Add committed, browsable dist/ download shelf

Make the library easy and educational to access for non-technical PMs: browse to /dist on GitHub, read a plain-language README, scan CATALOG.md, and download a skill or a pack directly — no terminal, no Releases tab. - dist/README.md + dist/CATALOG.md generated from skills/ (never drift) - dist/<skill>.zip: 56 individual upload-ready skill ZIPs (flat) - dist/packages/: curated bundles + Codex package - scripts/build-dist.sh: regenerates the shelf from skills/ (repeatable) - .gitignore: commit the curated shelf, ignore intermediate build scratch (fixed pattern so press-release.zip is not caught by the master-artifact rule) - docs/RELEASE-PACKAGING.md: record the intentional committed-dist policy Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-09-14 20:06:57 +08:00 · 2026-07-08 11:56:32 -04:00
parent 9c6b7a3fe6
commit c146d2a784
68 changed files with 329 additions and 3 deletions
@@ -10,7 +10,15 @@ __pycache__/
 .Python
 build/
 develop-eggs/
-dist/
+# NOTE: dist/ is an INTENTIONALLY COMMITTED, browsable distribution folder
+# (dist/README.md, dist/CATALOG.md, individual skill .zips, and dist/packages/).
+# See docs/RELEASE-PACKAGING.md. We ignore only the intermediate build scratch
+# that scripts/build-dist.sh regenerates and then curates into the tracked layout:
+dist/release/
+dist/skill-zips/
+dist/claude-desktop/
+dist/codex/
+dist/Product-Manager-Skills-*-release.zip
 downloads/
 eggs/
 .eggs/
@@ -0,0 +1,82 @@
+# Skill Catalog
+
+All **56 skills** in this library. Each links to its individual download ZIP in this folder — click, download, unzip, and upload the `SKILL.md` to Claude. No terminal required.
+
+> New here? Read [`README.md`](README.md) first — it explains how to pick a pack and install.
+
+## Component Skills (23)
+
+_Self-contained artifacts and templates._
+
+| Skill | What it does |
+|---|---|
+| [`altitude-horizon-framework`](altitude-horizon-framework.zip) | Understand the PM-to-Director transition through altitude and horizon thinking. Use when diagnosing scope, time-horizon, or leadership-level gaps. |
+| [`company-research`](company-research.zip) | Create a company research brief with executive quotes, product strategy, and org context. Use when preparing for interviews, competitive analysis, partnerships, or market-entry work. |
+| [`customer-journey-map`](customer-journey-map.zip) | Create a customer journey map across stages, touchpoints, actions, emotions, and metrics. Use when diagnosing a broken experience or aligning a team on the full customer flow. |
+| [`eol-message`](eol-message.zip) | Write a clear, empathetic EOL announcement with rationale, customer impact, and next steps. Use when retiring a product, feature, or plan without creating avoidable confusion. |
+| [`epic-hypothesis`](epic-hypothesis.zip) | Frame an epic as a testable hypothesis with target user, expected outcome, and validation method. Use when defining a major initiative before roadmap, discovery, or delivery planning. |
+| [`finance-metrics-quickref`](finance-metrics-quickref.zip) | Look up SaaS finance metrics, formulas, and benchmarks fast. Use when you need a quick metric definition, formula, or benchmark during analysis. |
+| [`jobs-to-be-done`](jobs-to-be-done.zip) | Uncover customer jobs, pains, and gains in a structured JTBD format. Use when clarifying unmet needs, repositioning a product, or improving discovery and messaging. |
+| [`pestel-analysis`](pestel-analysis.zip) | Analyze political, economic, social, technological, environmental, and legal forces. Use when external market shifts could materially affect a product, roadmap, or strategy. |
+| [`pol-probe`](pol-probe.zip) | Define a Proof of Life probe to test a risky hypothesis cheaply. Use when you need harsh truth before building real product. |
+| [`positioning-statement`](positioning-statement.zip) | Create a Geoffrey Moore-style positioning statement. Use when clarifying who you serve, what problem you solve, your category, and why you're different from alternatives. |
+| [`press-release`](press-release.zip) | Write an Amazon-style press release that defines customer value before building. Use when aligning stakeholders on a new product, feature, or strategic bet. |
+| [`problem-statement`](problem-statement.zip) | Write a user-centered problem statement with who is blocked, what they are trying to do, why it matters, and how it feels. Use when framing discovery, prioritization, or a PRD. |
+| [`product-sense-interview-answer`](product-sense-interview-answer.zip) | Structure a spoken PM product-sense answer with assumptions, segmentation, pain-point prioritization, and MVP tradeoffs. Use when practicing design, improve, or build-next interview questions. |
+| [`proto-persona`](proto-persona.zip) | Create a proto-persona from current research, market signals, and team knowledge. Use when you need a working customer profile before deeper validation. |
