skillpacks 0.1.0

package/packs/alignment-page-admin/claude/upgrade-alignment-pages/SKILL.md

@@ -0,0 +1,106 @@
+---
+name: upgrade-alignment-pages
+description: Audit and explicitly upgrade generated alignment/*.html review pages to the current local alignment-page standard while preserving page-specific context
+type: ops
+version: v0.1
+argument-hint: "[--repo <path>] [--apply] [alignment/*.html...]"
+---
+
+# Upgrade Alignment Pages
+
+Invoke as `/upgrade-alignment-pages`.
+
+Use this skill when a repository already has generated `alignment/*.html` review pages and the user wants to audit or update them against the current local alignment-page convention. This skill targets generated alignment HTML artifacts only.
+
+## Inputs
+
+- Default target repository: current working directory.
+- Optional `--repo <path>` to target another repository.
+- Optional explicit page paths under the target repository's `alignment/` directory.
+- Optional `--apply`, or clear user wording such as "apply the upgrade" or "upgrade these pages", to allow page rewrites.
+
+## Mode
+
+- Default mode is audit/dry-run.
+- The skill name alone is not apply intent; do not modify files unless the visible user request explicitly asks to apply or upgrade existing pages.
+- In audit/dry-run mode, inspect pages and report drift without creating, editing, moving, or deleting any files.
+
+## Process
+
+1. Resolve scope:
+   - Locate the project-root `alignment/` directory; stop if absent.
+   - Enumerate `alignment/*.html`, excluding `alignment/index.html`.
+   - If the user provided page paths, include only those paths after confirming they are inside the project-root `alignment/` directory.
+
+2. Load local standards:
+   - Read applicable local convention sources from `AGENTS.md`, `CLAUDE.md`, and active bundled `ALIGNMENT-PAGE.md` files found under `global/`, `packs/`, `.claude/skills/`, and `.codex/skills/`.
+   - Treat those local files as read-only standards. Do not fetch external standards.
+   - Extract the current required HTML behaviors: dark-mode styling, inline approval gates, section feedback controls, feedback-only YAML, final answer YAML, copy fallback behavior, unanswered-question handling, archive-before-replace behavior, and diff/change highlighting for updates.
+
+3. Audit every selected page:
+   - Read the whole HTML file before judging it.
+   - Identify page-specific substance: title, meta/context, research findings, evidence/source matrices, assumptions, decisions, open questions, approval gates, review notes, proposed file changes, prior user feedback, and any page-specific scripts.
+   - Report missing or stale standard features per page.
+   - Classify each page as `current`, `upgrade-needed`, or `blocked-content-loss-risk`.
+
+4. Stop on content-loss risk:
+   - If a page's structure is too ambiguous to upgrade while preserving substantive content, do not rewrite it.
+   - Report exactly what content could not be mapped and what human decision is needed.
+
+4b. Batch-mode handoff (apply mode only):
+   - Count pages classified as `upgrade-needed` (excluding `blocked-content-loss-risk`).
+   - If count > 2:
+     - Generate a phase in `tasks/todo.md` titled "## Phase: Upgrade Alignment Pages" with:
+       - Execution Profile: serial
+       - A Context block listing the standards sources discovered in step 2 and the archive timestamp path (`docs/history/archive/YYYY-MM-DD/HHMMSS/`)
+       - One checklist step per upgrade-needed page: `- [ ] Upgrade alignment/<filename>.html — archive original, rewrite to current standard preserving all content, verify content preservation`
+       - A final step: `- [ ] Run /compile-central-alignment and verify all archives; commit and push`
+       - Acceptance criteria matching the audit findings
+     - If `tasks/todo.md` already has unchecked items, append the phase at the bottom with a separator (`---`) and warn the user about pre-existing items.
+     - Output the full audit report.
+     - Report: "Generated exec-loop task plan with N steps. Recommended next command: /exec"
+     - Stop. Do not modify any HTML files.
+   - If count <= 2: proceed to step 5 (inline apply).
+
+5. Apply only when explicit:
+   - Before replacing each page, archive the original to `docs/history/archive/YYYY-MM-DD/HHMMSS/alignment/<filename>.html`.
+   - Rewrite the page contextually from the original, preserving page-specific research, decisions, questions, gates, review context, and user feedback.
+   - Add or modernize missing standard elements without replacing the page with a generic template.
+   - Preserve relative links and keep the page self-contained unless the original already used explicit external resources.
+   - Highlight upgrade changes where useful with inline notes, a change summary section, or scoped diff styling.
+
+6. Verify after apply:
+   - Confirm every changed page has a matching archive copy.
+   - Re-open each changed page textually and confirm the preserved title, decisions/findings, questions, and gates still exist.
+   - Run or recommend `/compile-central-alignment` so `alignment/index.html` reflects updated page metadata.
+
+## Audit Report
+
+Include:
+
+- Target repository and mode.
+- Standards sources read.
+- Pages inspected and pages excluded.
+- Per-page status with missing standard features.
+- Content preservation risks or blockers.
+- In apply mode, archive paths and changed page paths.
+- Verification performed.
+- Next action: usually `/compile-central-alignment` after successful apply, or no mutation needed when all pages are current.
+- In batch mode: the generated `tasks/todo.md` phase with exec-loop steps and the recommended `/exec` command.
+
+## Constraints
+
+- Do not edit `CLAUDE.md`, `AGENTS.md`, any `SKILL.md`, or any bundled `ALIGNMENT-PAGE.md` file.
+- Do not modify non-alignment HTML files.
+- Do not modify `alignment/index.html`; leave index regeneration to `/compile-central-alignment`.
+- Do not rewrite pages in audit/dry-run mode.
+- Do not replace page-specific content with a generic template.
+- Stop and report when an upgrade is likely to lose research, decisions, questions, gates, or review context.
+- Do not create or modify GitHub Actions workflows.
+
+## Default Shipping Contract
+
+- **Audit mode:** no file mutations; no commit or push.
+- **Apply mode (inline, ≤2 pages):** modified generated alignment pages and archive copies are normal repo artifacts. Follow the target repository's shipping rules after verification.
+- **Apply mode (batch, >2 pages):** generates `tasks/todo.md` phase only; does not modify any HTML files. Commit the task plan, then hand off to `/exec`.
+- **Default next-step routing:** after successful inline apply, `Recommended next command: /compile-central-alignment`; after batch-mode handoff, `Recommended next command: /exec`; otherwise report the audit result and recommend no follow-up skill when no upgrades are needed.

