skillpacks 0.1.0

package/packs/repo-maintenance/claude/bootstrap-repo/archive/v0.1/SKILL.md

@@ -0,0 +1,95 @@
+---
+name: bootstrap-repo
+description: Initialize or reset a repository README and agent workflow docs from a short project brief
+type: execution
+version: v0.1
+argument-hint: "<project brief>"
+---
+
+# Bootstrap Repo
+
+Initialize a repository with a useful `README.md` and the standard agent workflow docs. When invoked with `--reset-existing`, first archive stale implementation and documentation files from a non-empty stuck repo so the fresh start is not built on old code or old assumptions by accident.
+
+## Process
+
+1. **Parse the project brief and mode** from `$ARGUMENTS`:
+   - Detect `--reset-existing`, `--in-place-reset`, or an explicit request to archive/reset the current codebase before bootstrap.
+   - Extract the project name, purpose, setup instructions, run/test commands, and any constraints.
+   - If the brief is missing or too thin to write a useful README, ask for the project name and one-sentence purpose. Ask for setup or run instructions only when the repository does not make them discoverable.
+
+2. **Inspect the target repository:**
+   - Read existing `README.md`, `CLAUDE.md`, `AGENTS.md`, package manifests, obvious build files, and directory names.
+   - Preserve discovered commands and facts. Do not invent dependency managers, deployment targets, or product claims.
+
+3. **Reset existing stale repo when explicitly requested:**
+   - Only perform this step when reset mode is explicit. Never archive or move files during ordinary bootstrap.
+   - Confirm the repo is non-empty and contains stale implementation, docs, research, specs, task files, design notes, or generated app structure. If it is already empty or freshly initialized, skip archival and note why.
+   - Create `archive/YYYY-MM-DD-HHMMSS/` and move stale implementation and documentation files/directories there before writing fresh bootstrap docs.
+   - Archive old docs by default, including `docs/`, `alignment/`, `research/`, `specs/`, `tasks/`, planning reports, implementation notes, design docs, old README content, and prior roadmap/todo/history files. These may remain useful as historical evidence in the archive, but they must not stay active as source-of-truth inputs.
+   - Do not archive `.git/`, `.agents/`, `archive/`, `desk-flip-report.md`, root agent config files needed for the current session, or the newly written high-level concept artifact.
+   - Preserve exactly one active concept seed, such as `concept.md` or `README.md` `## Concept`, derived from the bootstrap brief or `desk-flip-report.md`. Keep it high level: product name, target user, core problem, value proposition, non-goals, and open questions. Do not preserve old research/spec detail as active files.
+   - Preserve a manifest at `archive/YYYY-MM-DD-HHMMSS/MANIFEST.md` listing every moved path, every intentionally preserved path, and the high-level concept source that justified the reset.
+   - Prefer `git mv` for tracked paths so history remains understandable. Use ordinary moves only for untracked paths.
+   - Do not delete old files outright. If a path cannot be moved safely, stop and report the blocker instead of partially resetting further.
+   - After archival, the root should contain only the fresh-start sources of truth: git metadata, agent config, the archive directory, `desk-flip-report.md`, the high-level concept artifact, and any newly written bootstrap docs. Old docs/research/specs belong in the archive.
+
+4. **Create or update `README.md`:**
+   - If `README.md` is absent, empty, or placeholder-like, write a concise README with:
+     - `# <Project Name>`
+     - A short purpose summary.
+     - `## Getting Started`
+     - `## Development`
+     - `## Notes`
+   - If `README.md` already has substantial content, preserve it. Ask before replacing it; otherwise add a small bootstrap section only when it improves the file.
+   - Use the project brief as the primary source and repository inspection as supporting evidence.
+
+5. **Provision agent workflow docs:**
+   - Run `/provision-agentic-config` for the same repository.
+   - Confirm `CLAUDE.md` and `AGENTS.md` exist after provisioning.
+   - Preserve unrelated existing content in both files.
+
+6. **Verify the result:**
+   - Check that `README.md`, `CLAUDE.md`, and `AGENTS.md` exist.
+   - Confirm the corresponding workflow orchestration block appears exactly once in each of `CLAUDE.md` and `AGENTS.md`.
+   - Report whether the monorepo safety block was included or skipped by `/provision-agentic-config`.
+   - In reset mode, check that `archive/YYYY-MM-DD-HHMMSS/MANIFEST.md` exists and lists moved and preserved paths, and verify old docs/research/specs/tasks were archived rather than left active.
+
+7. **Route research-first after product bootstrap:**
+   - If this is a product, app, SaaS, dashboard, internal tool, marketplace, website, or other user-facing restart, rebuild market and lifecycle alignment from the high-level concept before UI requirements or prototypes.
+   - Check `.agents/project.json.enabled_packs` when present. If `business-discovery` is not enabled, recommend `/pack install business-discovery` before `/icp`. If `customer-lifecycle` is not enabled, include `/pack install customer-lifecycle` before `/journey-map`.
+   - When required packs are available, recommend `/icp <concept>` as the next command. After `/icp`, the intended sequence is `/competitive-analysis` -> `/journey-map` -> `/positioning` -> `/user-flow-map` -> `/ui-interview --requirements-only` -> `/ux-variations --layout-mode` -> prototype work.
+   - If current, accepted `research/icp.md`, `research/competitive-analysis.md`, and `research/journey-map.md` already exist from the fresh reset but positioning is missing, then recommend `/positioning <topic>`.
+   - If positioning exists but a flow map is missing, recommend `/user-flow-map <topic>`.
+   - If a flow map exists but UI requirements are missing, recommend `/ui-interview --requirements-only <topic>`.
+   - If UI requirements exist but layout variations are missing, recommend `/ux-variations --layout-mode <topic>`.
+   - Only route directly to `/roadmap` or `/exec` when the project is non-UI/non-product work or already has accepted alignment artifacts and a consolidated prototype.
+   - The intended product sequence after reset is: `/icp` -> `/competitive-analysis` -> `/journey-map` -> `/positioning` -> `/user-flow-map` -> `/ui-interview --requirements-only` -> `/ux-variations --layout-mode` -> build variants/prototypes via `/exec` or the applicable prototype-building route -> `/uat --variant-evaluation` -> `/consolidate-variations` -> `/research-roadmap --post-prototype` -> `/spec-interview` or `/roadmap`.
+
+## Output
+
+```markdown
+Bootstrapped repository
+- README.md: [created | updated | preserved], source: [arguments | prompts | existing content]
+- Reset archive: [created archive/YYYY-MM-DD-HHMMSS | skipped (<reason>)]
+- Active concept seed: [concept.md | README.md ## Concept | other]
+- CLAUDE.md: [created | updated | unchanged], corresponding workflow block appears once
+- AGENTS.md: [created | updated | unchanged], corresponding workflow block appears once
+- Monorepo safety block: [included (<heuristic>) | skipped]
+- Verification: [commands/checks run]
+- Recommended next command: [/pack install business-discovery | /pack install customer-lifecycle | /pack install product-design | /icp <concept> | /positioning <topic> | /user-flow-map <topic> | /ui-interview --requirements-only <topic> | /ux-variations --layout-mode <topic> | /roadmap | /exec]
+```
+
+## Constraints
+
+- Do not overwrite substantial existing `README.md` content without explicit user confirmation.
+- Do not invent setup, test, deploy, or architecture details that are not in the brief or repository.
+- Keep the README concise and useful for a new contributor.
+- Do not modify files other than `README.md`, `CLAUDE.md`, and `AGENTS.md` unless the user explicitly asks or invokes reset mode.
+- Reset mode may move stale files, including old docs/research/specs/tasks, into `archive/YYYY-MM-DD-HHMMSS/` and write that archive's `MANIFEST.md`; it may not delete files outright.
+- In reset mode, do not preserve old docs as active files just because they were marked salvageable. Use them only as archived historical evidence; active research and requirements restart from the high-level concept.
+- Do not create, modify, or suggest GitHub Actions workflows.
+
+
+## Default Shipping Contract
+
+Follow the shared shipping contract convention in CLAUDE.md.

