feat: skill optimization + add Tessl Skill Review CI

.agents/skills/tessl__bulk-optimize

@@ -0,0 +1 @@
+../../.tessl/tiles/tessl-labs/bulk-optimize/skills/bulk-optimize

.claude/skills/tessl__bulk-optimize

@@ -0,0 +1 @@
+../../.tessl/tiles/tessl-labs/bulk-optimize/skills/bulk-optimize

.codex/config.toml

@@ -0,0 +1,4 @@
+[mcp_servers.tessl]
+type = "stdio"
+command = "tessl"
+args = [ "mcp", "start" ]

.codex/skills/tessl__bulk-optimize

@@ -0,0 +1 @@
+../../.tessl/tiles/tessl-labs/bulk-optimize/skills/bulk-optimize

.cursor/mcp.json

@@ -0,0 +1,12 @@
+{
+  "mcpServers": {
+    "tessl": {
+      "type": "stdio",
+      "command": "tessl",
+      "args": [
+        "mcp",
+        "start"
+      ]
+    }
+  }
+}

.cursor/skills/tessl__bulk-optimize

@@ -0,0 +1 @@
+../../.tessl/tiles/tessl-labs/bulk-optimize/skills/bulk-optimize

.gemini/settings.json

@@ -0,0 +1,12 @@
+{
+  "mcpServers": {
+    "tessl": {
+      "type": "stdio",
+      "command": "tessl",
+      "args": [
+        "mcp",
+        "start"
+      ]
+    }
+  }
+}

.gemini/skills/tessl__bulk-optimize

@@ -0,0 +1 @@
+../../.tessl/tiles/tessl-labs/bulk-optimize/skills/bulk-optimize

.github/skills/tessl__bulk-optimize

@@ -0,0 +1 @@
+../../.tessl/tiles/tessl-labs/bulk-optimize/skills/bulk-optimize

.github/workflows/skill-review.yml

@@ -0,0 +1,22 @@
+# Tessl Skill Review — runs on PRs that change any SKILL.md; posts scores as one PR comment.
+# Docs: https://github.com/tesslio/skill-review
+name: Tessl Skill Review
+
+on:
+  pull_request:
+    branches: [main]
+    paths:
+      - "**/SKILL.md"
+
+jobs:
+  review:
+    runs-on: ubuntu-latest
+    permissions:
+      pull-requests: write
+      contents: read
+    steps:
+      - uses: actions/checkout@v4
+      - uses: tesslio/skill-review@main
+      # Optional quality gate (off by default):
+      # with:
+      #   fail-threshold: 70

.mcp.json

@@ -0,0 +1,12 @@
+{
+  "mcpServers": {
+    "tessl": {
+      "type": "stdio",
+      "command": "tessl",
+      "args": [
+        "mcp",
+        "start"
+      ]
+    }
+  }
+}

.tessl/tiles/tessl-labs/bulk-optimize/README.md

@@ -0,0 +1,68 @@
+# Bulk Optimize
+
+A skill for bulk optimization of external skills for PR contributions (Alan's tool).
+
+## Purpose
+
+This skill is designed for **contributors** (like Alan) who:
+- Improve multiple skills in external/OSS repositories
+- Create pull requests with skill improvements
+- Need to avoid common PR rejection patterns
+- Want to validate changes before submitting
+
+**NOT for**: Personal skill improvement (use `skill-optimizer` instead)
+
+## Status: Ready for Testing ✅
+
+**Current Score**: 93% (Description: 100%, Content: 85%)
+
+## Key Features
+
+### Safety Checks
+- ✅ Auto-generated file detection (avoid googleworkspace scenario)
+- ✅ Merge conflict warnings (recent path migrations)
+- ✅ Domain expertise preservation (avoid coreyhaines31 scenario)
+- ✅ Repository pattern analysis
+
+### Validation
+- ✅ Code syntax validation (catch googleworkspace flag errors)
+- ✅ Command-line syntax validation
+- ✅ File reference validation
+- ✅ Post-change score verification
+
+### PR Guidance
+- ✅ Recommends one-skill-per-PR when appropriate
+- ✅ Risk assessment for high-scoring skills
+- ✅ Suggests opening issues first for unsolicited changes
+- ✅ Explains rubric for transparency
+
+## Files
+
+- `skills/bulk-optimize/SKILL.md` - Main skill (93% score)
+- `skills/bulk-optimize/RUBRIC.md` - Evaluation rubric reference
+- `COMPARISON.md` - Analysis vs endpoint approach
+- `README.md` - This file
+
+## Usage
+
+For bulk PR work on external repos:
+
+```bash
+# Clone/fork external repo
+gh repo fork owner/repo --clone
+
+# In Claude Code with bulk-optimize installed
+"Use bulk-optimize to improve skills in this repo"
+```
+
+The skill will:
+1. Run safety checks (auto-generated, conflicts)
+2. Analyze all skills
+3. Recommend scope (one-skill vs batch)
+4. Validate improvements
+5. Guide PR creation
+
+## See Also
+
+- **skill-optimizer**: For personal skill improvement (simpler, user-focused)
+- **auto-p-o**: Original bash script this replaces

