@fernado03/zoo-flow 0.1.0

package/templates/full/.roo/skills/in-progress/review/SKILL.md

@@ -0,0 +1,39 @@
+---
+name: review
+description: Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
+---
+
+# Review
+
+Issue tracker should exist; run `/setup-matt-pocock-skills` if `docs/agents/issue-tracker.md` missing.
+
+## 1. Fixed point
+
+1. Use user-supplied commit/branch/tag/`main`/`HEAD~N` exactly.
+2. If missing, ask: `Review against what — a branch, a commit, or main?`
+3. Diff: `git diff {fixed-point}...HEAD`.
+4. Commits: `git log {fixed-point}..HEAD --oneline`.
+
+## 2. Spec
+
+Order:
+1. Issue refs in commits (`#123`, `Closes #45`, GitLab refs); fetch via `docs/agents/issue-tracker.md`.
+2. User path.
+3. Matching PRD/spec under `docs/`, `specs/`, `.scratch/`.
+4. If none, ask. If no spec, skip Spec axis with `no spec available`.
+
+## 3. Standards
+
+Collect: `CLAUDE.md`, `AGENTS.md`, `CONTRIBUTING.md`, context docs, `docs/adr/`, `.editorconfig`, `eslint.config.*`, `biome.json`, Prettier config, `tsconfig.json`, `STYLE.md`, `STANDARDS.md`, `STYLEGUIDE.md`, similar.
+
+## 4. Parallel sub-agents
+
+Standards prompt: diff command; commits; standards files; report documented-standard violations per file/hunk; cite standard; hard vs judgement; skip tooling-enforced; under 400 words.
+
+Spec prompt: diff command; commits; spec path/content; report missing/partial requirements, scope creep, wrong-looking implementation; quote spec line; under 400 words.
+
+## 5. Aggregate
+
+1. Present `## Standards` and `## Spec` separately.
+2. DO NOT merge/rerank axes.
+3. End with counts per axis + worst issue.

package/templates/full/.roo/skills/in-progress/writing-beats/SKILL.md

@@ -0,0 +1,32 @@
+---
+name: writing-beats
+description: Shape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write only that beat, then offer options for where to pivot next, beat by beat, until the article reaches a natural end. Use when the user has raw material and wants to assemble it as a narrative rather than an argument.
+---
+
+# Writing Beats
+
+## Setup
+
+1. Read raw markdown fully.
+2. If article output path missing, ask once.
+3. Never edit raw material.
+4. Re-read article before every write.
+
+## Loop
+
+1. Offer 2–3 starting beats from raw material.
+2. Preview likely next pivots for each.
+3. User picks.
+4. Write only selected beat to article.
+5. Re-read article.
+6. Offer 2–3 next beats from current ending.
+7. Loop until natural end.
+
+## Rules
+
+- Beat = one move: scene/point/question/aside/twist.
+- Size to need: sentence, paragraph, or short vignette.
+- If needs headings/5 paragraphs, split.
+- Pull/paraphrase/split/merge raw fragments.
+- Leave unused raw material.
+- Rewrite/go back → edit specific beat; preserve rest.

package/templates/full/.roo/skills/in-progress/writing-fragments/SKILL.md

@@ -0,0 +1,45 @@
+---
+name: writing-fragments
+description: Grilling session that mines the user for fragments — heterogeneous nuggets of writing (claims, vignettes, sharp sentences, half-thoughts) — and appends them to a single document as raw material for a future article. Use when the user wants to develop ideas before imposing structure, or mentions "fragments", "ideate", or "raw material" for writing.
+---
+
+# Writing Fragments
+
+## Setup
+
+1. Capture fragments from initial prompt onward.
+2. If output path missing, ask once.
+3. First write: one H1 working title; no metadata/TOC/date.
+4. Re-read file before every write.
+5. Append only unless user requests specific edit.
+
+## Fragment forms
+
+- Sharp sentence.
+- Claim + one-line reason.
+- Vignette/scenario/analogy/code snippet.
+- Half-thought.
+- Quote/dialogue.
+- Observation cluster.
+- Complaint/confession/punchline.
+
+## File format
+
+```markdown
+# Working title
+
+Fragment one.
+
+---
+
+Fragment two.
+```
+
+Rules:
+- Separate fragments with `---`.
+- No body headings/tags.
+- Order = capture order.
+- Append silently; mention briefly.
+- Preserve user edits.
+- Support `cut last`, `rewrite`, `merge` immediately.
+- DO NOT impose outline/structure.