package/packs/repo-maintenance/claude/env-setup/CHANGELOG.md

@@ -0,0 +1,5 @@
+# env-setup changelog (claude)
+
+## v0.0 - 2026-06-10
+
+- Initial version.

package/packs/repo-maintenance/claude/env-setup/SKILL.md

@@ -0,0 +1,69 @@
+---
+name: env-setup
+description: Scaffold the local env file with required variable stubs from .env.example and code, open it for the user to fill, and verify completeness by key names only — never reading secret values
+type: execution
+version: v0.0
+argument-hint: "[target env file or framework hint]"
+---
+
+# Env Setup
+
+Scaffold the project's local environment file with stubs for every required variable, open it so the user can fill in values, and verify completeness by key names only. This skill must never read, print, or summarize secret values from any env file.
+
+## Process
+
+1. **Resolve the target file** from `$ARGUMENTS`:
+   - Default to `.env.local`.
+   - Accept an explicit file path (e.g. `.env`, `.dev.vars`) or a framework hint (e.g. `next`, `wrangler`) and map it to that framework's convention.
+   - If the repository's own convention differs from the default (e.g. plain Node projects loading `.env`, Wrangler projects using `.dev.vars`), use the detected convention and say so in the report.
+
+2. **Discover required variables.** Build the union of:
+   - Keys in `.env.example`, `.env.sample`, or equivalent template files.
+   - Code references: `process.env.X`, `import.meta.env.X`, `os.environ[...]`, and framework config files.
+   - Setup sections in `README.md` and project docs.
+   - If the target file already exists, extract key names only (e.g. `cut -d= -f1`) to learn which keys are already present. Never read, cat, print, or summarize values from the target file or any other secret-bearing env file.
+
+3. **Scaffold stubs:**
+   - Create the target file if it does not exist.
+   - Append only the missing keys as `KEY=` stubs, each with a one-line comment hint for where the value comes from (provider dashboard, teammate, generated locally).
+   - Never overwrite, reorder, or rewrite existing lines in the target file.
+
+4. **Gitignore guard:**
+   - Verify the target file is covered by `.gitignore`. If it is not, add a matching ignore entry and warn the user.
+   - Never remove an env file from `.gitignore`, and never commit the target env file.
+
+5. **Open the file for the user:**
+   - Open the target file in VS Code with `code <file>`.
+   - Inside WSL, if `code` is unavailable, follow the CLAUDE.md Windows/WSL file-opening convention (`wslpath` + `cmd.exe /c start`).
+
+6. **Verify by presence only.** When the user says they are done (or on a re-run):
+   - Report which keys are still empty, by key name only. Never echo values.
+   - For non-secret generatable keys (e.g. `AUTH_SECRET`, session salts), offer to generate a value locally with a command such as `openssl rand -base64 32` — only with user confirmation, and write it into the file without printing it back.
+
+7. **Write forward to `.env.example`:** if discovery found required keys that are missing from `.env.example`, append them there as empty stubs so the template stays complete. This is a tracked change and ships normally.
+
+## Output
+
+```markdown
+Env setup
+- Target file: <path> [created | updated | already complete]
+- Keys scaffolded: [key names | none]
+- Keys still empty: [key names | none]
+- Gitignore: [already covered | entry added | WARNING not covered]
+- Editor: [opened in VS Code | open manually: <path>]
+- .env.example: [updated with N keys | unchanged]
+- **Next work:** [fill in the empty keys listed above | none]
+- **Recommended next command:** [re-run /env-setup to verify completeness | none]
+```
+
+## Constraints
+
+- Never read, print, echo, or summarize secret **values** from any env file — operate on key names only.
+- Never commit the target env file, and never weaken `.gitignore` coverage of env files.
+- Never overwrite or rewrite existing lines in the target env file; only append missing stubs.
+- If the user pastes a secret value into the conversation, warn them that it is now in chat history and suggest rotating it if sensitive.
+- Do not invent required variables that no template, code reference, or doc mentions.
+
+## Default Shipping Contract
+
+Follow the shared shipping contract convention in CLAUDE.md. Only `.env.example` and `.gitignore` edits are tracked-file mutations to ship; the target env file itself is never committed.