+| [`recommendation-canvas`](recommendation-canvas.zip) | Evaluate an AI product idea across outcomes, hypotheses, risks, and positioning. Use when deciding whether an AI solution deserves investment or recommendation. |
+| [`saas-economics-efficiency-metrics`](saas-economics-efficiency-metrics.zip) | Evaluate SaaS unit economics and capital efficiency. Use when deciding whether the business can scale efficiently or needs correction. |
+| [`saas-revenue-growth-metrics`](saas-revenue-growth-metrics.zip) | Calculate SaaS revenue, retention, and growth metrics. Use when diagnosing momentum, churn, expansion, or product-market-fit signals. |
+| [`stakeholder-identification`](stakeholder-identification.zip) | Map every stakeholder before engaging anyone. Use when launching an initiative, scoping discovery, or building an engagement plan from scratch. |
+| [`stakeholder-mapping`](stakeholder-mapping.zip) | Prioritize stakeholders using two complementary grids. Use when setting engagement strategy and surfacing whose voice needs elevating after stakeholder identification. |
+| [`storyboard`](storyboard.zip) | Create a six-frame storyboard that shows a user's journey from problem to solution. Use when you need a fast narrative for alignment, concept reviews, or demos. |
+| [`user-story`](user-story.zip) | Create user stories with Mike Cohn format and Gherkin acceptance criteria. Use when turning user needs into development-ready work with clear outcomes and testable conditions. |
+| [`user-story-mapping`](user-story-mapping.zip) | Create a user story map that lays out activities, steps, tasks, and release slices. Use when planning a workflow, backlog, or MVP around the user journey. |
+| [`user-story-splitting`](user-story-splitting.zip) | Break a large story or epic into smaller deliverable stories using proven split patterns. Use when backlog items are too big for estimation, sequencing, or independent release. |
+
+## Interactive Skills (26)
+
+_Guided, multi-turn advisors that ask then recommend._
+
+| Skill | What it does |
+|---|---|
+| [`acquisition-channel-advisor`](acquisition-channel-advisor.zip) | Evaluate acquisition channels using unit economics, customer quality, and scalability. Use when deciding whether to scale, test, or kill a growth channel. |
+| [`agent-orchestration-advisor`](agent-orchestration-advisor.zip) | Design multi-agent AI workflows with clear boundaries, handoffs, and monitoring. Use when a complex PM task should run as parallel specialized agents instead of one linear process. |
+| [`ai-shaped-readiness-advisor`](ai-shaped-readiness-advisor.zip) | Assess whether your product work is AI-first or AI-shaped. Use when evaluating AI maturity and choosing the next team capability to build. |
+| [`business-health-diagnostic`](business-health-diagnostic.zip) | Diagnose SaaS business health across growth, retention, efficiency, and capital. Use when preparing a business review or prioritizing urgent fixes. |
+| [`context-engineering-advisor`](context-engineering-advisor.zip) | Diagnose context stuffing vs. context engineering. Use when an AI workflow feels bloated, brittle, or hard to steer reliably. |
+| [`customer-journey-mapping-workshop`](customer-journey-mapping-workshop.zip) | Run a customer journey mapping workshop with adaptive questions and outputs. Use when you need to map stages, actions, emotions, pain points, and opportunities for a persona and scenario. |
+| [`derisk-measurement-advisor`](derisk-measurement-advisor.zip) | Identify what to measure, test, or track to de-risk a product or AI idea. Use when stress-testing an idea across internal (DUFV) and external (PESTEL) dimensions. |
+| [`director-readiness-advisor`](director-readiness-advisor.zip) | Guide the PM-to-Director transition across preparing, interviewing, landing, and recalibrating. Use when leadership scope is changing and you need practical coaching. |
+| [`discovery-interview-prep`](discovery-interview-prep.zip) | Plan customer discovery interviews with the right goal, segment, constraints, and method. Use when preparing interviews for problem validation, churn research, or new product ideas. |
+| [`epic-breakdown-advisor`](epic-breakdown-advisor.zip) | Break down epics into user stories with Humanizing Work split patterns. Use when a backlog item is too large to estimate, sequence, or deliver safely. |
+| [`feature-investment-advisor`](feature-investment-advisor.zip) | Evaluate feature investments using revenue impact, cost structure, ROI, and strategy. Use when deciding whether a feature deserves investment. |
+| [`finance-based-pricing-advisor`](finance-based-pricing-advisor.zip) | Evaluate pricing changes using ARPU, conversion, churn risk, NRR, and payback. Use when deciding whether a pricing move should ship. |