package/templates/full/.roo/skills/in-progress/writing-shape/SKILL.md

@@ -0,0 +1,50 @@
+---
+name: writing-shape
+description: Take a markdown file of raw material and shape it into an article through a conversational session — drafting candidate openings, growing the piece paragraph by paragraph, arguing about format (lists, tables, callouts, quotes) at each step. Use when the user has a pile of notes, fragments, or a rough draft and wants help turning it into something publishable.
+---
+
+# Writing Shape
+
+## Setup
+
+1. Read raw markdown fully.
+2. Treat raw file read-only.
+3. If article path missing, ask once.
+4. Re-read article before every write.
+
+## Loop
+
+1. Draft 2–3 openings with different thesis/angle.
+2. User picks or composes hybrid.
+3. Opening defines article path.
+4. Ask what reader needs next.
+5. Pull from raw material.
+6. Argue format: prose/list/table/callout/quote/code.
+7. Append agreed block immediately.
+8. Repeat until article done.
+
+## Pressure tests
+
+- What does this paragraph do that previous didn't?
+- If cut, what breaks?
+- Prose/list/table/callout? Why?
+- Sentence doing two jobs? Split or pick one.
+- Opening promised X; current draft drifted to Y?
+
+## Format rules
+
+- Prose carries argument.
+- List only for parallel items.
+- Callout for derailing tips/warnings/asides.
+- Table when same fields repeat 3+ times.
+- Quote when exact wording matters.
+- Code block for multi-line/runnable/illustrative; inline code for single token.
+
+## Rules
+
+- Mine pile; do not follow as script.
+- Paraphrase/split/merge fragments.
+- If pile lacks needed example/info, ask user or cut section.
+- Preserve user edits.
+- Edit specific paragraph in place when requested.
+- DO NOT publish or add unsolicited frontmatter.

package/templates/full/.roo/skills/misc/README.md

@@ -0,0 +1,6 @@
+# Misc
+
+- **[git-guardrails-claude-code](./git-guardrails-claude-code/SKILL.md)** — Block dangerous git cmds in Claude Code.
+- **[migrate-to-shoehorn](./migrate-to-shoehorn/SKILL.md)** — Replace test `as` assertions with shoehorn helpers.
+- **[scaffold-exercises](./scaffold-exercises/SKILL.md)** — Create exercise dirs passing lint.
+- **[setup-pre-commit](./setup-pre-commit/SKILL.md)** — Add Husky + lint-staged + Prettier checks.

package/templates/full/.roo/skills/misc/git-guardrails-claude-code/SKILL.md

@@ -0,0 +1,64 @@
+---
+name: git-guardrails-claude-code
+description: Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
+---
+
+# Setup Git Guardrails
+
+Block patterns: `git push`, `git reset --hard`, `git clean -f`, `git clean -fd`, `git branch -D`, `git checkout .`, `git restore .`, `push --force`, `reset --hard`.
+
+## Process
+
+1. Ask scope: Project `.claude/settings.json` or Global `~/.claude/settings.json`.
+2. Copy `scripts/block-dangerous-git.sh` to `.claude/hooks/block-dangerous-git.sh` in selected scope.
+3. Run `chmod +x {script}`.
+4. Merge hook into settings; DO NOT overwrite existing settings.
+
+Project settings:
+
+```json
+{
+  "hooks": {
+    "PreToolUse": [
+      {
+        "matcher": "Bash",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "\"$CLAUDE_PROJECT_DIR\"/.claude/hooks/block-dangerous-git.sh"
+          }
+        ]
+      }
+    ]
+  }
+}
+```
+
+Global settings:
+
+```json
+{
+  "hooks": {
+    "PreToolUse": [
+      {
+        "matcher": "Bash",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "~/.claude/hooks/block-dangerous-git.sh"
+          }
+        ]
+      }
+    ]
+  }
+}
+```
+
+5. Ask pattern customisation.
+6. Verify:
+
+```bash
+echo '{"tool_input":{"command":"git push origin main"}}' | {path-to-script}
+```
+
+Expected: exit 2 + `BLOCKED` stderr.