package/packs/alignment-page-admin/claude/upgrade-alignment-pages/archive/v0.0/SKILL.md

@@ -0,0 +1,89 @@
+---
+name: upgrade-alignment-pages
+description: Audit and explicitly upgrade generated alignment/*.html review pages to the current local alignment-page standard while preserving page-specific context
+type: utility
+version: v0.0
+argument-hint: "[--repo <path>] [--apply] [alignment/*.html...]"
+---
+
+# Upgrade Alignment Pages
+
+Invoke as `/upgrade-alignment-pages`.
+
+Use this skill when a repository already has generated `alignment/*.html` review pages and the user wants to audit or update them against the current local alignment-page convention. This skill targets generated alignment HTML artifacts only.
+
+## Inputs
+
+- Default target repository: current working directory.
+- Optional `--repo <path>` to target another repository.
+- Optional explicit page paths under the target repository's `alignment/` directory.
+- Optional `--apply`, or clear user wording such as "apply the upgrade" or "upgrade these pages", to allow page rewrites.
+
+## Mode
+
+- Default mode is audit/dry-run.
+- The skill name alone is not apply intent; do not modify files unless the visible user request explicitly asks to apply or upgrade existing pages.
+- In audit/dry-run mode, inspect pages and report drift without creating, editing, moving, or deleting any files.
+
+## Workflow
+
+1. Resolve scope:
+   - Locate the project-root `alignment/` directory; stop if absent.
+   - Enumerate `alignment/*.html`, excluding `alignment/index.html`.
+   - If the user provided page paths, include only those paths after confirming they are inside the project-root `alignment/` directory.
+
+2. Load local standards:
+   - Read applicable local convention sources from `AGENTS.md`, `CLAUDE.md`, and active bundled `ALIGNMENT-PAGE.md` files found under `global/`, `packs/`, `.claude/skills/`, and `.codex/skills/`.
+   - Treat those local files as read-only standards. Do not fetch external standards.
+   - Extract the current required HTML behaviors: dark-mode styling, inline approval gates, section feedback controls, feedback-only YAML, final answer YAML, copy fallback behavior, unanswered-question handling, archive-before-replace behavior, and diff/change highlighting for updates.
+
+3. Audit every selected page:
+   - Read the whole HTML file before judging it.
+   - Identify page-specific substance: title, meta/context, research findings, evidence/source matrices, assumptions, decisions, open questions, approval gates, review notes, proposed file changes, prior user feedback, and any page-specific scripts.
+   - Report missing or stale standard features per page.
+   - Classify each page as `current`, `upgrade-needed`, or `blocked-content-loss-risk`.
+
+4. Stop on content-loss risk:
+   - If a page's structure is too ambiguous to upgrade while preserving substantive content, do not rewrite it.
+   - Report exactly what content could not be mapped and what human decision is needed.
+
+5. Apply only when explicit:
+   - Before replacing each page, archive the original to `docs/history/archive/YYYY-MM-DD/HHMMSS/alignment/<filename>.html`.
+   - Rewrite the page contextually from the original, preserving page-specific research, decisions, questions, gates, review context, and user feedback.
+   - Add or modernize missing standard elements without replacing the page with a generic template.
+   - Preserve relative links and keep the page self-contained unless the original already used explicit external resources.
+   - Highlight upgrade changes where useful with inline notes, a change summary section, or scoped diff styling.
+
+6. Verify after apply:
+   - Confirm every changed page has a matching archive copy.
+   - Re-open each changed page textually and confirm the preserved title, decisions/findings, questions, and gates still exist.
+   - Run or recommend `/compile-central-alignment` so `alignment/index.html` reflects updated page metadata.
+
+## Audit Report
+
+Include:
+
+- Target repository and mode.
+- Standards sources read.
+- Pages inspected and pages excluded.
+- Per-page status with missing standard features.
+- Content preservation risks or blockers.
+- In apply mode, archive paths and changed page paths.
+- Verification performed.
+- Next action: usually `/compile-central-alignment` after successful apply, or no mutation needed when all pages are current.
+
+## Constraints
+
+- Do not edit `CLAUDE.md`, `AGENTS.md`, any `SKILL.md`, or any bundled `ALIGNMENT-PAGE.md` file.
+- Do not modify non-alignment HTML files.
+- Do not modify `alignment/index.html`; leave index regeneration to `/compile-central-alignment`.
+- Do not rewrite pages in audit/dry-run mode.
+- Do not replace page-specific content with a generic template.
+- Stop and report when an upgrade is likely to lose research, decisions, questions, gates, or review context.
+- Do not create or modify GitHub Actions workflows.
+
+## Default Shipping Contract
+
+- **Audit mode:** no file mutations; no commit or push.
+- **Apply mode:** modified generated alignment pages and archive copies are normal repo artifacts. Follow the target repository's shipping rules after verification.
+- **Default next-step routing:** after successful apply, `Recommended next command: /compile-central-alignment`; otherwise report the audit result and recommend no follow-up skill when no upgrades are needed.

