CtrlK
BlogDocsLog inGet started
Tessl Logo

031-architecture-adr-functional-requirements

Facilitates conversational discovery to create Architectural Decision Records (ADRs) for functional requirements covering CLI, REST/HTTP APIs, or both. Use when the user wants to document command-line or HTTP service architecture, capture functional requirements, create ADRs for CLI or API projects, or design interfaces with documented decisions. This should trigger for requests such as Create ADR for functional requirements; Document functional requirements; Capture functional requirements; Generate functional requirements in an ADR; Decide CLI versus REST functional requirements for an ADR. Part of Plinth Toolkit

69

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

70%

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

A well-structured interactive skill with clear sequencing, validation checkpoints, and clean single-level progressive disclosure. It loses points on conciseness for duplicated trigger/constraint text and on actionability because the concrete discovery questions and ADR format live only in the reference.

Suggestions

Remove the "When to use this skill" list from the body since it duplicates the frontmatter description's trigger phrases, or replace it with a one-line pointer.

De-duplicate the Workflow step constraints that repeat the Constraints section (e.g., the discovery-batch and summary-validation rules) by referencing them once.

Add a brief inline example of the ADR document structure or one or two sample discovery questions so the body is actionable without forcing a jump to the reference.

DimensionReasoningScore

Conciseness

The body is free of padded concept explanations, but the "When to use this skill" list duplicates the trigger phrases already present in the frontmatter description, and the Workflow's step constraints restate items from the Constraints section ("Never ask all discovery questions at once", "Validate summary with user"), so it could be tightened.

2 / 3

Actionability

Concrete procedural guidance exists (run the local shell `date` command, load `references/031-architecture-adr-functional-requirements.md`, pose one or two questions at a time), but the specifics that make it copy-paste ready — the actual discovery questions and the ADR output format — are deferred to the reference rather than shown.

2 / 3

Workflow Clarity

A clear numbered sequence (0–3) with explicit validation checkpoints ("Validate summary with user", "Wait for user to confirm proceed before generating the ADR") and a feedback loop via user confirmation before the ADR is generated.

3 / 3

Progressive Disclosure

SKILL.md is a concise overview with well-organized sections and a single clearly signaled, one-level-deep reference link to references/031-architecture-adr-functional-requirements.md, which exists in the bundle.

3 / 3

Total

10

/

12

Passed

Description

100%

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, well-formed description that states concrete capabilities in third person, provides explicit trigger guidance, and clearly separates the niche from other skills. No notable weaknesses.

DimensionReasoningScore

Specificity

Uses third-person voice ("Facilitates conversational discovery to create Architectural Decision Records (ADRs)") and lists multiple concrete actions: facilitating discovery, creating ADRs, documenting architecture, capturing requirements, and designing interfaces across CLI and REST/HTTP surfaces.

3 / 3

Completeness

Explicitly answers both what ("Facilitates conversational discovery to create ADRs for functional requirements...") and when ("Use when the user wants to... This should trigger for requests such as..."), with an explicit Use-when clause and enumerated triggers.

3 / 3

Trigger Term Quality

Includes natural user phrasings ("document command-line or HTTP service architecture", "capture functional requirements", "create ADRs for CLI or API projects") plus an explicit trigger list ("Create ADR for functional requirements; Document functional requirements; Capture functional requirements"), giving broad coverage of terms a user would actually say.

3 / 3

Distinctiveness Conflict Risk

The ADR-for-functional-requirements niche scoped to CLI and/or REST APIs is clearly distinct, and "Part of Plinth Toolkit" plus specific trigger phrases make it unlikely to fire for unrelated skills.

3 / 3

Total

12

/

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
jabrena/plinth
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.