package/templates/full/.roo/skills/misc/git-guardrails-claude-code/scripts/block-dangerous-git.sh

@@ -0,0 +1,25 @@
+#!/bin/bash
+
+INPUT=$(cat)
+COMMAND=$(echo "$INPUT" | jq -r '.tool_input.command')
+
+DANGEROUS_PATTERNS=(
+  "git push"
+  "git reset --hard"
+  "git clean -fd"
+  "git clean -f"
+  "git branch -D"
+  "git checkout \."
+  "git restore \."
+  "push --force"
+  "reset --hard"
+)
+
+for pattern in "${DANGEROUS_PATTERNS[@]}"; do
+  if echo "$COMMAND" | grep -qE "$pattern"; then
+    echo "BLOCKED: '$COMMAND' matches dangerous pattern '$pattern'. The user has prevented you from doing this." >&2
+    exit 2
+  fi
+done
+
+exit 0

package/templates/full/.roo/skills/misc/migrate-to-shoehorn/SKILL.md

@@ -0,0 +1,37 @@
+---
+name: migrate-to-shoehorn
+description: Migrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.
+---
+
+# Migrate to Shoehorn
+
+RULE: Test code only. Never production.
+
+## Install
+
+```bash
+npm i @total-typescript/shoehorn
+```
+
+## Mapping
+
+- `as Type` → `fromPartial()`.
+- `as unknown as Type` → `fromAny()`.
+- `fromPartial()` = partial data that should type-check.
+- `fromAny()` = intentionally wrong data.
+- `fromExact()` = full object now, partial later.
+
+## Workflow
+
+1. Ask target test files/use cases if missing.
+2. Install dependency.
+3. Find assertions:
+
+```bash
+grep -r " as [A-Z]" --include="*.test.ts" --include="*.spec.ts"
+```
+
+4. Replace `as Type` with `fromPartial()`.
+5. Replace `as unknown as Type` with `fromAny()`.
+6. Add imports.
+7. Run type check.

package/templates/full/.roo/skills/misc/scaffold-exercises/SKILL.md

@@ -0,0 +1,61 @@
+---
+name: scaffold-exercises
+description: Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section.
+---
+
+# Scaffold Exercises
+
+Goal: create exercise dirs passing `pnpm ai-hero-cli internal lint`, then commit.
+
+## Naming
+
+- Sections: `exercises/XX-section-name/`.
+- Exercises: `XX.YY-exercise-name/` inside section.
+- Lowercase dash-case.
+
+## Variants
+
+Each exercise needs ≥1: `problem/`, `solution/`, `explainer/`. Default stub: `explainer/` unless plan says otherwise.
+
+## Required files
+
+- Each variant folder: non-empty `readme.md`.
+- Minimal readme:
+
+```md
+# Exercise Title
+
+Description here
+```
+
+- If folder has code, `main.ts` >1 line required.
+- Readme-only stubs allowed.
+
+## Workflow
+
+1. Parse plan into sections/exercises/variants.
+2. `mkdir -p` dirs.
+3. Create readme stubs.
+4. Run `pnpm ai-hero-cli internal lint`.
+5. Fix until pass.
+6. Moves/renames: use `git mv`, not `mv`.
+7. Commit with `git commit`.
+
+## Lint constraints
+
+- Exercise has subfolder.
+- At least one of `problem/`, `explainer/`, `explainer.1/` exists.
+- Primary readme exists and non-empty.
+- No `.gitkeep`.
+- No `speaker-notes.md`.
+- No broken links.
+- No `pnpm run exercise` in readmes.
+- `main.ts` required only when code present.
+
+## Example
+
+```bash
+mkdir -p exercises/05-memory-skill-building/05.01-introduction-to-memory/explainer
+mkdir -p exercises/05-memory-skill-building/05.02-short-term-memory/{explainer,problem,solution}
+mkdir -p exercises/05-memory-skill-building/05.03-long-term-memory/explainer
+```