package/packs/repo-maintenance/codex/bootstrap-repo/CHANGELOG.md

@@ -0,0 +1,13 @@
+# bootstrap-repo changelog (codex)
+
+## v0.2 - 2026-06-07
+
+- Routed product bootstrap next-command guidance from retired `$icp` to `$customer-discovery` while preserving `research/icp.md` as accepted evidence.
+
+## v0.1 - 2026-06-06
+
+- Route product bootstraps through `$user-flow-map`, `$ui-interview --requirements-only`, and `$ux-variations --layout-mode` before prototype work.
+
+## v0.0
+
+- Initial version.

package/packs/repo-maintenance/codex/bootstrap-repo/SKILL.md

@@ -0,0 +1,97 @@
+---
+name: bootstrap-repo
+description: Initialize or reset a repository README and agent workflow docs from a short project brief
+type: execution
+version: v0.2
+argument-hint: "<project brief>"
+---
+
+# Bootstrap Repo
+
+Invoke as `$bootstrap-repo`.
+
+Initialize a repository with a useful `README.md` and the standard agent workflow docs. When invoked with `--reset-existing`, first archive stale implementation and documentation files from a non-empty stuck repo so the fresh start is not built on old code or old assumptions by accident.
+
+## Process
+
+1. **Parse the project brief and mode** from `$ARGUMENTS`:
+   - Detect `--reset-existing`, `--in-place-reset`, or an explicit request to archive/reset the current codebase before bootstrap.
+   - Extract the project name, purpose, setup instructions, run/test commands, and any constraints.
+   - If the brief is missing or too thin to write a useful README, ask for the project name and one-sentence purpose. Ask for setup or run instructions only when the repository does not make them discoverable.
+
+2. **Inspect the target repository:**
+   - Read existing `README.md`, `CLAUDE.md`, `AGENTS.md`, package manifests, obvious build files, and directory names.
+   - Preserve discovered commands and facts. Do not invent dependency managers, deployment targets, or product claims.
+
+3. **Reset existing stale repo when explicitly requested:**
+   - Only perform this step when reset mode is explicit. Never archive or move files during ordinary bootstrap.
+   - Confirm the repo is non-empty and contains stale implementation, docs, research, specs, task files, design notes, or generated app structure. If it is already empty or freshly initialized, skip archival and note why.
+   - Create `archive/YYYY-MM-DD-HHMMSS/` and move stale implementation and documentation files/directories there before writing fresh bootstrap docs.
+   - Archive old docs by default, including `docs/`, `alignment/`, `research/`, `specs/`, `tasks/`, planning reports, implementation notes, design docs, old README content, and prior roadmap/todo/history files. These may remain useful as historical evidence in the archive, but they must not stay active as source-of-truth inputs.
+   - Do not archive `.git/`, `.agents/`, `archive/`, `desk-flip-report.md`, root agent config files needed for the current session, or the newly written high-level concept artifact.
+   - Preserve exactly one active concept seed, such as `concept.md` or `README.md` `## Concept`, derived from the bootstrap brief or `desk-flip-report.md`. Keep it high level: product name, target user, core problem, value proposition, non-goals, and open questions. Do not preserve old research/spec detail as active files.
+   - Preserve a manifest at `archive/YYYY-MM-DD-HHMMSS/MANIFEST.md` listing every moved path, every intentionally preserved path, and the high-level concept source that justified the reset.
+   - Prefer `git mv` for tracked paths so history remains understandable. Use ordinary moves only for untracked paths.
+   - Do not delete old files outright. If a path cannot be moved safely, stop and report the blocker instead of partially resetting further.
+   - After archival, the root should contain only the fresh-start sources of truth: git metadata, agent config, the archive directory, `desk-flip-report.md`, the high-level concept artifact, and any newly written bootstrap docs. Old docs/research/specs belong in the archive.
+
+4. **Create or update `README.md`:**
+   - If `README.md` is absent, empty, or placeholder-like, write a concise README with:
+     - `# <Project Name>`
+     - A short purpose summary.
+     - `## Getting Started`
+     - `## Development`
+     - `## Notes`
+   - If `README.md` already has substantial content, preserve it. Ask before replacing it; otherwise add a small bootstrap section only when it improves the file.
+   - Use the project brief as the primary source and repository inspection as supporting evidence.
+
+5. **Provision agent workflow docs:**