.tessl/tiles/tessl-labs/bulk-optimize/skills/bulk-optimize/SKILL.md

@@ -0,0 +1,135 @@
+---
+name: bulk-optimize
+description: |
+  Bulk skill optimization for external PR contributions. Greps for "auto-generated" markers to skip generated files, validates Python/JS syntax with ast.parse and node --check, checks git log for recent migrations, runs tessl skill review, and generates PR templates with before/after scores. Use when improving multiple skills in external repositories, preparing bulk PRs, contributing skill improvements, batch editing skills, or mass updating open source skills.
+---
+
+# Bulk Optimize
+
+Improve external SKILL.md files for PR contributions using `tessl skill review` plus safety checks that prevent rejected PRs. Respects maintainers by detecting auto-generated files, preserving domain expertise, and suggesting appropriate PR scope.
+
+## For External PR Contributions
+
+Adds safety checks for contributing to other people's repositories. See [TEMPLATES.md](TEMPLATES.md) for lessons from past PR rejections.
+
+## Workflow
+
+### Phase 1: Safety Checks (CRITICAL)
+
+Run before making changes to prevent rejected PRs:
+
+```bash
+# 1. Auto-generated file detection
+grep -i "auto-generated\|generated by\|DO NOT EDIT\|generator:" <skill-path>/SKILL.md
+
+# 2. Recent migration detection
+git log --oneline -10 --all -- <skill-directory>/ | grep -i "migrate\|rename\|move"
+
+# 3. Repository pattern analysis
+find . -name "SKILL.md" -type f | head -5 | xargs head -20
+```
+
+**If auto-generated detected**: STOP - changes must go to generator source
+**If recent migration found**: WARN - may cause merge conflicts
+**Note domain patterns**: Preserve expert framing and terminology in Phase 4
+
+### Phase 2: Baseline Evaluation
+
+**Run review for each skill:**
+
+```bash
+tessl skill review <skill-path>/SKILL.md
+```
+
+Parse output to extract:
+- Overall score
+- Validation issues
+- Description/content dimension scores
+- Judge suggestions
+
+**If improving multiple skills:**
+- Track baseline scores for all
+- Identify which need improvement most
+- Consider PR scope (see Phase 7)
+
+### Phase 3: Discover Skill Bundle
+
+Read SKILL.md and list files in its directory. Bundle = SKILL.md + sibling files + referenced files. Use for progressive disclosure improvements.
+
+Use bundle context for recommendations.
+
+### Phase 4: Generate Recommendations (Preserve Domain Expertise)
+
+Review recommendations to preserve valuable domain knowledge. Grep for specialized terminology (CRO, funnel, A/B test, etc.).
+
+**KEEP**: Expert framing with domain concepts ("CRO expert who understands funnel optimization, conversion psychology...")
+**REMOVE**: Generic expert statements ("You are an expert at helping users...")
+
+For each issue: what to change, why (dimension + score), before/after, impact, domain check.
+
+### Phase 5: Validate Recommendations
+
+```python
+# Validate Python syntax
+import ast
+ast.parse(code_snippet)  # Raises SyntaxError if invalid
+```
+
+```bash
+# Validate command flags
+gh pr create --help | grep -q "\-\-flag" || echo "Invalid"
+
+# Validate file references
+[[ -f "$SKILL_DIR/$FILE" ]] || echo "Missing file"
+```
+
+### Phase 6: Present Recommendations
+
+Show recommendations with:
+- Current state (score)
+- Issue explanation
+- Recommended change
+- Impact
+- Domain preservation note
+
+**Get approval per skill or in batch** (user choice).
+
+### Phase 7: PR Scope Assessment
+
+**Multiple skills (15+)**: Recommend one-skill-per-PR for easier review. Start with 2-3 highest-impact, get feedback, iterate.
+
+**High-scoring skills (90%+)**: Open issue first before unsolicited PR. Risk: maintainer may not want cosmetic changes.
+
+### Phase 8: Apply Changes
+
+Apply approved changes to approved skills only.
+
+### Phase 9: Verify Improvements
+
+```bash
+# For each changed skill
+tessl skill review <skill-path>/SKILL.md
+```
+
+Show before/after scores.
+
+### Phase 10: Final Accuracy Review
+
+Re-run validation from Phase 5 on updated SKILL.md. Check:
+- ✓ Code syntax valid
+- ✓ Command flags correct
+- ✓ File references exist
+- ✓ Third-person voice
+- ✓ "Use when..." clause present
+
+Fix issues, then re-run `tessl skill review`.
+
+### Phase 11: PR Guidance
+
+Use commit message format, PR description template, and best practices from [TEMPLATES.md](TEMPLATES.md). Display ready-to-create PR info for user confirmation.
+
+## Notes
+
+- Uses `tessl skill review` plus PR-specific safety checks
+- For external PR work on repos you don't maintain
+- For personal skill improvement, use `skill-optimizer` instead