package/templates/full/.roo/skills/misc/setup-pre-commit/SKILL.md

@@ -0,0 +1,62 @@
+---
+name: setup-pre-commit
+description: Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.
+---
+
+# Setup Pre-Commit Hooks
+
+Creates Husky pre-commit, lint-staged Prettier, optional typecheck/test.
+
+## Process
+
+1. Detect package manager: `package-lock.json`→npm; `pnpm-lock.yaml`→pnpm; `yarn.lock`→yarn; `bun.lockb`→bun; default npm.
+2. Install dev deps, adapting package manager:
+
+```bash
+npm i -D husky lint-staged prettier
+```
+
+3. Init Husky:
+
+```bash
+npx husky init
+```
+
+4. Write `.husky/pre-commit`, adapting package manager; omit missing scripts and tell user:
+
+```text
+npx lint-staged
+npm run typecheck
+npm run test
+```
+
+5. Create `.lintstagedrc`:
+
+```json
+{
+  "*": "prettier --ignore-unknown --write"
+}
+```
+
+6. Create `.prettierrc` only if no Prettier config:
+
+```json
+{
+  "useTabs": false,
+  "tabWidth": 2,
+  "printWidth": 80,
+  "singleQuote": false,
+  "trailingComma": "es5",
+  "semi": true,
+  "arrowParens": "always"
+}
+```
+
+7. Verify: executable `.husky/pre-commit`; `.lintstagedrc`; `prepare` script = `husky`; Prettier config; `npx lint-staged`.
+8. Commit:
+
+```bash
+git commit -m "Add pre-commit hooks (husky + lint-staged + prettier)"
+```
+
+RULE: Wait for explicit user approval before commit if current mode requires HITL.

package/templates/full/.roo/skills/personal/README.md

@@ -0,0 +1,6 @@
+# Personal
+
+Personal setup only; not promoted.
+
+- **[edit-article](./edit-article/SKILL.md)** — Restructure/tighten article drafts.
+- **[obsidian-vault](./obsidian-vault/SKILL.md)** — Search/create/manage Obsidian notes.

package/templates/full/.roo/skills/personal/edit-article/SKILL.md

@@ -0,0 +1,13 @@
+---
+name: edit-article
+description: Edit and improve articles by restructuring sections, improving clarity, and tightening prose. Use when user wants to edit, revise, or improve an article draft.
+---
+
+# Edit Article
+
+1. Divide article by headings.
+2. Identify main point per section.
+3. Reorder sections/content so dependencies flow first.
+4. Confirm section plan with user.
+5. Rewrite each section for clarity/coherence/flow.
+6. Max 240 chars per paragraph.

package/templates/full/.roo/skills/personal/obsidian-vault/SKILL.md

@@ -0,0 +1,39 @@
+---
+name: obsidian-vault
+description: Search, create, and manage notes in the Obsidian vault with wikilinks and index notes. Use when user wants to find, create, or organize notes in Obsidian.
+---
+
+# Obsidian Vault
+
+## Vault path
+
+1. Use `$OBSIDIAN_VAULT_PATH`.
+2. If unset, STOP and ask absolute vault path.
+
+## Naming
+
+- Index notes aggregate related topics: `Ralph Wiggum Index.md`.
+- Title Case filenames.
+- No folders for org; use wikilinks/index notes.
+
+## Linking
+
+- Use `[[wikilinks]]`.
+- Add related/dependency links at bottom.
+- Index notes = wikilink lists.
+
+## Commands
+
+```bash
+find "/mnt/d/Obsidian Vault/AI Research/" -name "*.md" | grep -i "keyword"
+grep -rl "keyword" "/mnt/d/Obsidian Vault/AI Research/" --include="*.md"
+grep -rl "\\[\\[Note Title\\]\\]" "/mnt/d/Obsidian Vault/AI Research/"
+find "/mnt/d/Obsidian Vault/AI Research/" -name "*Index*"
+```
+
+## Create note
+
+1. Title Case filename.
+2. Write one learning unit.
+3. Add related wikilinks at bottom.
+4. If numbered sequence, use hierarchy.