+   - Run `$provision-agentic-config` for the same repository.
+   - Confirm `CLAUDE.md` and `AGENTS.md` exist after provisioning.
+   - Preserve unrelated existing content in both files.
+
+6. **Verify the result:**
+   - Check that `README.md`, `CLAUDE.md`, and `AGENTS.md` exist.
+   - Confirm the corresponding workflow orchestration block appears exactly once in each of `CLAUDE.md` and `AGENTS.md`.
+   - Report whether the monorepo safety block was included or skipped by `$provision-agentic-config`.
+   - In reset mode, check that `archive/YYYY-MM-DD-HHMMSS/MANIFEST.md` exists and lists moved and preserved paths, and verify old docs/research/specs/tasks were archived rather than left active.
+
+7. **Route research-first after product bootstrap:**
+   - If this is a product, app, SaaS, dashboard, internal tool, marketplace, website, or other user-facing restart, rebuild market and lifecycle alignment from the high-level concept before UI requirements or prototypes.
+   - Check `.agents/project.json.enabled_packs` when present. If `business-discovery` is not enabled, recommend `$pack install business-discovery` before `$customer-discovery`. If `customer-lifecycle` is not enabled, include `$pack install customer-lifecycle` before `$journey-map`.
+   - When required packs are available, recommend `$customer-discovery <concept>` as the next command. After `$customer-discovery`, the intended sequence is `$competitive-analysis` -> `$journey-map` -> `$positioning` -> `$user-flow-map` -> `$ui-interview --requirements-only` -> `$ux-variations --layout-mode` -> prototype work.
+   - If current, accepted `research/icp.md`, `research/competitive-analysis.md`, and `research/journey-map.md` already exist from the fresh reset but positioning is missing, then recommend `$positioning <topic>`.
+   - If positioning exists but a flow map is missing, recommend `$user-flow-map <topic>`.
+   - If a flow map exists but UI requirements are missing, recommend `$ui-interview --requirements-only <topic>`.
+   - If UI requirements exist but layout variations are missing, recommend `$ux-variations --layout-mode <topic>`.
+   - Only route directly to `$roadmap` or `$exec` when the project is non-UI/non-product work or already has accepted alignment artifacts and a consolidated prototype.
+   - The intended product sequence after reset is: `$customer-discovery` -> `$competitive-analysis` -> `$journey-map` -> `$positioning` -> `$user-flow-map` -> `$ui-interview --requirements-only` -> `$ux-variations --layout-mode` -> build variants/prototypes via `$exec` or the applicable prototype-building route -> `$uat --variant-evaluation` -> `$consolidate-variations` -> `$research-roadmap --post-prototype` -> `$spec-interview` or `$roadmap`.
+
+## Output
+
+```markdown
+Bootstrapped repository
+- README.md: [created | updated | preserved], source: [arguments | prompts | existing content]
+- Reset archive: [created archive/YYYY-MM-DD-HHMMSS | skipped (<reason>)]
+- Active concept seed: [concept.md | README.md ## Concept | other]
+- CLAUDE.md: [created | updated | unchanged], corresponding workflow block appears once
+- AGENTS.md: [created | updated | unchanged], corresponding workflow block appears once
+- Monorepo safety block: [included (<heuristic>) | skipped]
+- Verification: [commands/checks run]
+- Recommended next command: [$pack install business-discovery | $pack install customer-lifecycle | $pack install product-design | $customer-discovery <concept> | $positioning <topic> | $user-flow-map <topic> | $ui-interview --requirements-only <topic> | $ux-variations --layout-mode <topic> | $roadmap | $exec]
+```
+
+## Constraints
+
+- Do not overwrite substantial existing `README.md` content without explicit user confirmation.
+- Do not invent setup, test, deploy, or architecture details that are not in the brief or repository.
+- Keep the README concise and useful for a new contributor.
+- Do not modify files other than `README.md`, `CLAUDE.md`, and `AGENTS.md` unless the user explicitly asks or invokes reset mode.
+- Reset mode may move stale files, including old docs/research/specs/tasks, into `archive/YYYY-MM-DD-HHMMSS/` and write that archive's `MANIFEST.md`; it may not delete files outright.
+- In reset mode, do not preserve old docs as active files just because they were marked salvageable. Use them only as archived historical evidence; active research and requirements restart from the high-level concept.
+- Do not create, modify, or suggest GitHub Actions workflows.
+
+
+## Default Shipping Contract
+
+Follow the shared shipping contract convention in CLAUDE.md.