+| [`incoming-request-advisor`](incoming-request-advisor.zip) | Decode an incoming message into a structured breakdown that separates the literal ask from the job-to-be-done. Use before replying to a loaded Slack ping, email, mandate, or escalation. |
+| [`lean-ux-canvas`](lean-ux-canvas.zip) | Guide teams through Lean UX Canvas v2. Use when framing a business problem, surfacing assumptions, and defining what to learn next. |
+| [`opportunity-solution-tree`](opportunity-solution-tree.zip) | Build an Opportunity Solution Tree from outcomes to opportunities, solutions, and tests. Use when a stakeholder request needs problem framing before you decide what to build. |
+| [`organic-growth-advisor`](organic-growth-advisor.zip) | Identify which organic growth path to pursue — new segments, geographies, channels, or products. Use when diagnosing where a growth constraint lives and which McKinsey growth level to act on next. |
+| [`pm-skill-creator`](pm-skill-creator.zip) | Design a new PM skill through guided conversation. Use when you have raw content or an idea and want to shape it into a compliant skill. |
+| [`pol-probe-advisor`](pol-probe-advisor.zip) | Select the right Proof of Life (PoL) probe based on hypothesis, risk, and resources. Use this to match the validation method to the real learning goal, not tooling comfort. |
+| [`positioning-workshop`](positioning-workshop.zip) | Run a positioning workshop that surfaces target customer, unmet need, category, benefits, and differentiation. Use when your product messaging feels fuzzy, generic, or misaligned. |
+| [`prioritization-advisor`](prioritization-advisor.zip) | Choose a prioritization framework based on stage, team context, and stakeholder needs. Use when deciding between RICE, ICE, value/effort, or another scoring approach. |
+| [`problem-framing-canvas`](problem-framing-canvas.zip) | Guide teams through MITRE's Problem Framing Canvas. Use when you need a clearer problem statement before jumping to solutions. |
+| [`stakeholder-engagement-advisor`](stakeholder-engagement-advisor.zip) | Plan engagement for a specific stakeholder. Use when preparing an outreach, navigating resistance, or aligning a critical relationship before a key milestone. |
+| [`tam-sam-som-calculator`](tam-sam-som-calculator.zip) | Calculate TAM, SAM, and SOM with explicit assumptions, methods, and caveats. Use when sizing a market for a product idea, business case, or executive review. |
+| [`user-story-mapping-workshop`](user-story-mapping-workshop.zip) | Run a user story mapping workshop with adaptive questions and a structured map output. Use when you need backbone activities, tasks, and release slices for a workflow. |
+| [`vp-cpo-readiness-advisor`](vp-cpo-readiness-advisor.zip) | Guide the transition to VP or CPO across preparing, interviewing, landing, and recalibrating. Use when executive product scope is changing fast. |
+| [`workshop-facilitation`](workshop-facilitation.zip) | Facilitate workshop sessions in a one-step, multi-turn flow. Use when an interactive skill needs consistent pacing, options, and progress tracking. |
+
+## Workflow Skills (7)
+
+_End-to-end processes that orchestrate other skills._
+
+| Skill | What it does |
+|---|---|
+| [`company-intel`](company-intel.zip) | Research a company, industry, or competitor set using web search and seven analytical lenses. Use when you need structured intel that feeds downstream PM skills. |
+| [`discovery-process`](discovery-process.zip) | Run a full discovery cycle from problem hypothesis to validated solution. Use when a team needs a structured path through framing, interviews, synthesis, and experiments. |
+| [`executive-onboarding-playbook`](executive-onboarding-playbook.zip) | Plan a VP or CPO 30-60-90 day diagnostic onboarding path. Use when entering a new executive product role and avoiding premature change. |
+| [`prd-development`](prd-development.zip) | Build a structured PRD that connects problem, users, solution, and success criteria. Use when turning discovery notes into an engineering-ready document for a major initiative. |
+| [`product-strategy-session`](product-strategy-session.zip) | Run an end-to-end product strategy session across positioning, discovery, and roadmap planning. Use when a team needs validated direction before committing to execution. |
+| [`roadmap-planning`](roadmap-planning.zip) | Plan a strategic roadmap across prioritization, epic definition, stakeholder alignment, and sequencing. Use when turning strategy into a release plan that teams can execute. |
+| [`skill-authoring-workflow`](skill-authoring-workflow.zip) | Turn raw PM content into a compliant, publish-ready skill. Use when creating or updating a repo skill without breaking standards. |
@@ -0,0 +1,41 @@
+# Product Manager Skills — Downloads
+
+Welcome. This folder is the **easy download shelf** for the library — no code, no
+terminal. Grab what you want, unzip it, and upload the skills to Claude.
