-convention.md)).
+7. **Record.** Append to [`/okf/log.md`](/okf/log.md) and update [`/okf/index.md`](/okf/index.md).
+
+## Situating-context requirement (quality gate)
+
+> **Every extracted concept body MUST include 1–2 sentences of situating context: where it came
+> from, why it was extracted, and what decision or question it informs.**
+
+This is a hard quality gate: **no active promotion of a concept without situating context.** A
+concept stripped of its origin is an orphaned assertion — the reader cannot judge its authority,
+scope, or relevance. The situating context is what lets a future agent decide whether the concept
+applies to the problem in hand. Extraction that omits it fails the gate and does not promote.
+
+## Promotion path
+
+- Source (immutable) → extracted concept in `core/` or `products/<slug>/` → (if it generalizes
+  across PMs) promoted to [`/okf/shared/`](/okf/core/concepts/okf-governance.md). Promotion is
+  deliberate, never automatic.
+
+## Activation criteria
+
+Graduates from bootstrap when sources are accumulating faster than hand-authoring can keep up and the
+PM decides automated extraction earns its keep. Until then, reference only.
+
+## Level 3 sub-cases (specification)
+
+- Multi-concept sources requiring a split-and-link pass: `source-split.md` (author on activation).
+- Conflicting sources where extraction must reconcile or flag disagreement: `source-conflict.md`
+  (author on activation).

package/payload/skills/strategic-brief.skill

@@ -0,0 +1,57 @@
+---
+name: strategic-brief
+description: Make the strategic case for WHETHER to pursue an initiative — problem, bet, alternatives (incl. do-nothing), cost-of-wrong with an early failure signal, and a go/no-go recommendation — before a PRD is written. OPTIONAL, router-recommended for new-bet feature work (D61); never required, never suggested for prototype/chore/incident/health-anchored work. Output: planning/briefs/<id>-brief.md.
+version: 1.0.0
+owner: wawan
+risk: low
+category: strategy
+scope: read:okf, write:planning/briefs
+---
+
+# strategic-brief — Make the Strategic Case
+
+Produces a strategic brief: the argument for *whether* an initiative should exist, made **before** a
+[PRD](/skills/core/prd.skill) specs *what and why in detail*. The PRD assumes the bet is already
+chosen; the brief is where that choice is argued. **Activated by [D61](/DECISIONS.md)** (2026-07-21)
+after being spec-only since P0 — its own activation criteria (OKRs on a regular cadence; initiative
+volume where informal prioritization strains) are now met.
+
+> **Format note:** three-level progressive disclosure
+> ([SKILL-FORMAT](/skills/core/SKILL-FORMAT.md)). Level 1 above is the trigger; this body is Level 2.
+
+## When to use vs. not (D61 — optional, router-recommended)
+
+- **Use** when the work is a **new bet** — a new product, capability, or direction whose "whether"
+  has not been argued — typically on the [pmos-router](/skills/core/pmos-router.skill)'s
+  recommendation at intake. The PM may always demand one.
+- **Skippable by design.** The brief is never a gate. Skipping it on a new bet is the PM's call;
+  the router recommends, it does not require. (Mandatory briefs recreate the ceremony-pressure
+  failure D58's rubric-recommended stance was designed against.)
+- **Do not use** for prototype-lane work (the lookable artifact IS the whether-test there),
+  chores/incidents, health-anchored upkeep, or increments on an already-accepted direction.
+
+## Procedure
+
+1. **Frame the problem and the bet.** What is the problem, who has it, and what is the specific bet
+   proposed in response.
+2. **Tie to strategy.** Map the bet to a parent objective in the
+   [OKR tree](/okf/core/concepts/okr-tree.md) and to the north-star metric. A brief that ladders to
+   nothing is a no.
+3. **Force alternatives.** At least two, including **"do nothing."** A brief with one option is
+   advocacy, not analysis.
+4. **State the cost of being wrong.** What it costs if the bet fails, and the **early signal** that
+   would say it is failing — this becomes the initiative's kill-condition seed.
+5. **Recommend, with confidence.** A clear **go / no-go / defer**, explicit confidence, written in
+   the [anti-optimism](/okf/core/concepts/okr-anti-optimism.md) stance — report the case against
+   your own recommendation before the case for it.
+
+## Output
+
+- `planning/briefs/<initiative-id>-brief.md` — operational instance, never in the OKF bundle.
+- An accepted brief becomes the PRD's parent rationale (the PRD links it). A **no-go** files the
+  concept into [planning/out-of-scope/](/planning/out-of-scope/README.md) so it is not re-litigated.
+
+## Level 3 sub-cases
+
+- Portfolio-level briefs weighing multiple bets against one budget: `strategic-brief-portfolio.md`
+  (author when first needed).