package/packs/repo-maintenance/codex/bootstrap-repo/agents/openai.yaml

@@ -0,0 +1,7 @@
+interface:
+  display_name: "Bootstrap Repo"
+  short_description: "Create README and agent workflow docs"
+  default_prompt: "Use $bootstrap-repo with a short project brief to create or update README.md, then provision CLAUDE.md and AGENTS.md."
+
+policy:
+  allow_implicit_invocation: true

package/packs/repo-maintenance/codex/bootstrap-repo/archive/v0.0/SKILL.md

@@ -0,0 +1,95 @@
+---
+name: bootstrap-repo
+description: Initialize or reset a repository README and agent workflow docs from a short project brief
+type: execution
+version: v0.0
+argument-hint: "<project brief>"
+---
+
+# Bootstrap Repo
+
+Invoke as `$bootstrap-repo`.
+
+Initialize a repository with a useful `README.md` and the standard agent workflow docs. When invoked with `--reset-existing`, first archive stale implementation and documentation files from a non-empty stuck repo so the fresh start is not built on old code or old assumptions by accident.
+
+## Process
+
+1. **Parse the project brief and mode** from `$ARGUMENTS`:
+   - Detect `--reset-existing`, `--in-place-reset`, or an explicit request to archive/reset the current codebase before bootstrap.
+   - Extract the project name, purpose, setup instructions, run/test commands, and any constraints.
+   - If the brief is missing or too thin to write a useful README, ask for the project name and one-sentence purpose. Ask for setup or run instructions only when the repository does not make them discoverable.
+
+2. **Inspect the target repository:**
+   - Read existing `README.md`, `CLAUDE.md`, `AGENTS.md`, package manifests, obvious build files, and directory names.
+   - Preserve discovered commands and facts. Do not invent dependency managers, deployment targets, or product claims.
+
+3. **Reset existing stale repo when explicitly requested:**
+   - Only perform this step when reset mode is explicit. Never archive or move files during ordinary bootstrap.
+   - Confirm the repo is non-empty and contains stale implementation, docs, research, specs, task files, design notes, or generated app structure. If it is already empty or freshly initialized, skip archival and note why.
+   - Create `archive/YYYY-MM-DD-HHMMSS/` and move stale implementation and documentation files/directories there before writing fresh bootstrap docs.
+   - Archive old docs by default, including `docs/`, `alignment/`, `research/`, `specs/`, `tasks/`, planning reports, implementation notes, design docs, old README content, and prior roadmap/todo/history files. These may remain useful as historical evidence in the archive, but they must not stay active as source-of-truth inputs.
+   - Do not archive `.git/`, `.agents/`, `archive/`, `desk-flip-report.md`, root agent config files needed for the current session, or the newly written high-level concept artifact.
+   - Preserve exactly one active concept seed, such as `concept.md` or `README.md` `## Concept`, derived from the bootstrap brief or `desk-flip-report.md`. Keep it high level: product name, target user, core problem, value proposition, non-goals, and open questions. Do not preserve old research/spec detail as active files.
+   - Preserve a manifest at `archive/YYYY-MM-DD-HHMMSS/MANIFEST.md` listing every moved path, every intentionally preserved path, and the high-level concept source that justified the reset.
+   - Prefer `git mv` for tracked paths so history remains understandable. Use ordinary moves only for untracked paths.
+   - Do not delete old files outright. If a path cannot be moved safely, stop and report the blocker instead of partially resetting further.
+   - After archival, the root should contain only the fresh-start sources of truth: git metadata, agent config, the archive directory, `desk-flip-report.md`, the high-level concept artifact, and any newly written bootstrap docs. Old docs/research/specs belong in the archive.
+
+4. **Create or update `README.md`:**
+   - If `README.md` is absent, empty, or placeholder-like, write a concise README with:
+     - `# <Project Name>`
+     - A short purpose summary.
+     - `## Getting Started`
+     - `## Development`
+     - `## Notes`
+   - If `README.md` already has substantial content, preserve it. Ask before replacing it; otherwise add a small bootstrap section only when it improves the file.
+   - Use the project brief as the primary source and repository inspection as supporting evidence.
+
+5. **Provision agent workflow docs:**
+   - Run `$provision-agentic-config` for the same repository.
+   - Confirm `CLAUDE.md` and `AGENTS.md` exist after provisioning.
+   - Preserve unrelated existing content in both files.
+
+6. **Verify the result:**
+   - Check that `README.md`, `CLAUDE.md`, and `AGENTS.md` exist.
+   - Confirm the corresponding workflow orchestration block appears exactly once in each of `CLAUDE.md` and `AGENTS.md`.
+   - Report whether the monorepo safety block was included or skipped by `$provision-agentic-config`.
+   - In reset mode, check that `archive/YYYY-MM-DD-HHMMSS/MANIFEST.md` exists and lists moved and preserved paths, and verify old docs/research/specs/tasks were archived rather than left active.
+
+7. **Route research-first after product bootstrap:**
+   - If this is a product, app, SaaS, dashboard, internal tool, marketplace, website, or other user-facing restart, rebuild market and lifecycle alignment from the high-level concept before UI requirements or prototypes.
+   - Check `.agents/project.json.enabled_packs` when present. If `business-discovery` is not enabled, recommend `$pack install business-discovery` before `$icp`. If `customer-lifecycle` is not enabled, include `$pack install customer-lifecycle` before `$journey-map`.
+   - When required packs are available, recommend `$icp <concept>` as the next command. After `$icp`, the intended sequence is `$competitive-analysis` -> `$journey-map` -> `$ux-variations` -> `$ui-interview` -> prototype work.
+   - If current, accepted `research/icp.md`, `research/competitive-analysis.md`, and `research/journey-map.md` already exist from the fresh reset, then recommend `$ux-variations <topic>`.
+   - If UX variations already exist but interface details are missing, recommend `$ui-interview <topic>`.
+   - Only route directly to `$roadmap` or `$exec` when the project is non-UI/non-product work or already has accepted alignment artifacts and a consolidated prototype.
+   - The intended product sequence after reset is: `$icp` -> `$competitive-analysis` -> `$journey-map` -> `$ux-variations` -> `$ui-interview` -> build variants/prototypes via `$exec` or the applicable prototype-building route -> `$uat --variant-evaluation` -> `$consolidate-variations` -> `$research-roadmap --post-prototype` -> `$spec-interview` or `$roadmap`.
+
+## Output
+
+```markdown
+Bootstrapped repository
+- README.md: [created | updated | preserved], source: [arguments | prompts | existing content]
+- Reset archive: [created archive/YYYY-MM-DD-HHMMSS | skipped (<reason>)]
+- Active concept seed: [concept.md | README.md ## Concept | other]
+- CLAUDE.md: [created | updated | unchanged], corresponding workflow block appears once
+- AGENTS.md: [created | updated | unchanged], corresponding workflow block appears once
+- Monorepo safety block: [included (<heuristic>) | skipped]
+- Verification: [commands/checks run]
+- Recommended next command: [$pack install business-discovery | $pack install customer-lifecycle | $icp <concept> | $ux-variations <topic> | $ui-interview <topic> | $roadmap | $exec]
+```
+
+## Constraints
+
+- Do not overwrite substantial existing `README.md` content without explicit user confirmation.
+- Do not invent setup, test, deploy, or architecture details that are not in the brief or repository.
+- Keep the README concise and useful for a new contributor.
+- Do not modify files other than `README.md`, `CLAUDE.md`, and `AGENTS.md` unless the user explicitly asks or invokes reset mode.
+- Reset mode may move stale files, including old docs/research/specs/tasks, into `archive/YYYY-MM-DD-HHMMSS/` and write that archive's `MANIFEST.md`; it may not delete files outright.
+- In reset mode, do not preserve old docs as active files just because they were marked salvageable. Use them only as archived historical evidence; active research and requirements restart from the high-level concept.
+- Do not create, modify, or suggest GitHub Actions workflows.
+
+
+## Default Shipping Contract
+
+Follow the shared shipping contract convention in CLAUDE.md.