package/packs/alignment-page-admin/codex/compile-central-alignment/CHANGELOG.md

@@ -0,0 +1,19 @@
+# Changelog
+
+## v0.2 - 2026-06-06
+
+- Group index entries by category (research, product-design, utility, qa-meta, ops-analysis) instead of a flat date-sorted list.
+- Read `data-alignment-category` from each page's `<html>` element; fall back to filename prefix matching; default to `research`.
+- Render each non-empty category as a section with `<h2>` heading, display name, and page count.
+- Text filter hides individual cards and collapses empty category headings.
+
+## v0.1 - 2026-06-05
+
+- Open or focus the regenerated central `alignment/index.html` with `node scripts/open-html-page.mjs alignment/index.html --browser auto`.
+- Require reporting the opener status: `focused`, `opened`, `fallback-opened`, `blocked`, or `failed`.
+- Clarify that `blocked` opener status does not fail the skill when the index was generated and verified.
+- Preserve the index as a local convenience artifact that is not committed or pushed by default.
+
+## v0.0 - 2026-05-30
+
+- Initial central alignment index generation skill.

package/packs/alignment-page-admin/codex/compile-central-alignment/SKILL.md

@@ -0,0 +1,57 @@
+---
+name: compile-central-alignment
+description: Generate a central alignment/index.html table of contents for all alignment pages in the current repo
+type: ops
+version: v0.2
+---
+
+# Compile Central Alignment
+
+Invoke as `$compile-central-alignment`.
+
+Generate a browsable `alignment/index.html` linking to every alignment page in the current repository. Works in any repo with an `alignment/` directory.
+
+## Process
+
+1. Locate `alignment/` at the project root; stop if absent.
+2. Scan `alignment/*.html` (exclude `index.html`), extract per-file: `<title>`, first `<h1>`, first `<p class="meta">`, `data-alignment-category` from `<html>` element, modification date.
+3. Group and sort:
+   - Assign category per page: `data-alignment-category` attribute first; else match filename against prefix lists:
+     - `research`: `devtool-positioning`, `devtool-adoption`, `devtool-monetization`, `devtool-user-map`, `devtool-workflow`, `devtool-dx-journey`, `devtool-integration-map`, `deep-research`, `repo-glossary`
+     - `product-design`: `idea-scope-brief`, `fork-idea-branch`, `animation-design-planner`, `skills-showcase`, `skills-inventory`
+     - `utility`: `investigate`, `session-triage`, `prompt-history-backfill`
+     - `qa-meta`: `expert-review`, `benchmark`, `targeted-skill-builder`, `devtool-docs-audit`
+     - `ops-analysis`: `analyze-sessions`, `canonical-workflow`, `run-batch`
+     - Default: `research`
+   - Group by category in fixed order: research → product-design → utility → qa-meta → ops-analysis
+   - Within each category, sort by modification date descending
+4. Generate `alignment/index.html` — self-contained HTML with:
+   - Visual style matching existing alignment pages (same CSS variables, fonts, layout)
+   - Category sections: each non-empty category gets an `<h2>` with display name and count (e.g., "Research (7)"), followed by its card grid
+   - Display names: Research, Product Design & Spec, Utility & Maintenance, QA & Meta-Skill Improvement, Ops & Session Analysis
+   - Card grid with linked titles, descriptions, dates
+   - Text filter input searching across all categories, hiding empty category headings
+   - Total page count and generation timestamp
+   - All relative links, no external dependencies
+   - Skip categories with zero pages
+5. Verify `alignment/index.html` was written and still works as a direct `file://` page.
+6. Open or focus the generated index with:
+   - `node scripts/open-html-page.mjs alignment/index.html --browser auto`
+7. Report the opener script status exactly as one of `focused`, `opened`, `fallback-opened`, `blocked`, or `failed`.