package/payload/skills-native/source-to-concept/SKILL.md

@@ -0,0 +1,69 @@
+---
+name: source-to-concept
+description: Extract a durable OKF concept from a raw ingested source, with situating context, and promote it into the knowledge bundle. SPEC-ONLY in P0; not executable yet.
+license: MIT
+metadata:
+  pmos-maturity_mode: bootstrap
+  pmos-version: 0.1.0
+  pmos-owner: wawan
+  pmos-risk: medium
+  pmos-category: knowledge
+  pmos-scope: read:okf/sources, write:okf
+---
+
+> ⚠️ **SPEC-ONLY — NON-EXECUTABLE IN P0.** `maturity_mode: bootstrap`. This file specifies a skill
+> that does **not** run in P0. Seed concepts are authored by hand in P0; automated source→concept
+> extraction activates in a later phase by a PM decision.
+
+# source-to-concept — Extract a Concept from a Source (spec)
+
+This skill (once active) turns a raw artifact in [`/okf/sources/`](/okf/core/concepts/okf-governance.md)
+into a curated OKF concept in `core/concepts/` or `products/<product_slug>/`, preserving provenance
+and conforming to the [OKF spec](/okf/core/concepts/okf-governance.md).
+
+> **Format note:** three-level progressive disclosure
+> ([SKILL-FORMAT](/skills/core/SKILL-FORMAT.md)). Level 1 is the trigger; this body is the spec of
+> the procedure; Level 3 holds rare extraction variants.
+
+## Intended procedure (specification)
+
+1. **Read the source immutably.** Sources in `/okf/sources/` are provenance and are **never edited
+   in place**. Extraction reads from them; it does not modify them.
+2. **Distill one concept per document.** A concept is a single unit of knowledge
+   ([okf-governance](/okf/core/concepts/okf-governance.md)). If a source yields several, produce
+   several concept files, each focused.
+3. **Write spec-conformant frontmatter.** `type` required; `title`, `description`, `tags`,
+   `timestamp` recommended. Do not reintroduce dropped custom fields.
+4. **Add situating context (quality gate — see below).**
+5. **Cross-link.** Bundle-relative links to related concepts; broken links to not-yet-written
+   concepts are tolerated.
+6. **Place by scope.** Core if true across products; under `products/<product_slug>/` if
+   product-specific ([product-slug-convention](/okf/core/concepts/product-slug-convention.md)).
+7. **Record.** Append to [`/okf/log.md`](/okf/log.md) and update [`/okf/index.md`](/okf/index.md).
+
+## Situating-context requirement (quality gate)
+
+> **Every extracted concept body MUST include 1–2 sentences of situating context: where it came
+> from, why it was extracted, and what decision or question it informs.**
+
+This is a hard quality gate: **no active promotion of a concept without situating context.** A
+concept stripped of its origin is an orphaned assertion — the reader cannot judge its authority,
+scope, or relevance. The situating context is what lets a future agent decide whether the concept
+applies to the problem in hand. Extraction that omits it fails the gate and does not promote.
+
+## Promotion path
+
+- Source (immutable) → extracted concept in `core/` or `products/<slug>/` → (if it generalizes
+  across PMs) promoted to [`/okf/shared/`](/okf/core/concepts/okf-governance.md). Promotion is
+  deliberate, never automatic.
+
+## Activation criteria
+
+Graduates from bootstrap when sources are accumulating faster than hand-authoring can keep up and the
+PM decides automated extraction earns its keep. Until then, reference only.
+
+## Level 3 sub-cases (specification)
+
+- Multi-concept sources requiring a split-and-link pass: `source-split.md` (author on activation).
+- Conflicting sources where extraction must reconcile or flag disagreement: `source-conflict.md`
+  (author on activation).