package/templates/full/.roo/skills/productivity/README.md

@@ -0,0 +1,6 @@
+# Productivity
+
+- **[caveman](./caveman/SKILL.md)** — Ultra-compressed communication mode.
+- **[grill-me](./grill-me/SKILL.md)** — Relentless plan/design interview.
+- **[handoff](./handoff/SKILL.md)** — Save compact handoff doc in temp dir.
+- **[write-a-skill](./write-a-skill/SKILL.md)** — Create skill structure/docs/scripts.

package/templates/full/.roo/skills/productivity/caveman/SKILL.md

@@ -0,0 +1,28 @@
+---
+name: caveman
+description: >
+  Ultra-compressed communication mode. Cuts token usage ~75% by dropping
+  filler, articles, and pleasantries while keeping full technical accuracy.
+  Use when user says "caveman mode", "talk like caveman", "use caveman",
+  "less tokens", "be brief", or invokes /caveman.
+---
+
+# Caveman
+
+ACTIVE until user says stop/normal mode.
+
+Rules:
+- Drop articles/filler/pleasantries/hedging.
+- Keep technical accuracy + exact terms.
+- Fragments OK.
+- Use short synonyms.
+- Abbrev: DB/auth/config/req/res/fn/impl.
+- Use arrows for causality.
+- Code blocks unchanged.
+- Quote errors exact.
+
+Pattern: `[thing] [action] [reason]. [next step].`
+
+Auto-clarity:
+- Use normal clarity briefly for security warnings/irreversible actions/risky multi-step/repeated clarification.
+- Resume caveman after.

package/templates/full/.roo/skills/productivity/grill-me/SKILL.md

@@ -0,0 +1,13 @@
+---
+name: grill-me
+description: Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
+---
+
+# Grill Me
+
+1. Interview plan/design until shared understanding.
+2. Walk design tree branch-by-branch.
+3. Resolve dependency order between decisions.
+4. Ask one question at a time.
+5. Include recommended answer.
+6. Inspect code instead of asking when code can answer.

package/templates/full/.roo/skills/productivity/handoff/SKILL.md

@@ -0,0 +1,14 @@
+---
+name: handoff
+description: Compact the current conversation into a handoff document for another agent to pick up.
+argument-hint: "What will the next session be used for?"
+---
+
+# Handoff
+
+1. Write handoff for fresh agent.
+2. Save in OS temp dir, not workspace.
+3. Tailor to user args.
+4. Include suggested skills section.
+5. Reference artifacts by path/URL; do not duplicate.
+6. Redact secrets/API keys/passwords/PII.

package/templates/full/.roo/skills/productivity/write-a-skill/SKILL.md

@@ -0,0 +1,52 @@
+---
+name: write-a-skill
+description: Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
+---
+
+# Write A Skill
+
+## Process
+
+1. Gather: task/domain; use cases/triggers; scripts needed; references.
+2. Draft: concise `SKILL.md`; reference files if `SKILL.md` >100 lines or distinct domains; scripts for deterministic repeated ops.
+3. Review with user.
+4. Revise.
+
+## Structure
+
+```text
+skill-name/
+├── SKILL.md
+├── REFERENCE.md
+├── EXAMPLES.md
+└── scripts/
+    └── helper.js
+```
+
+## Frontmatter
+
+```md
+---
+name: skill-name
+description: Brief description. Use when [specific triggers].
+---
+```
+
+Description rules:
+- Max 1024 chars.
+- Third person.
+- First sentence = capability.
+- Second sentence = `Use when ...` triggers.
+
+## Scripts
+
+Add when: deterministic op; repeated code; explicit error handling needed.
+
+## Review checklist
+
+- [ ] Description has triggers.
+- [ ] `SKILL.md` under 100 lines.
+- [ ] No time-sensitive info.
+- [ ] Terminology consistent.
+- [ ] Examples concrete.
+- [ ] References one level deep.