+
+There are **56 skills** in total. Two ways to get them:
+
+## 1. Grab a bundle (recommended)
+
+Bundles live in [`packages/`](packages/). Download one ZIP, unzip it, and you'll
+find upload-ready skill ZIPs inside.
+
+| Bundle | Best for |
+|---|---|
+| [`pm-skills-starter-pack.zip`](packages/pm-skills-starter-pack.zip) | Most PMs — a small, practical starter set |
+| [`02-discovery-pack.zip`](packages/02-discovery-pack.zip) | Understanding customers, problems, and opportunities |
+| [`03-strategy-pack.zip`](packages/03-strategy-pack.zip) | Positioning, market thinking, product direction |
+| [`04-delivery-pack.zip`](packages/04-delivery-pack.zip) | Stories, epics, PRDs, roadmap execution |
+| [`05-ai-pm-pack.zip`](packages/05-ai-pm-pack.zip) | AI product work |
+| [`99-all-skills-pack.zip`](packages/99-all-skills-pack.zip) | Everything — all 56 skills |
+| [`pm-skills-codex.zip`](packages/pm-skills-codex.zip) | OpenAI Codex users (`.agents/skills` + `AGENTS.md`) |
+
+## 2. Grab one skill at a time
+
+Every skill has its own ZIP right here in this folder. Browse them in
+[`CATALOG.md`](CATALOG.md), then click the one you want.
+
+## How to install (Claude Desktop / Web)
+
+1. Download a bundle (or an individual skill ZIP).
+2. If it's a bundle, unzip it to reveal the individual skill ZIPs.
+3. In Claude, open **Skills** and upload the skill ZIP(s).
+4. Start asking better product questions.
+
+Full step-by-step guides live in [`../docs/`](../docs): `INSTALL-CLAUDE-DESKTOP.md`,
+`INSTALL-CLAUDE-CODE.md`, and `INSTALL-CODEX.md`.
+
+---
+
+_This folder is generated by `scripts/build-dist.sh` from the canonical `skills/`
+source. Don't edit files here by hand — re-run the script to refresh them._
@@ -8,6 +8,42 @@ The release experience should feel simple:
 Download one pack. Unzip it. Upload the skill ZIPs inside. Start asking better product questions.
 ```

+## `dist/` Is a Committed, Browsable Download Shelf
+
+**Policy (intentional):** `dist/` is checked into the repo so anyone — including
+non-technical PMs who never touch a terminal — can browse to
+`https://github.com/deanpeters/Product-Manager-Skills/tree/main/dist`, read a
+plain-language `README.md`, scan the `CATALOG.md`, and download a skill or a pack
+directly. Making the library easy and educational to access is the point; hiding
+the ZIPs behind the Releases tab worked against that.
+
+The **tracked** layout (produced by `scripts/build-dist.sh`):
+
+```text
+dist/
+  README.md              # plain-language landing page (renders on GitHub)
+  CATALOG.md             # browsable catalog of every skill, by category
+  <skill-name>.zip       # individual, upload-ready skill ZIPs (flat)
+  packages/
+    pm-skills-starter-pack.zip
+    02-discovery-pack.zip
+    03-strategy-pack.zip
+    04-delivery-pack.zip
+    05-ai-pm-pack.zip
+    99-all-skills-pack.zip
+    pm-skills-codex.zip
+```
+
+`README.md` and `CATALOG.md` are **generated from `skills/`**, so they never drift
+from the source. Re-run `scripts/build-dist.sh` after adding or changing skills.