package/packs/repo-maintenance/codex/bootstrap-repo/archive/v0.1/SKILL.md

@@ -0,0 +1,97 @@
+---
+name: bootstrap-repo
+description: Initialize or reset a repository README and agent workflow docs from a short project brief
+type: execution
+version: v0.1
+argument-hint: "<project brief>"
+---
+
+# Bootstrap Repo
+
+Invoke as `$bootstrap-repo`.
+
+Initialize a repository with a useful `README.md` and the standard agent workflow docs. When invoked with `--reset-existing`, first archive stale implementation and documentation files from a non-empty stuck repo so the fresh start is not built on old code or old assumptions by accident.
+
+## Process
+
+1. **Parse the project brief and mode** from `$ARGUMENTS`:
+   - Detect `--reset-existing`, `--in-place-reset`, or an explicit request to archive/reset the current codebase before bootstrap.
+   - Extract the project name, purpose, setup instructions, run/test commands, and any constraints.
+   - If the brief is missing or too thin to write a useful README, ask for the project name and one-sentence purpose. Ask for setup or run instructions only when the repository does not make them discoverable.
+
+2. **Inspect the target repository:**
+   - Read existing `README.md`, `CLAUDE.md`, `AGENTS.md`, package manifests, obvious build files, and directory names.
+   - Preserve discovered commands and facts. Do not invent dependency managers, deployment targets, or product claims.
+
+3. **Reset existing stale repo when explicitly requested:**
+   - Only perform this step when reset mode is explicit. Never archive or move files during ordinary bootstrap.
+   - Confirm the repo is non-empty and contains stale implementation, docs, research, specs, task files, design notes, or generated app structure. If it is already empty or freshly initialized, skip archival and note why.
+   - Create `archive/YYYY-MM-DD-HHMMSS/` and move stale implementation and documentation files/directories there before writing fresh bootstrap docs.
+   - Archive old docs by default, including `docs/`, `alignment/`, `research/`, `specs/`, `tasks/`, planning reports, implementation notes, design docs, old README content, and prior roadmap/todo/history files. These may remain useful as historical evidence in the archive, but they must not stay active as source-of-truth inputs.
+   - Do not archive `.git/`, `.agents/`, `archive/`, `desk-flip-report.md`, root agent config files needed for the current session, or the newly written high-level concept artifact.
+   - Preserve exactly one active concept seed, such as `concept.md` or `README.md` `## Concept`, derived from the bootstrap brief or `desk-flip-report.md`. Keep it high level: product name, target user, core problem, value proposition, non-goals, and open questions. Do not preserve old research/spec detail as active files.
+   - Preserve a manifest at `archive/YYYY-MM-DD-HHMMSS/MANIFEST.md` listing every moved path, every intentionally preserved path, and the high-level concept source that justified the reset.
+   - Prefer `git mv` for tracked paths so history remains understandable. Use ordinary moves only for untracked paths.
+   - Do not delete old files outright. If a path cannot be moved safely, stop and report the blocker instead of partially resetting further.
+   - After archival, the root should contain only the fresh-start sources of truth: git metadata, agent config, the archive directory, `desk-flip-report.md`, the high-level concept artifact, and any newly written bootstrap docs. Old docs/research/specs belong in the archive.
+
+4. **Create or update `README.md`:**
+   - If `README.md` is absent, empty, or placeholder-like, write a concise README with:
+     - `# <Project Name>`
+     - A short purpose summary.
+     - `## Getting Started`
+     - `## Development`
+     - `## Notes`
+   - If `README.md` already has substantial content, preserve it. Ask before replacing it; otherwise add a small bootstrap section only when it improves the file.
+   - Use the project brief as the primary source and repository inspection as supporting evidence.
+
+5. **Provision agent workflow docs:**
+   - Run `$provision-agentic-config` for the same repository.
+   - Confirm `CLAUDE.md` and `AGENTS.md` exist after provisioning.
+   - Preserve unrelated existing content in both files.
+
+6. **Verify the result:**