+   - `blocked` means the browser-open attempt was unavailable or blocked; it does not fail this skill when `alignment/index.html` was generated and verified.
+
+## Constraints
+
+- Do not modify existing alignment pages — only create or overwrite `alignment/index.html`.
+- Do not commit or push `alignment/index.html` by default — it is a local convenience artifact, regenerated fresh each time.
+- Empty-state page if no `.html` files found (besides `index.html`).
+- Must work as `file://` URL — no server required.
+- Do not open individual alignment pages from this skill; individual alignment-producing skills handle their own review pages, and this skill opens or focuses only the central index.
+
+## Default Shipping Contract
+
+- **No commit/push.** Local convenience file, regenerated on demand. Do not commit `alignment/index.html` unless the user explicitly asks.
+- **Default next-step routing:** After generating the index, suggest contextual next steps based on what was found:
+  - If any pages have old modification dates or the scan revealed outdated content: `Recommended next command: $upgrade-alignment-pages`
+  - If the index is freshly built with all pages current: confirm completion with no further routing
+  - Do not default to `$skills` as a generic fallback

package/packs/alignment-page-admin/codex/compile-central-alignment/agents/openai.yaml

@@ -0,0 +1,7 @@
+interface:
+  display_name: "Compile Central Alignment"
+  short_description: "Generate alignment page index"
+  default_prompt: "Use $compile-central-alignment to generate a central index of all alignment pages."
+
+policy:
+  allow_implicit_invocation: true

package/packs/alignment-page-admin/codex/compile-central-alignment/archive/v0.0/SKILL.md

@@ -0,0 +1,40 @@
+---
+name: compile-central-alignment
+description: Generate a central alignment/index.html table of contents for all alignment pages in the current repo
+type: ops
+version: v0.0
+---
+
+# Compile Central Alignment
+
+Invoke as `$compile-central-alignment`.
+
+Generate a browsable `alignment/index.html` linking to every alignment page in the current repository. Works in any repo with an `alignment/` directory.
+
+## Process
+
+1. Locate `alignment/` at the project root; stop if absent.
+2. Scan `alignment/*.html` (exclude `index.html`), extract per-file: `<title>`, first `<h1>`, first `<p class="meta">`, modification date.
+3. Sort by modification date descending.
+4. Generate `alignment/index.html` — self-contained HTML with:
+   - Visual style matching existing alignment pages (same CSS variables, fonts, layout)
+   - Card grid with linked titles, descriptions, dates
+   - Text filter input for quick search
+   - Page count and generation timestamp
+   - All relative links, no external dependencies
+5. Open in browser (WSL-aware: `wslpath -w` + `cmd.exe /c start`).
+
+## Constraints
+
+- Do not modify existing alignment pages — only create/overwrite `alignment/index.html`.
+- Do not commit or push — local convenience artifact, regenerated fresh each time.
+- Empty-state page if no `.html` files found (besides `index.html`).
+- Must work as `file://` URL — no server required.
+
+## Default Shipping Contract
+
+- **No commit/push.** Local convenience file, regenerated on demand.
+- **Default next-step routing:** After generating the index, suggest contextual next steps based on what was found:
+  - If any pages have old modification dates or the scan revealed outdated content: `Recommended next command: $upgrade-alignment-pages`
+  - If the index is freshly built with all pages current: confirm completion with no further routing
+  - Do not default to `$skills` as a generic fallback

package/packs/alignment-page-admin/codex/compile-central-alignment/archive/v0.1/SKILL.md

