constitution:checklist-generator
Distill CONSTITUTION.md into 6-12 actionable checklist items with semantic deduplication. Use when user asks to "generate checklist", "create action items from constitution", or after amendments to regenerate verification tasks.
What this skill does
# Constitution Checklist Generator
You are generating an **Implementation Checklist** from a project's CONSTITUTION.md file.
## Goal
Distill constitutional principles into 6-12 actionable, verifiable checkbox items that engineers can use to validate their work complies with project governance.
## Workflow
### 1. Locate Constitution
Search for CONSTITUTION.md:
1. Current directory
2. Parent directories (walk up tree)
3. Git root if available
If not found: Error with "No CONSTITUTION.md found. Run constitution:writer first."
### 2. Extract Principles
Parse CONSTITUTION.md:
- Identify `##` sections (principles)
- Extract core requirements from each section
- Ignore preamble, changelog, footer
### 3. Distill to Checkboxes
**Target:** 6-12 items total (fewer is better)
**Guidelines:**
- Combine related sub-rules into single checkbox
- Make specific and verifiable (not "Write good code")
- Prioritize NON-NEGOTIABLE items first
- Use active voice ("Ensure X", "Verify Y", "Document Z")
**Example Transformations:**
- Principle: "Single Responsibility - Each function does one thing"
→ Checkbox: `[ ] Functions have single, clear purpose (check for multi-responsibility)`
- Principle: "No Silent Failures - Always log errors, never empty catch"
→ Checkbox: `[ ] Error handlers log context (no empty catch/except blocks)`
- Principle: "Test Coverage - 80% minimum, integration tests for APIs"
→ Checkbox: `[ ] Test coverage ≥80% with integration tests for all API endpoints`
### 4. Semantic Deduplication (If Existing Checklist)
When `## Implementation Checklist` section exists:
**Algorithm:**
1. Parse existing checklist items (strip `[ ]` prefixes)
2. Parse newly generated items
3. For each existing item:
- Find semantic match in new items (keyword similarity)
- If match found: **KEEP existing wording** (preserve customization)
- If no match: **REMOVE** (outdated principle)
4. For each new item:
- If not covered by kept items: **ADD**
- If similar to kept item: Compare specificity
- Keep more specific version
- Log decision: "Kept existing item (more specific)"
**Similarity Scoring:**
- Extract keywords (lowercase, remove common words)
- Count shared keywords
- Threshold: ≥50% shared keywords = similar
**Specificity Comparison:**
- Count specific technical terms (e.g., ">=80%", "API endpoints", "conventional format")
- More specific terms = higher specificity
- Tie: Keep existing (preserves user customization)
**Example:**
```
Existing: "Use conventional commits"
New: "All commits follow conventional format"
→ KEEP existing (semantic match, similar specificity)
Existing: "Tests required for new features"
New: "Test coverage ≥80% with integration tests for all API endpoints"
→ REPLACE with new (new is more specific)
```
### 5. Append or Update Checklist
**If no existing checklist:**
Append to end of CONSTITUTION.md:
```markdown
---
## Implementation Checklist
Before considering work complete, verify:
- [ ] [Item 1]
- [ ] [Item 2]
- [ ] [Item 3]
- [ ] [Item 4]
- [ ] [Item 5]
- [ ] [Item 6]
```
**If existing checklist:**
Replace entire `## Implementation Checklist` section with deduplicated version.
**Preserve:**
- Checkbox format: `- [ ]` (unchecked)
- Ordering: Most critical first
- Section header: `## Implementation Checklist`
### 6. Report
Output summary:
```
✓ Generated checklist from CONSTITUTION.md
- [N] items total
- [K] kept from existing checklist
- [R] removed (outdated)
- [A] added (new principles)
Merge decisions:
- "Use conventional commits" KEPT (matches "All commits follow...")
- "Tests required" REPLACED (new version more specific)
- "Document public APIs" ADDED (new principle)
```
## Edge Cases
**No principles found:** Error with "CONSTITUTION.md has no ## sections"
**Constitution too short:** If <3 principles, generate 3-5 items (don't pad artificially)
**Uncertain similarity:** When in doubt, KEEP both items (err on side of completeness)
**User customization:** Always preserve existing wording when semantically equivalent
## Anti-Patterns
❌ **Don't:**
- Generate vague items like "Write quality code"
- Create >15 items (checkbox fatigue)
- Remove existing items without semantic analysis
- Duplicate items with slightly different wording
- Change existing wording when semantic match found
✅ **Do:**
- Make items specific and verifiable
- Combine related sub-rules
- Preserve user customizations
- Log merge decisions clearly
- Keep count between 6-12 items
Related in General
modeling-omnistudio-epc-catalog
IncludedSalesforce Industries CME EPC product-modeling skill for Product2-based catalog creation. Use when creating EPC products, configuring product attributes, building offer bundles with Product Child Items, or reviewing EPC DataPack JSON metadata for product catalog changes. TRIGGER when: user creates or updates Product2 EPC records, AttributeAssignment payloads, AttributeMetadata/AttributeDefaultValues, Offer bundles, or ProductChildItem relationships. DO NOT TRIGGER when: designing OmniScripts/FlexCards/Integration Procedures (use building-omnistudio-omniscript, building-omnistudio-flexcard, or building-omnistudio-integration-procedure), implementing Apex business logic (use generating-apex), or troubleshooting deployment pipelines (use deploying-metadata).
relationship-science-coach
IncludedUse this skill for direct, practical adult relationship coaching: couples conflict, repair, trust, marriage, dating, flirting, attachment patterns, emotional connection, sex, desire differences, eroticism, kink negotiation, affection, love languages, breakups, and long-term passion. Draw on Gottman, EFT and Hold Me Tight, attachment science, modern sex research, Perel, Nagoski, Kerner, Schnarch, Love and Stosny, and flexible love-language tools. Be concrete and low-hedge. Redirect only for imminent danger, abuse, coercive control, minors, non-consent, self-harm, stalking, or medical/legal/psychiatric decisions.
building-sf-integrations
IncludedSalesforce integration architecture and runtime plumbing with 120-point scoring. Use this skill to set up Named Credentials, External Credentials, External Services, REST/SOAP callout patterns, Platform Events, and Change Data Capture. TRIGGER when: user sets up Named Credentials, External Services, REST/SOAP callouts, Platform Events, CDC, or touches .namedCredential-meta.xml files. DO NOT TRIGGER when: Connected App/OAuth config (use configuring-connected-apps), Apex-only logic (use generating-apex), or data import/export (use handling-sf-data).
venue-templates
IncludedAccess comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.
let-fate-decide
IncludedDraws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated. Interprets the spread to guide next steps. Use when the user says 'let fate decide', 'YOLO', 'whatever', 'idk', or other nonchalant phrases, makes Yu-Gi-Oh references, or when you are about to arbitrarily pick between multiple reasonable approaches. Prefer over ask-questions-if-underspecified when the user's tone is casual or playful rather than precision-seeking.
net-ops
IncludedCross-platform network troubleshooting (Windows, macOS, Linux) via local or remote shell. Use for: DNS broken, can't resolve hostnames, nslookup/dig works but apps fail, NRPT, WFP, scutil, /etc/resolver, systemd-resolved, /etc/resolv.conf, NetworkManager, VPN DNS leak residue (ProtonVPN/Mullvad/WireGuard/AnyConnect), AV/firewall blocking DNS or DoH, Tailscale DNS interaction, intermittent connectivity, remote diagnostics over SSH.