Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Documentation templates for ADRs, runbooks, architecture docs, and knowledge transfer documents. Use when creating Architecture Decision Records, writing operational runbooks, documenting system architecture, or creating technical specifications. Do NOT use for code implementation or ticket management.
.claude/skills/bybren-llc-confluence-docs/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-11 | ✗→✓ | ▲ Improved | 24% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 7% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 22% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 23% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 46% | 0% |
Provide standardized templates for creating technical documentation. These templates ensure consistent, high-quality documentation across the project.
| ADR | Location | Topic | | ------- | ---------------------------------------------------------- | ------------------------- | | ADR-002 | docs/adr/ADR-002-constants-unification.md | Constants organization | | ADR-003 | docs/adr/ADR-003-dependency-upgrade-typescript-fixes.md | Dependency upgrades | | ADR-004 | docs/adr/ADR-004-server-component-data-access-pattern.md | Server component patterns | | ADR-005 | docs/adr/ADR-005-ci-infrastructure-services.md | CI infrastructure | | ADR-006 | docs/adr/ADR-006-bonus-pdf-private-bucket-security.md | Security patterns | | ADR-007 | docs/adr/ADR-007-rendertrust-marketing-pages.md | Marketing architecture |
markdown# ADR-XXX: [Title] ## Status [Proposed | Accepted | Deprecated | Superseded] ## Context What is the issue that we're seeing that motivates this decision? ## Decision What is the change that we're proposing and/or doing? ## Consequences ### Positive - [Benefit 1] - [Benefit 2] ### Negative - [Tradeoff 1] - [Tradeoff 2] ### Neutral - [Observation] ## Implementation Notes How should this decision be implemented? ## Related Decisions - ADR-XXX: [Related decision] ## References - [Link to relevant documentation]
markdown# Runbook: [Operation Name] ## Overview Brief description of what this runbook covers. ## Prerequisites - [ ] Access to [system] - [ ] Required permissions - [ ] Tools installed ## Procedure ### Step 1: [Action Name] \`\`\`bash # Command to execute \`\`\` **Expected output**: Description of what you should see **If error**: What to do if something goes wrong ### Step 2: [Action Name] ... ## Verification How to verify the operation was successful. ## Rollback Steps to undo the operation if needed. ## Troubleshooting ### Issue: [Common problem] **Symptoms**: What you see **Cause**: Why it happens **Solution**: How to fix it ## Contacts - Primary: [Name/Role] - Escalation: [Name/Role] ## Revision History | Date | Author | Changes | | ---------- | ------ | --------------- | | YYYY-MM-DD | Name | Initial version |
markdown# [System/Component] Architecture ## Overview High-level description of the system/component. ## Goals and Non-Goals ### Goals - [What this system should do] ### Non-Goals - [What this system should NOT do] ## Architecture Diagram \`\`\` [ASCII diagram or link to diagram] \`\`\` ## Components ### Component 1: [Name] - **Purpose**: What it does - **Location**: Where it lives - **Dependencies**: What it needs ### Component 2: [Name] ... ## Data Flow How data moves through the system. ## Security Considerations - Authentication - Authorization (RLS) - Data protection ## Performance Considerations - Caching strategy - Database optimization - API response times ## Monitoring and Observability - Key metrics - Alerting thresholds - Log locations ## Future Considerations What might change or be improved. ## References - Related ADRs - External documentation
markdown# KT: [Topic Name] - {{TICKET_PREFIX}}-XXX ## Summary What was done and why it matters. ## Context Background information needed to understand this work. ## Key Decisions Made 1. [Decision 1]: [Reasoning] 2. [Decision 2]: [Reasoning] ## Implementation Details ### What Changed - File: `path/to/file.ts` - Change description ### How It Works Explanation of the implementation. ## Gotchas and Lessons Learned Things that might trip up future developers. ## Testing How to verify everything works. ## Related Tickets - {{TICKET_PREFIX}}-XXX: [Related work] ## Future Work What should be done next.