+   - Check that `README.md`, `CLAUDE.md`, and `AGENTS.md` exist.
+   - Confirm the corresponding workflow orchestration block appears exactly once in each of `CLAUDE.md` and `AGENTS.md`.
+   - Report whether the monorepo safety block was included or skipped by `$provision-agentic-config`.
+   - In reset mode, check that `archive/YYYY-MM-DD-HHMMSS/MANIFEST.md` exists and lists moved and preserved paths, and verify old docs/research/specs/tasks were archived rather than left active.
+
+7. **Route research-first after product bootstrap:**
+   - If this is a product, app, SaaS, dashboard, internal tool, marketplace, website, or other user-facing restart, rebuild market and lifecycle alignment from the high-level concept before UI requirements or prototypes.
+   - Check `.agents/project.json.enabled_packs` when present. If `business-discovery` is not enabled, recommend `$pack install business-discovery` before `$icp`. If `customer-lifecycle` is not enabled, include `$pack install customer-lifecycle` before `$journey-map`.
+   - When required packs are available, recommend `$icp <concept>` as the next command. After `$icp`, the intended sequence is `$competitive-analysis` -> `$journey-map` -> `$positioning` -> `$user-flow-map` -> `$ui-interview --requirements-only` -> `$ux-variations --layout-mode` -> prototype work.
+   - If current, accepted `research/icp.md`, `research/competitive-analysis.md`, and `research/journey-map.md` already exist from the fresh reset but positioning is missing, then recommend `$positioning <topic>`.
+   - If positioning exists but a flow map is missing, recommend `$user-flow-map <topic>`.
+   - If a flow map exists but UI requirements are missing, recommend `$ui-interview --requirements-only <topic>`.
+   - If UI requirements exist but layout variations are missing, recommend `$ux-variations --layout-mode <topic>`.
+   - Only route directly to `$roadmap` or `$exec` when the project is non-UI/non-product work or already has accepted alignment artifacts and a consolidated prototype.
+   - The intended product sequence after reset is: `$icp` -> `$competitive-analysis` -> `$journey-map` -> `$positioning` -> `$user-flow-map` -> `$ui-interview --requirements-only` -> `$ux-variations --layout-mode` -> build variants/prototypes via `$exec` or the applicable prototype-building route -> `$uat --variant-evaluation` -> `$consolidate-variations` -> `$research-roadmap --post-prototype` -> `$spec-interview` or `$roadmap`.
+
+## Output
+
+```markdown
+Bootstrapped repository
+- README.md: [created | updated | preserved], source: [arguments | prompts | existing content]
+- Reset archive: [created archive/YYYY-MM-DD-HHMMSS | skipped (<reason>)]
+- Active concept seed: [concept.md | README.md ## Concept | other]
+- CLAUDE.md: [created | updated | unchanged], corresponding workflow block appears once
+- AGENTS.md: [created | updated | unchanged], corresponding workflow block appears once
+- Monorepo safety block: [included (<heuristic>) | skipped]
+- Verification: [commands/checks run]
+- Recommended next command: [$pack install business-discovery | $pack install customer-lifecycle | $pack install product-design | $icp <concept> | $positioning <topic> | $user-flow-map <topic> | $ui-interview --requirements-only <topic> | $ux-variations --layout-mode <topic> | $roadmap | $exec]
+```
+
+## Constraints
+
+- Do not overwrite substantial existing `README.md` content without explicit user confirmation.
+- Do not invent setup, test, deploy, or architecture details that are not in the brief or repository.
+- Keep the README concise and useful for a new contributor.
+- Do not modify files other than `README.md`, `CLAUDE.md`, and `AGENTS.md` unless the user explicitly asks or invokes reset mode.
+- Reset mode may move stale files, including old docs/research/specs/tasks, into `archive/YYYY-MM-DD-HHMMSS/` and write that archive's `MANIFEST.md`; it may not delete files outright.
+- In reset mode, do not preserve old docs as active files just because they were marked salvageable. Use them only as archived historical evidence; active research and requirements restart from the high-level concept.
+- Do not create, modify, or suggest GitHub Actions workflows.
+
+
+## Default Shipping Contract
+
+Follow the shared shipping contract convention in CLAUDE.md.