@@ -0,0 +1,45 @@
+---
+name: compile-central-alignment
+description: Generate a central alignment/index.html table of contents for all alignment pages in the current repo
+type: ops
+version: v0.1
+---
+
+# Compile Central Alignment
+
+Invoke as `$compile-central-alignment`.
+
+Generate a browsable `alignment/index.html` linking to every alignment page in the current repository. Works in any repo with an `alignment/` directory.
+
+## Process
+
+1. Locate `alignment/` at the project root; stop if absent.
+2. Scan `alignment/*.html` (exclude `index.html`), extract per-file: `<title>`, first `<h1>`, first `<p class="meta">`, modification date.
+3. Sort by modification date descending.
+4. Generate `alignment/index.html` — self-contained HTML with:
+   - Visual style matching existing alignment pages (same CSS variables, fonts, layout)
+   - Card grid with linked titles, descriptions, dates
+   - Text filter input for quick search
+   - Page count and generation timestamp
+   - All relative links, no external dependencies
+5. Verify `alignment/index.html` was written and still works as a direct `file://` page.
+6. Open or focus the generated index with:
+   - `node scripts/open-html-page.mjs alignment/index.html --browser auto`
+7. Report the opener script status exactly as one of `focused`, `opened`, `fallback-opened`, `blocked`, or `failed`.
+   - `blocked` means the browser-open attempt was unavailable or blocked; it does not fail this skill when `alignment/index.html` was generated and verified.
+
+## Constraints
+
+- Do not modify existing alignment pages — only create or overwrite `alignment/index.html`.
+- Do not commit or push `alignment/index.html` by default — it is a local convenience artifact, regenerated fresh each time.
+- Empty-state page if no `.html` files found (besides `index.html`).
+- Must work as `file://` URL — no server required.
+- Do not open individual alignment pages from this skill; individual alignment-producing skills handle their own review pages, and this skill opens or focuses only the central index.
+
+## Default Shipping Contract
+
+- **No commit/push.** Local convenience file, regenerated on demand. Do not commit `alignment/index.html` unless the user explicitly asks.
+- **Default next-step routing:** After generating the index, suggest contextual next steps based on what was found:
+  - If any pages have old modification dates or the scan revealed outdated content: `Recommended next command: $upgrade-alignment-pages`
+  - If the index is freshly built with all pages current: confirm completion with no further routing
+  - Do not default to `$skills` as a generic fallback

package/packs/alignment-page-admin/codex/upgrade-alignment-pages/CHANGELOG.md

@@ -0,0 +1,11 @@
+# Changelog
+
+## v0.1 - 2026-05-31
+
+- Add batch-mode handoff (step 4b): when 3+ pages need upgrade in apply mode, generate an exec-loop task plan in `tasks/todo.md` instead of rewriting all pages inline. Each page gets its own `$exec` iteration with a fresh context window.
+- Inline apply (≤2 pages) continues as before.
+- Updated shipping contract to document batch-mode behavior.
+
+## v0.0 - 2026-05-30
+
+- Initial alignment-page upgrade skill for dry-run drift audits and explicit apply-mode HTML upgrades with archive-before-replace safeguards.

