CtrlK
BlogDocsLog inGet started
Tessl Logo

adr

Generate Architecture Decision Records that capture the reasoning behind technical decisions. Use when the user asks to "create an ADR", "document a decision", "record why we chose X", or discusses architectural trade-offs worth preserving.

76

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-constructed, lean instruction skill: a copy-paste-ready ADR template, concrete numbered guidance, and clean sectioning with no padding. The main improvement would be adding a short worked example of a completed ADR.

DimensionReasoningScore

Conciseness

Lean and efficient with no explanation of concepts Claude already knows; the template's scaffolding questions are canonical ADR structure that earns their place, and every section is purposeful.

3 / 3

Actionability

Provides a copy-paste-ready markdown template plus concrete instructions (specific paths like docs/adr/, adr/ at root, and sentence budgets like 'Context: 2-4 sentences'), which is concrete actionable guidance for an instruction-only skill.

3 / 3

Workflow Clarity

A clear five-step numbered sequence (extract context, find location, number, write concisely, capture the why) for a simple non-destructive generative task where the action is unambiguous; the simple-skills exception applies so no validation checkpoint is required.

3 / 3

Progressive Disclosure

Self-contained single-file skill with well-organized sections (ADR Format, Instructions, See Also) and clearly signaled one-level cross-references; no deep reference nesting and no content that needs splitting out.

3 / 3

Total

12

/

12

Passed

Description

90%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description with explicit 'Use when...' triggers and natural user phrasings. Its only weakness is specificity: it describes essentially one action rather than enumerating several concrete capabilities.

Suggestions

Enumerate a couple more concrete actions to lift specificity, e.g. 'Generate Architecture Decision Records from conversation context, number and place them in the project's ADR directory, and capture trade-offs and rejected alternatives.'

DimensionReasoningScore

Specificity

Names the ADR domain and one concrete action ('Generate Architecture Decision Records that capture the reasoning behind technical decisions') but does not list multiple distinct concrete actions like the 3-anchor (extract/fill/merge); above 1 because a concrete action and domain are stated.

2 / 3

Completeness

Clearly answers both what ('Generate Architecture Decision Records that capture the reasoning...') and when with an explicit 'Use when the user asks to...' clause.

3 / 3

Trigger Term Quality

Quoted natural phrases users would say — 'create an ADR', 'document a decision', 'record why we chose X', plus 'architectural trade-offs' — give good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

Clear ADR niche with distinct triggers; unlikely to fire for unrelated skills, though 'document a decision' is mildly generic it is anchored by the ADR framing.

3 / 3

Total

11

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
tslateman/duet
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.