+
+The intermediate build directories (`dist/claude-desktop/`, `dist/codex/`,
+`dist/skill-zips/`, `dist/release/`, and the master `dist/*-release.zip`) remain
+**git-ignored** — only the curated shelf above is committed.
+
+GitHub Releases still exist and are still produced on `v*` tags; the committed
+`dist/` shelf is a complement to them, not a replacement.
+
 ## Maintainer Flow

 From the repo root:
@@ -84,8 +120,8 @@ Build everything:

 ## Important Rules

- Do not edit files under `dist/` directly.
- Do not commit generated ZIP files unless the repo intentionally changes that policy.
+- Do not edit files under `dist/` by hand — they are generated. Re-run `scripts/build-dist.sh` to refresh the committed shelf.
+- The committed `dist/` shelf (README, CATALOG, skill ZIPs, `packages/`) **is** intentionally version-controlled; the intermediate build dirs are git-ignored. This is the "intentional policy change" the older rule referred to.
 - Claude Desktop/Web packs are ZIPs of individual upload-ready skill ZIPs. Users unzip the pack first, then upload the skill ZIPs inside to Claude.
 - Codex packages are expanded `.agents/skills` folders inside a ZIP, not ZIPs of ZIPs.
 - Do not remove `.claude-plugin/marketplace.json`; Claude Code users rely on the marketplace path.
@@ -0,0 +1,159 @@
+#!/usr/bin/env bash
+#
+# build-dist.sh - Assemble the committed, browsable dist/ distribution folder.
+#
+# This is the folder users can navigate to at:
+#   https://github.com/deanpeters/Product-Manager-Skills/tree/main/dist
+#
+# Layout produced (all tracked in git):
+#   dist/README.md              plain-language landing page (renders on GitHub)
+#   dist/CATALOG.md             browsable catalog of every skill, by category
+#   dist/<skill>.zip            individual, upload-ready skill ZIPs (flat)
+#   dist/packages/<pack>.zip    curated bundles + the Codex package
+#
+# It runs the existing build-release.sh (which validates + builds every
+# artifact), then curates the tracked layout and regenerates the two docs.
+# Nothing under dist/ is hand-maintained; re-run this to refresh it.
+
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
+DIST="$ROOT/dist"
+
+echo "[1/4] Building all release artifacts (validate + packs + codex + skill zips)"
+bash "$SCRIPT_DIR/build-release.sh" >/dev/null
+echo "  done"
+
+echo "[2/4] Curating tracked layout"
+# Clear the tracked parts (leave the ignored build scratch dirs in place)
+find "$DIST" -maxdepth 1 -type f -name '*.zip' -delete 2>/dev/null || true
+rm -rf "$DIST/packages"
+mkdir -p "$DIST/packages"
+
+# Individual skill ZIPs -> dist/ root (flat)
+cp "$DIST"/skill-zips/*.zip "$DIST"/
+skill_zip_count="$(find "$DIST" -maxdepth 1 -type f -name '*.zip' | wc -l | tr -d ' ')"
+
+# Curated bundles + codex -> dist/packages/
+for p in pm-skills-starter-pack 02-discovery-pack 03-strategy-pack \
+         04-delivery-pack 05-ai-pm-pack 99-all-skills-pack; do
+  cp "$DIST/claude-desktop/$p.zip" "$DIST/packages/"
+done
+cp "$DIST/codex/pm-skills-codex.zip" "$DIST/packages/"
+echo "  $skill_zip_count individual skill ZIPs, $(find "$DIST/packages" -name '*.zip' | wc -l | tr -d ' ') packages"
+
+echo "[3/4] Generating CATALOG.md and README.md"
+python3 - "$ROOT" <<'PY'
+import os, sys, glob
+try:
+    import yaml
+except ImportError:
+    sys.exit("PyYAML required (used elsewhere in this repo)")
+
+root = sys.argv[1]
+dist = os.path.join(root, "dist")
+skills_dir = os.path.join(root, "skills")
+
+def frontmatter(path):
+    text = open(path, encoding="utf-8").read()
+    if not text.startswith("---"):
+        return {}
+    end = text.find("\n---", 3)
+    return yaml.safe_load(text[3:end]) or {}
+
+skills = []
+for p in sorted(glob.glob(os.path.join(skills_dir, "*", "SKILL.md"))):
+    fm = frontmatter(p)
+    name = fm.get("name") or os.path.basename(os.path.dirname(p))