package/templates/full/.roomodes

@@ -0,0 +1,47 @@
+{
+  "customModes": [
+    {
+      "slug": "code-tweaker",
+      "name": "⚡ Code Tweaker",
+      "roleDefinition": "You are an Execution Specialist. You implement, test, update docs, prototype, and commit when explicitly approved.",
+      "whenToUse": "Use for direct implementation, CSS/UI changes, TDD loops, documentation updates, runnable prototypes, known fixes, and local commits.",
+      "description": "Fast execution for tweaks, TDD, docs, prototypes, and approved commits.",
+      "customInstructions": "Use `.roo/rules-code-tweaker/` for mode-specific behavior.\n\nPermitted commands: /tweak, /tdd, /update-docs, /commit-and-document, /prototype.\n\nFollow `.roo/rules/01-command-protocol.md` to load and execute commands. Follow `.roo/rules/00-paths.md` for path safety. Follow `.roo/rules/03-manual-reply-protocol.md` when asking the user to choose, approve, or continue.\n\nIf assigned any other command, stop and report the routing error.",
+      "groups": [
+        "read",
+        "edit",
+        "command",
+        "mcp"
+      ]
+    },
+    {
+      "slug": "system-architect",
+      "name": "🏗️ System Architect",
+      "roleDefinition": "You are a System Architect. You plan, diagnose, explore, triage, and design. You do NOT write implementation code.",
+      "whenToUse": "Use for complex debugging (/fix), feature planning (/feature), architecture changes (/refactor), issue triage (/triage), and codebase exploration (/explore).",
+      "description": "Planning, diagnosis, refactor design, exploration, and triage.",
+      "customInstructions": "Use `.roo/rules-system-architect/` for mode-specific behavior.\n\nPermitted commands: /feature, /fix, /refactor, /explore, /triage.\n\nFollow `.roo/rules/01-command-protocol.md` to load and execute commands. Follow `.roo/rules/00-paths.md` for path safety. Follow `.roo/rules/03-manual-reply-protocol.md` when asking the user to choose, approve, or continue.\n\nIf assigned any other command, stop and report the routing error.",
+      "groups": [
+        "command",
+        "mcp",
+        "read",
+        [
+          "edit",
+          {
+            "fileRegex": "(.*\\.md$|^\\.scratch/.*|^docs/.*)",
+            "description": "Markdown files, .scratch/, and docs/ directories only"
+          }
+        ]
+      ]
+    },
+    {
+      "slug": "custom-orchestrator",
+      "name": "🪃 Custom Orchestrator",
+      "roleDefinition": "You are a PM and router. You choose workflows and delegate subtasks. You NEVER inspect implementation files, write code, or use switch_mode.",
+      "whenToUse": "Use for initial task planning, choosing slash commands, routing work, or discussing workflow.",
+      "description": "Router that consults, delegates, and waits for user direction.",
+      "customInstructions": "Use `.roo/rules-custom-orchestrator/` for mode-specific behavior.\n\nRoute only these commands:\n\n- /tweak, /tdd, /update-docs, /commit-and-document, /prototype -> code-tweaker\n- /fix, /feature, /refactor, /explore, /triage -> system-architect\n\nUse `new_task` only. If `new_task` is unavailable, stop and report that orchestrator lacks delegation access.\n\nFollow `.roo/rules/03-manual-reply-protocol.md` when offering workflow choices.",
+      "groups": []
+    }
+  ]
+}