| Doc Type | Location | Naming | | -------------- | ------------------------------------ | -------------------------------------- | | ADRs | docs/adr/ | ADR-XXX-{description}.md | | Runbooks | docs/runbooks/ | {operation}-runbook.md | | Architecture | docs/architecture/ | {system}-architecture.md | | KT Docs | docs/ | KT-{{TICKET_PREFIX}}-XXX-{topic}.md | | Technical Docs | docs/agent-outputs/technical-docs/ | {{TICKET_PREFIX}}-XXX-{description}.md |
Before publishing any documentation:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-06 | pass→pass | 8,780 | 5,536 | -37% | 1 | 1 | 0% | 1,411 | 2,153 | +53% | 0 | 0 | — |
case-11 | fail→pass | 8,570 | 2,042 | -76% | 1 | 1 | 0% | 1,335 | 1,661 | +24% | 0 | 0 | — |
case-17 | pass→pass | 5,458 | 2,197 | -60% | 1 | 1 | 0% | 744 | 1,674 | +125% | 0 | 0 | — |
case-04 | pass→pass | 13,530 | 11,152 | -18% | 1 | 1 | 0% | 2,506 | 3,419 | +36% | 0 | 0 | — |
case-05 | pass→pass | 5,796 | 5,735 | -1% | 1 | 1 | 0% | 945 | 2,311 | +145% | 0 | 0 | — |
case-01 | fail→pass | 18,393 | 10,956 | -40% | 1 | 1 | 0% | 2,882 | 3,087 | +7% | 0 | 0 | — |
case-02 | fail→pass | 20,826 | 16,616 | -20% | 1 | 1 | 0% | 3,532 | 4,318 | +22% | 0 | 0 | — |
case-03 | fail→pass | 17,647 | 12,221 | -31% | 1 | 1 | 0% | 2,698 | 3,306 | +23% | 0 | 0 | — |
case-07 | fail→pass | 6,971 | 2,422 | -65% | 1 | 1 | 0% | 1,189 | 1,739 | +46% | 0 | 0 | — |
case-08 | fail→pass | 21,931 | 2,328 | -89% | 1 | 1 | 0% | 976 | 1,714 | +76% | 0 | 0 | — |
case-09 | pass→pass | 11,264 | 1,774 | -84% | 1 | 1 | 0% | 1,848 | 1,664 | -10% | 0 | 0 | — |
case-10 | fail→pass | 8,363 | 2,244 | -73% | 1 | 1 | 0% | 1,397 | 1,780 | +27% | 0 | 0 | — |
case-12 | fail→pass | 3,870 | 1,801 | -53% | 1 | 1 | 0% | 514 | 1,560 | +204% | 0 | 0 | — |
case-13 | fail→pass | 12,816 | 1,771 | -86% | 1 | 1 | 0% | 697 | 1,582 | +127% | 0 | 0 | — |
case-14 | fail→pass | 2,593 | 2,063 | -20% | 1 | 1 | 0% | 318 | 1,639 | +415% | 0 | 0 | — |
case-15 | fail→pass | 24,675 | 17,253 | -30% | 1 | 1 | 0% | 4,065 | 4,176 | +3% | 0 | 0 | — |
case-16 | pass→pass | 10,314 | 1,635 | -84% | 1 | 1 | 0% | 1,627 | 1,580 | -3% | 0 | 0 | — |
case-18 | pass→pass | 18,470 | 12,148 | -34% | 1 | 1 | 0% | 2,836 | 3,283 | +16% | 0 | 0 | — |
case-19 | fail→pass | 17,722 | 12,420 | -30% | 1 | 1 | 0% | 2,713 | 3,338 | +23% | 0 | 0 | — |
case-20 | fail→pass | 6,017 | 2,451 | -59% | 1 | 1 | 0% | 843 | 1,744 | +107% | 0 | 0 | — |
case-21 | pass→pass | 18,426 | 13,233 | -28% | 1 | 1 | 0% | 2,491 | 3,253 | +31% | 0 | 0 | — |
case-22 | fail→pass | 13,458 | 4,336 | -68% | 1 | 1 | 0% | 2,079 | 1,956 | -6% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 21 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +64 percentage points is the difference between those two pass rates over the 21 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.