package/packs/alignment-page-admin/codex/upgrade-alignment-pages/SKILL.md

@@ -0,0 +1,106 @@
+---
+name: upgrade-alignment-pages
+description: Audit and explicitly upgrade generated alignment/*.html review pages to the current local alignment-page standard while preserving page-specific context
+type: ops
+version: v0.1
+argument-hint: "[--repo <path>] [--apply] [alignment/*.html...]"
+---
+
+# Upgrade Alignment Pages
+
+Invoke as `$upgrade-alignment-pages`.
+
+Use this skill when a repository already has generated `alignment/*.html` review pages and the user wants to audit or update them against the current local alignment-page convention. This skill targets generated alignment HTML artifacts only.
+
+## Inputs
+
+- Default target repository: current working directory.
+- Optional `--repo <path>` to target another repository.
+- Optional explicit page paths under the target repository's `alignment/` directory.
+- Optional `--apply`, or clear user wording such as "apply the upgrade" or "upgrade these pages", to allow page rewrites.
+
+## Mode
+
+- Default mode is audit/dry-run.
+- The skill name alone is not apply intent; do not modify files unless the visible user request explicitly asks to apply or upgrade existing pages.
+- In audit/dry-run mode, inspect pages and report drift without creating, editing, moving, or deleting any files.
+
+## Process
+
+1. Resolve scope:
+   - Locate the project-root `alignment/` directory; stop if absent.
+   - Enumerate `alignment/*.html`, excluding `alignment/index.html`.
+   - If the user provided page paths, include only those paths after confirming they are inside the project-root `alignment/` directory.
+
+2. Load local standards:
+   - Read applicable local convention sources from `AGENTS.md`, `CLAUDE.md`, and active bundled `ALIGNMENT-PAGE.md` files found under `global/`, `packs/`, `.claude/skills/`, and `.codex/skills/`.
+   - Treat those local files as read-only standards. Do not fetch external standards.
+   - Extract the current required HTML behaviors: dark-mode styling, inline approval gates, section feedback controls, feedback-only YAML, final answer YAML, copy fallback behavior, unanswered-question handling, archive-before-replace behavior, and diff/change highlighting for updates.
+
+3. Audit every selected page:
+   - Read the whole HTML file before judging it.
+   - Identify page-specific substance: title, meta/context, research findings, evidence/source matrices, assumptions, decisions, open questions, approval gates, review notes, proposed file changes, prior user feedback, and any page-specific scripts.
+   - Report missing or stale standard features per page.
+   - Classify each page as `current`, `upgrade-needed`, or `blocked-content-loss-risk`.
+
+4. Stop on content-loss risk:
+   - If a page's structure is too ambiguous to upgrade while preserving substantive content, do not rewrite it.
+   - Report exactly what content could not be mapped and what human decision is needed.
+
+4b. Batch-mode handoff (apply mode only):
+   - Count pages classified as `upgrade-needed` (excluding `blocked-content-loss-risk`).
+   - If count > 2:
+     - Generate a phase in `tasks/todo.md` titled "## Phase: Upgrade Alignment Pages" with:
+       - Execution Profile: serial
+       - A Context block listing the standards sources discovered in step 2 and the archive timestamp path (`docs/history/archive/YYYY-MM-DD/HHMMSS/`)
+       - One checklist step per upgrade-needed page: `- [ ] Upgrade alignment/<filename>.html — archive original, rewrite to current standard preserving all content, verify content preservation`
+       - A final step: `- [ ] Run $compile-central-alignment and verify all archives; commit and push`
+       - Acceptance criteria matching the audit findings
+     - If `tasks/todo.md` already has unchecked items, append the phase at the bottom with a separator (`---`) and warn the user about pre-existing items.
+     - Output the full audit report.
+     - Report: "Generated exec-loop task plan with N steps. Recommended next command: $exec"
+     - Stop. Do not modify any HTML files.
+   - If count <= 2: proceed to step 5 (inline apply).
+
+5. Apply only when explicit:
+   - Before replacing each page, archive the original to `docs/history/archive/YYYY-MM-DD/HHMMSS/alignment/<filename>.html`.
+   - Rewrite the page contextually from the original, preserving page-specific research, decisions, questions, gates, review context, and user feedback.
+   - Add or modernize missing standard elements without replacing the page with a generic template.
+   - Preserve relative links and keep the page self-contained unless the original already used explicit external resources.
+   - Highlight upgrade changes where useful with inline notes, a change summary section, or scoped diff styling.
+
+6. Verify after apply:
+   - Confirm every changed page has a matching archive copy.
+   - Re-open each changed page textually and confirm the preserved title, decisions/findings, questions, and gates still exist.
+   - Run or recommend `$compile-central-alignment` so `alignment/index.html` reflects updated page metadata.
+
+## Audit Report
+
+Include:
+
+- Target repository and mode.
+- Standards sources read.
+- Pages inspected and pages excluded.
+- Per-page status with missing standard features.
+- Content preservation risks or blockers.
+- In apply mode, archive paths and changed page paths.
+- Verification performed.
+- Next action: usually `$compile-central-alignment` after successful apply, or no mutation needed when all pages are current.
+- In batch mode: the generated `tasks/todo.md` phase with exec-loop steps and the recommended `$exec` command.
+
+## Constraints
+
+- Do not edit `CLAUDE.md`, `AGENTS.md`, any `SKILL.md`, or any bundled `ALIGNMENT-PAGE.md` file.
+- Do not modify non-alignment HTML files.
+- Do not modify `alignment/index.html`; leave index regeneration to `$compile-central-alignment`.
+- Do not rewrite pages in audit/dry-run mode.
+- Do not replace page-specific content with a generic template.
+- Stop and report when an upgrade is likely to lose research, decisions, questions, gates, or review context.
+- Do not create or modify GitHub Actions workflows.
+
+## Default Shipping Contract
+
+- **Audit mode:** no file mutations; no commit or push.
+- **Apply mode (inline, ≤2 pages):** modified generated alignment pages and archive copies are normal repo artifacts. Follow the target repository's shipping rules after verification.
+- **Apply mode (batch, >2 pages):** generates `tasks/todo.md` phase only; does not modify any HTML files. Commit the task plan, then hand off to `$exec`.
+- **Default next-step routing:** after successful inline apply, `Recommended next command: $compile-central-alignment`; after batch-mode handoff, `Recommended next command: $exec`; otherwise report the audit result and recommend no follow-up skill when no upgrades are needed.

