Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Create an Architectural Decision Record (ADR) document for AI-optimized decision documentation.
.claude/skills/create-architectural-decision-record/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | — | — |
| case-16 | ✗→✓ | ▲ Improved | — | — |
| case-10 | ✗→✓ | ▲ Improved | — | — |
| case-11 | ✗→✓ | ▲ Improved | — | — |
| case-22 | ✗→✓ | ▲ Improved | — | — |
Create an ADR document for ${input:DecisionTitle} using structured formatting optimized for AI consumption and human readability.
${input:Context}${input:Decision}${input:Alternatives}${input:Stakeholders}If any of the required inputs are not provided or cannot be determined from the conversation history, ask the user to provide the missing information before proceeding with ADR generation.
The ADR must be saved in the /docs/adr/ directory using the naming convention: adr-NNNN-[title-slug].md, where NNNN is the next sequential 4-digit number (e.g., adr-0001-database-selection.md).
The documentation file must follow the template below, ensuring that all sections are filled out appropriately. The front matter for the markdown should be structured correctly as per the example following:
md--- title: "ADR-NNNN: [Decision Title]" status: "Proposed" date: "YYYY-MM-DD" authors: "[Stakeholder Names/Roles]" tags: ["architecture", "decision"] supersedes: "" superseded_by: "" --- # ADR-NNNN: [Decision Title] ## Status **Proposed** | Accepted | Rejected | Superseded | Deprecated ## Context [Problem statement, technical constraints, business requirements, and environmental factors requiring this decision.] ## Decision [Chosen solution with clear rationale for selection.] ## Consequences ### Positive - **POS-001**: [Beneficial outcomes and advantages] - **POS-002**: [Performance, maintainability, scalability improvements] - **POS-003**: [Alignment with architectural principles] ### Negative - **NEG-001**: [Trade-offs, limitations, drawbacks] - **NEG-002**: [Technical debt or complexity introduced] - **NEG-003**: [Risks and future challenges] ## Alternatives Considered ### [Alternative 1 Name] - **ALT-001**: **Description**: [Brief technical description] - **ALT-002**: **Rejection Reason**: [Why this option was not selected] ### [Alternative 2 Name] - **ALT-003**: **Description**: [Brief technical description] - **ALT-004**: **Rejection Reason**: [Why this option was not selected] ## Implementation Notes - **IMP-001**: [Key implementation considerations] - **IMP-002**: [Migration or rollout strategy if applicable] - **IMP-003**: [Monitoring and success criteria] ## References - **REF-001**: [Related ADRs] - **REF-002**: [External documentation] - **REF-003**: [Standards or frameworks referenced]
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
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. The headline lift of +73 percentage points is the difference between those two pass rates over the 22 comparable cases. 3 cases got worse with the skill loaded, and they are included in that figure.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.