.tessl/tiles/tessl-labs/bulk-optimize/skills/bulk-optimize/TEMPLATES.md

@@ -0,0 +1,80 @@
+# Bulk Optimize Templates
+
+## Commit Message Format
+
+```bash
+git commit -m "$(cat <<'EOF'
+feat: improve <skill-name> skill quality scores
+
+- Add "Use when..." clause with trigger keywords (+15%)
+- Add executable code example (+10%)
+- Structure workflow into numbered steps (+8%)
+
+Score improvement: 72% → 95%
+
+Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
+EOF
+)"
+```
+
+## PR Description Template
+
+```markdown
+Hullo 👋 @<maintainer>
+
+I ran your skills through `tessl skill review` and found some targeted
+improvements. Here's the before/after:
+
+| Skill | Before | After | Change |
+|-------|--------|-------|--------|
+| <skill-name> | 72% | 95% | +23% |
+
+<details>
+<summary>Changes made</summary>
+
+- Added "Use when..." clause with natural trigger keywords
+- Replaced abstract advice with executable code example
+- Structured workflow into numbered validation steps
+
+</details>
+
+Honest disclosure — I work at @tesslio where we build tooling around
+skills like these. Not a pitch - just saw room for improvement and
+wanted to contribute.
+
+If you want to run reviews yourself, just `npm install @tessl/cli`
+then run `tessl skill review path/to/your/SKILL.md`.
+
+Thanks in advance 🙏
+```
+
+## Display Before Creating PR
+
+```
+Ready to create PR:
+
+Branch: improve/<skill-name>
+Commit: feat: improve <skill-name> skill quality scores
+Files: 1 changed (+15 -8)
+
+PR will be created to: <upstream-repo>
+
+Review changes? [Show diff / Create PR / Cancel]
+```
+
+## Best Practices from Successful PRs
+
+✅ **Concrete workflows** - Numbered steps with validation checkpoints
+✅ **Executable code** - Real, runnable examples (not pseudocode)
+✅ **Token efficiency** - Remove explanations of known concepts
+✅ **Progressive disclosure** - Link to REFERENCE.md vs inlining details
+✅ **One-skill-per-PR** - Easier review, higher acceptance rate
+
+## Past PR Rejections to Avoid
+
+| PR | Issue | Lesson |
+|----|-------|--------|
+| googleworkspace #320 | Invalid command flags | Validate all command syntax |
+| coreyhaines31 #65 | Bundled 15+ skills | One skill per PR for easier review |
+| JimLiu #53 | Changed high-scoring skill | Don't touch 90%+ skills without invitation |
+| Various | Auto-generated files | Always grep for "auto-generated" markers |

.tessl/tiles/tessl-labs/bulk-optimize/tile.json

@@ -0,0 +1,11 @@
+{
+  "name": "tessl-labs/bulk-optimize",
+  "version": "0.2.0",
+  "summary": "Bulk skill optimization for external PR contributions. Detects auto-generated files, merge conflicts, preserves domain expertise, validates syntax. Use when improving multiple external skills for pull requests.",
+  "private": true,
+  "skills": {
+    "bulk-optimize": {
+      "path": "skills/bulk-optimize/SKILL.md"
+    }
+  }
+}