package/packs/alignment-page-admin/codex/upgrade-alignment-pages/agents/openai.yaml

@@ -0,0 +1,7 @@
+interface:
+  display_name: "Upgrade Alignment Pages"
+  short_description: "Audit and upgrade alignment HTML pages"
+  default_prompt: "Use $upgrade-alignment-pages to audit existing alignment/*.html review pages for drift before applying any upgrades."
+
+policy:
+  allow_implicit_invocation: true

package/packs/alignment-page-admin/codex/upgrade-alignment-pages/archive/v0.0/SKILL.md

@@ -0,0 +1,89 @@
+---
+name: upgrade-alignment-pages
+description: Audit and explicitly upgrade generated alignment/*.html review pages to the current local alignment-page standard while preserving page-specific context
+type: utility
+version: v0.0
+argument-hint: "[--repo <path>] [--apply] [alignment/*.html...]"
+---
+
+# Upgrade Alignment Pages
+
+Invoke as `$upgrade-alignment-pages`.
+
+Use this skill when a repository already has generated `alignment/*.html` review pages and the user wants to audit or update them against the current local alignment-page convention. This skill targets generated alignment HTML artifacts only.
+
+## Inputs
+
+- Default target repository: current working directory.
+- Optional `--repo <path>` to target another repository.
+- Optional explicit page paths under the target repository's `alignment/` directory.
+- Optional `--apply`, or clear user wording such as "apply the upgrade" or "upgrade these pages", to allow page rewrites.
+
+## Mode
+
+- Default mode is audit/dry-run.
+- The skill name alone is not apply intent; do not modify files unless the visible user request explicitly asks to apply or upgrade existing pages.
+- In audit/dry-run mode, inspect pages and report drift without creating, editing, moving, or deleting any files.
+
+## Workflow
+
+1. Resolve scope:
+   - Locate the project-root `alignment/` directory; stop if absent.
+   - Enumerate `alignment/*.html`, excluding `alignment/index.html`.
+   - If the user provided page paths, include only those paths after confirming they are inside the project-root `alignment/` directory.
+
+2. Load local standards:
+   - Read applicable local convention sources from `AGENTS.md`, `CLAUDE.md`, and active bundled `ALIGNMENT-PAGE.md` files found under `global/`, `packs/`, `.claude/skills/`, and `.codex/skills/`.
+   - Treat those local files as read-only standards. Do not fetch external standards.
+   - Extract the current required HTML behaviors: dark-mode styling, inline approval gates, section feedback controls, feedback-only YAML, final answer YAML, copy fallback behavior, unanswered-question handling, archive-before-replace behavior, and diff/change highlighting for updates.
+
+3. Audit every selected page:
+   - Read the whole HTML file before judging it.
+   - Identify page-specific substance: title, meta/context, research findings, evidence/source matrices, assumptions, decisions, open questions, approval gates, review notes, proposed file changes, prior user feedback, and any page-specific scripts.
+   - Report missing or stale standard features per page.
+   - Classify each page as `current`, `upgrade-needed`, or `blocked-content-loss-risk`.
+
+4. Stop on content-loss risk:
+   - If a page's structure is too ambiguous to upgrade while preserving substantive content, do not rewrite it.
+   - Report exactly what content could not be mapped and what human decision is needed.
+
+5. Apply only when explicit:
+   - Before replacing each page, archive the original to `docs/history/archive/YYYY-MM-DD/HHMMSS/alignment/<filename>.html`.
+   - Rewrite the page contextually from the original, preserving page-specific research, decisions, questions, gates, review context, and user feedback.
+   - Add or modernize missing standard elements without replacing the page with a generic template.
+   - Preserve relative links and keep the page self-contained unless the original already used explicit external resources.
+   - Highlight upgrade changes where useful with inline notes, a change summary section, or scoped diff styling.
+
+6. Verify after apply:
+   - Confirm every changed page has a matching archive copy.
+   - Re-open each changed page textually and confirm the preserved title, decisions/findings, questions, and gates still exist.
+   - Run or recommend `$compile-central-alignment` so `alignment/index.html` reflects updated page metadata.
+
+## Audit Report
+
+Include:
+
+- Target repository and mode.
+- Standards sources read.
+- Pages inspected and pages excluded.
+- Per-page status with missing standard features.
+- Content preservation risks or blockers.
+- In apply mode, archive paths and changed page paths.
+- Verification performed.
+- Next action: usually `$compile-central-alignment` after successful apply, or no mutation needed when all pages are current.
+
+## Constraints
+
+- Do not edit `CLAUDE.md`, `AGENTS.md`, any `SKILL.md`, or any bundled `ALIGNMENT-PAGE.md` file.
+- Do not modify non-alignment HTML files.
+- Do not modify `alignment/index.html`; leave index regeneration to `$compile-central-alignment`.
+- Do not rewrite pages in audit/dry-run mode.
+- Do not replace page-specific content with a generic template.
+- Stop and report when an upgrade is likely to lose research, decisions, questions, gates, or review context.
+- Do not create or modify GitHub Actions workflows.
+
+## Default Shipping Contract
+
+- **Audit mode:** no file mutations; no commit or push.
+- **Apply mode:** modified generated alignment pages and archive copies are normal repo artifacts. Follow the target repository's shipping rules after verification.
+- **Default next-step routing:** after successful apply, `Recommended next command: $compile-central-alignment`; otherwise report the audit result and recommend no follow-up skill when no upgrades are needed.