package/packs/repo-maintenance/codex/env-setup/CHANGELOG.md

@@ -0,0 +1,5 @@
+# env-setup changelog (codex)
+
+## v0.0 - 2026-06-10
+
+- Initial version.

package/packs/repo-maintenance/codex/env-setup/SKILL.md

@@ -0,0 +1,71 @@
+---
+name: env-setup
+description: Scaffold the local env file with required variable stubs from .env.example and code, open it for the user to fill, and verify completeness by key names only — never reading secret values
+type: execution
+version: v0.0
+argument-hint: "[target env file or framework hint]"
+---
+
+# Env Setup
+
+Invoke as `$env-setup`.
+
+Scaffold the project's local environment file with stubs for every required variable, open it so the user can fill in values, and verify completeness by key names only. This skill must never read, print, or summarize secret values from any env file.
+
+## Process
+
+1. **Resolve the target file** from `$ARGUMENTS`:
+   - Default to `.env.local`.
+   - Accept an explicit file path (e.g. `.env`, `.dev.vars`) or a framework hint (e.g. `next`, `wrangler`) and map it to that framework's convention.
+   - If the repository's own convention differs from the default (e.g. plain Node projects loading `.env`, Wrangler projects using `.dev.vars`), use the detected convention and say so in the report.
+
+2. **Discover required variables.** Build the union of:
+   - Keys in `.env.example`, `.env.sample`, or equivalent template files.
+   - Code references: `process.env.X`, `import.meta.env.X`, `os.environ[...]`, and framework config files.
+   - Setup sections in `README.md` and project docs.
+   - If the target file already exists, extract key names only (e.g. `cut -d= -f1`) to learn which keys are already present. Never read, cat, print, or summarize values from the target file or any other secret-bearing env file.
+
+3. **Scaffold stubs:**
+   - Create the target file if it does not exist.
+   - Append only the missing keys as `KEY=` stubs, each with a one-line comment hint for where the value comes from (provider dashboard, teammate, generated locally).
+   - Never overwrite, reorder, or rewrite existing lines in the target file.
+
+4. **Gitignore guard:**
+   - Verify the target file is covered by `.gitignore`. If it is not, add a matching ignore entry and warn the user.
+   - Never remove an env file from `.gitignore`, and never commit the target env file.
+
+5. **Open the file for the user:**
+   - Open the target file in VS Code with `code <file>`.
+   - Inside WSL, if `code` is unavailable, follow the AGENTS.md/CLAUDE.md Windows/WSL file-opening convention (`wslpath` + `cmd.exe /c start`).
+
+6. **Verify by presence only.** When the user says they are done (or on a re-run):
+   - Report which keys are still empty, by key name only. Never echo values.
+   - For non-secret generatable keys (e.g. `AUTH_SECRET`, session salts), offer to generate a value locally with a command such as `openssl rand -base64 32` — only with user confirmation, and write it into the file without printing it back.
+
+7. **Write forward to `.env.example`:** if discovery found required keys that are missing from `.env.example`, append them there as empty stubs so the template stays complete. This is a tracked change and ships normally.
+
+## Output
+
+```markdown
+Env setup
+- Target file: <path> [created | updated | already complete]
+- Keys scaffolded: [key names | none]
+- Keys still empty: [key names | none]
+- Gitignore: [already covered | entry added | WARNING not covered]
+- Editor: [opened in VS Code | open manually: <path>]
+- .env.example: [updated with N keys | unchanged]
+- **Next work:** [fill in the empty keys listed above | none]
+- **Recommended next command:** [re-run $env-setup to verify completeness | none]
+```
+
+## Constraints
+
+- Never read, print, echo, or summarize secret **values** from any env file — operate on key names only.
+- Never commit the target env file, and never weaken `.gitignore` coverage of env files.
+- Never overwrite or rewrite existing lines in the target env file; only append missing stubs.
+- If the user pastes a secret value into the conversation, warn them that it is now in chat history and suggest rotating it if sensitive.
+- Do not invent required variables that no template, code reference, or doc mentions.
+
+## Default Shipping Contract
+
+Follow the shared shipping contract convention in CLAUDE.md. Only `.env.example` and `.gitignore` edits are tracked-file mutations to ship; the target env file itself is never committed.

package/packs/repo-maintenance/codex/env-setup/agents/openai.yaml

@@ -0,0 +1,7 @@
+interface:
+  display_name: "Env Setup"
+  short_description: "Scaffold local env file stubs without reading secrets"
+  default_prompt: "Use $env-setup to scaffold the local env file with required variable stubs, open it for filling in values, and verify completeness by key names only."
+
+policy:
+  allow_implicit_invocation: true

package/packs/report-gen/PACK.md

@@ -0,0 +1,21 @@
+# Report Gen Pack
+
+Report generation skills for building HTML report websites. Produces structured, visual report outputs from project data.
+
+Install this pack when generating HTML report websites from project or analysis data.
+
+Install in a project with:
+
+```bash
+scripts/pack.sh install report-gen
+```
+
+Then refresh local skill links if needed:
+
+```bash
+scripts/pack.sh refresh
+```
+
+## Skills
+
+- `report-website`: Generate a self-contained HTML report website from structured data or analysis results.