package/payload/skills-native/strategic-brief/SKILL.md

@@ -0,0 +1,59 @@
+---
+name: strategic-brief
+description: Make the strategic case for WHETHER to pursue an initiative — problem, bet, alternatives (incl. do-nothing), cost-of-wrong with an early failure signal, and a go/no-go recommendation — before a PRD is written. OPTIONAL, router-recommended for new-bet feature work (D61); never required, never suggested for prototype/chore/incident/health-anchored work. Output: planning/briefs/<id>-brief.md.
+license: MIT
+metadata:
+  pmos-version: 1.0.0
+  pmos-owner: wawan
+  pmos-risk: low
+  pmos-category: strategy
+  pmos-scope: read:okf, write:planning/briefs
+---
+
+# strategic-brief — Make the Strategic Case
+
+Produces a strategic brief: the argument for *whether* an initiative should exist, made **before** a
+[PRD](/skills/core/prd.skill) specs *what and why in detail*. The PRD assumes the bet is already
+chosen; the brief is where that choice is argued. **Activated by [D61](/DECISIONS.md)** (2026-07-21)
+after being spec-only since P0 — its own activation criteria (OKRs on a regular cadence; initiative
+volume where informal prioritization strains) are now met.
+
+> **Format note:** three-level progressive disclosure
+> ([SKILL-FORMAT](/skills/core/SKILL-FORMAT.md)). Level 1 above is the trigger; this body is Level 2.
+
+## When to use vs. not (D61 — optional, router-recommended)
+
+- **Use** when the work is a **new bet** — a new product, capability, or direction whose "whether"
+  has not been argued — typically on the [pmos-router](/skills/core/pmos-router.skill)'s
+  recommendation at intake. The PM may always demand one.
+- **Skippable by design.** The brief is never a gate. Skipping it on a new bet is the PM's call;
+  the router recommends, it does not require. (Mandatory briefs recreate the ceremony-pressure
+  failure D58's rubric-recommended stance was designed against.)
+- **Do not use** for prototype-lane work (the lookable artifact IS the whether-test there),
+  chores/incidents, health-anchored upkeep, or increments on an already-accepted direction.
+
+## Procedure
+
+1. **Frame the problem and the bet.** What is the problem, who has it, and what is the specific bet
+   proposed in response.
+2. **Tie to strategy.** Map the bet to a parent objective in the
+   [OKR tree](/okf/core/concepts/okr-tree.md) and to the north-star metric. A brief that ladders to
+   nothing is a no.
+3. **Force alternatives.** At least two, including **"do nothing."** A brief with one option is
+   advocacy, not analysis.
+4. **State the cost of being wrong.** What it costs if the bet fails, and the **early signal** that
+   would say it is failing — this becomes the initiative's kill-condition seed.
+5. **Recommend, with confidence.** A clear **go / no-go / defer**, explicit confidence, written in
+   the [anti-optimism](/okf/core/concepts/okr-anti-optimism.md) stance — report the case against
+   your own recommendation before the case for it.
+
+## Output
+
+- `planning/briefs/<initiative-id>-brief.md` — operational instance, never in the OKF bundle.
+- An accepted brief becomes the PRD's parent rationale (the PRD links it). A **no-go** files the
+  concept into [planning/out-of-scope/](/planning/out-of-scope/README.md) so it is not re-litigated.
+
+## Level 3 sub-cases
+
+- Portfolio-level briefs weighing multiple bets against one budget: `strategic-brief-portfolio.md`
+  (author when first needed).