package/packs/business-app/PACK.md

@@ -0,0 +1,18 @@
+# Business App Compatibility Pack
+
+`business-app` is now a compatibility alias, not a skill container. Its former skills were split into narrower packs to reduce loaded context:
+
+```text
+business-discovery, customer-lifecycle, business-growth, business-ops
+```
+
+Use the narrowest pack for the current phase:
+
+- `business-discovery`: ICP, customer/market research, value proposition, positioning, and lean canvas.
+- `customer-lifecycle`: journey mapping, onboarding, conversion, transaction, retention, expansion, and lifecycle metrics.
+- `business-growth`: engagement loops, metrics, monetization, GTM, landing copy, experiments, growth, and PMF.
+- `business-ops`: assumptions, feedback/retro/cohorts, risks, runway, investor updates, scale/mvp gaps, platform strategy, and research reconciliation.
+
+For backwards compatibility, `scripts/pack.sh install business-app` expands to all four packs. Prefer installing only the lane needed for the current work.
+
+PoketoWork kanban packs are hibernated while Poketo.work is being rebuilt; do not recommend `business-app-kanban` as an active overlay.

package/packs/business-discovery/PACK.md

@@ -0,0 +1,24 @@
+# Business Discovery Pack
+
+Project-local workflows for early business and product discovery.
+
+Install this pack when a project needs customer discovery, enterprise buyer mapping, competitive analysis, customer feedback synthesis, positioning, or optional value proposition / lean canvas synthesis.
+
+Default flow:
+
+```text
+customer-discovery -> competitive-analysis -> journey-map -> positioning -> user-flow-map
+```
+
+`journey-map` is provided by the `customer-lifecycle` pack. Install `customer-lifecycle` before continuing past competitive analysis when that pack is not already enabled.
+
+`value-prop-canvas` and `lean-canvas` are optional detours, not default blockers. Use `value-prop-canvas` when solution-customer fit is weak, disputed, or needs explicit fit scoring. Use `lean-canvas` when revenue, channels, cost, defensibility, or unfair-advantage assumptions are material risks.
+
+Skills:
+
+```text
+customer-discovery, enterprise-icp, competitive-analysis, customer-feedback,
+value-prop-canvas, lean-canvas, positioning
+```
+
+Install `customer-lifecycle` when discovery is ready to become journey, onboarding, conversion, transaction, retention, expansion, or lifecycle metrics work. Install `business-growth` when discovery and lifecycle evidence are ready to become GTM, growth, pricing, experiments, metrics, or PMF work. Install `business-ops` for ongoing operating reviews and business health.