+    skills.append({
+        "name": name,
+        "type": (fm.get("type") or "other").lower(),
+        "desc": (fm.get("description") or "").strip().strip('"'),
+    })
+
+TYPES = [
+    ("component", "Component Skills", "Self-contained artifacts and templates."),
+    ("interactive", "Interactive Skills", "Guided, multi-turn advisors that ask then recommend."),
+    ("workflow", "Workflow Skills", "End-to-end processes that orchestrate other skills."),
+]
+by_type = {t: [s for s in skills if s["type"] == t] for t, _, _ in TYPES}
+total = len(skills)
+
+# ---- CATALOG.md ----
+lines = [
+    "# Skill Catalog",
+    "",
+    f"All **{total} skills** in this library. Each links to its individual "
+    "download ZIP in this folder — click, download, unzip, and upload the "
+    "`SKILL.md` to Claude. No terminal required.",
+    "",
+    "> New here? Read [`README.md`](README.md) first — it explains how to pick "
+    "a pack and install.",
+    "",
+]
+for key, title, blurb in TYPES:
+    rows = sorted(by_type[key], key=lambda s: s["name"])
+    if not rows:
+        continue
+    lines += [f"## {title} ({len(rows)})", "", f"_{blurb}_", "",
+              "| Skill | What it does |", "|---|---|"]
+    for s in rows:
+        lines.append(f"| [`{s['name']}`]({s['name']}.zip) | {s['desc']} |")
+    lines.append("")
+open(os.path.join(dist, "CATALOG.md"), "w", encoding="utf-8").write("\n".join(lines))
+
+# ---- README.md ----
+readme = f"""# Product Manager Skills — Downloads
+
+Welcome. This folder is the **easy download shelf** for the library — no code, no
+terminal. Grab what you want, unzip it, and upload the skills to Claude.
+
+There are **{total} skills** in total. Two ways to get them:
+
+## 1. Grab a bundle (recommended)
+
+Bundles live in [`packages/`](packages/). Download one ZIP, unzip it, and you'll
+find upload-ready skill ZIPs inside.
+
+| Bundle | Best for |
+|---|---|
+| [`pm-skills-starter-pack.zip`](packages/pm-skills-starter-pack.zip) | Most PMs — a small, practical starter set |
+| [`02-discovery-pack.zip`](packages/02-discovery-pack.zip) | Understanding customers, problems, and opportunities |
+| [`03-strategy-pack.zip`](packages/03-strategy-pack.zip) | Positioning, market thinking, product direction |
+| [`04-delivery-pack.zip`](packages/04-delivery-pack.zip) | Stories, epics, PRDs, roadmap execution |
+| [`05-ai-pm-pack.zip`](packages/05-ai-pm-pack.zip) | AI product work |
+| [`99-all-skills-pack.zip`](packages/99-all-skills-pack.zip) | Everything — all {total} skills |
+| [`pm-skills-codex.zip`](packages/pm-skills-codex.zip) | OpenAI Codex users (`.agents/skills` + `AGENTS.md`) |
+
+## 2. Grab one skill at a time
+
+Every skill has its own ZIP right here in this folder. Browse them in
+[`CATALOG.md`](CATALOG.md), then click the one you want.
+
+## How to install (Claude Desktop / Web)
+
+1. Download a bundle (or an individual skill ZIP).
+2. If it's a bundle, unzip it to reveal the individual skill ZIPs.
+3. In Claude, open **Skills** and upload the skill ZIP(s).
+4. Start asking better product questions.
+
+Full step-by-step guides live in [`../docs/`](../docs): `INSTALL-CLAUDE-DESKTOP.md`,
+`INSTALL-CLAUDE-CODE.md`, and `INSTALL-CODEX.md`.
+
+---
+
+_This folder is generated by `scripts/build-dist.sh` from the canonical `skills/`
+source. Don't edit files here by hand — re-run the script to refresh them._
+"""
+open(os.path.join(dist, "README.md"), "w", encoding="utf-8").write(readme)
+print(f"  catalog + readme written ({total} skills)")
+PY
+
+echo "[4/4] dist/ assembled and ready to commit"
+echo
+echo "Tracked layout:"
+echo "  dist/README.md"
+echo "  dist/CATALOG.md"
+echo "  dist/*.zip                ($skill_zip_count individual skills)"
+echo "  dist/packages/*.zip       (bundles + codex)"