CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

decisions

Use when creating, editing, superseding, or reviewing Architecture Decision Records (ADRs) or Product Decision Records (PDRs) under `docs/decisions/` (including `docs/decisions/architecture/` and `docs/decisions/product/`); writing MADR-formatted decision documents; recording rationale for an architectural or upstream-driven choice; linking a decision to a TRaSH Guides upstream source; changing a decision's status (proposed, accepted, deprecated, superseded). Triggers on phrases like "write an ADR", "new PDR", "document this decision", "decision record", "add an architecture decision", or any edit to files matching `docs/decisions/**/*.md`. Do NOT use for general architecture documentation under `docs/architecture/`.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

78%Weight 40%Scale 1-5

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

A well-crafted instruction-only skill body: concrete project-specific rules, an explicit mandatory-template gate, clear status semantics, and thoughtful guidance on private upstream links and attribution. The main improvement opportunities are tightening the justificatory passages in Attribution/Perspective and spelling out how the sequential number is determined.

DimensionReasoningScore

Conciseness

The body is lean, assumes Claude knows what ADRs are, and provides only project-specific rules and context (e.g., the git date-verification command, the TRaSH Guides/Recyclarr relationship). Minor over-explanation remains: the 'Reasons:' bullet list under Attribution and parts of the Perspective section justify rules rather than state them. Not 5 because those passages could be trimmed; not 3 because padding is minor and most content is knowledge Claude lacks.

4 / 5

Actionability

Concrete, executable guidance throughout: template paths, the 'NNN-kebab-case-title.md' naming pattern, a copy-paste git command ('git log --format="%ai" <commit> -1'), a complete reference-style-link example, and enumerated status values. Minor gaps: how to determine the next sequential NNN is left implicit, and no sample decision document is shown inline (mitigated by the mandatory template reads).

4 / 5

Workflow Clarity

The sequence is clear and well-ordered — MANDATORY template read first, then rules (naming, dates, links), status selection, and ADR-vs-PDR scoping — with a real checkpoint ('ask the user for one before finalizing the PDR'). Not 5 because the workflow is organized as rule sections rather than an explicit ordered procedure, so checkpoints are implicit rather than listed; not 3 because the mandatory template gate and upstream-link gate function as validation for this document-writing task.

4 / 5

Progressive Disclosure

No bundle files exist, and the ~90-line body is appropriately self-contained: well-organized sections with clear headers, and the only external materials (the ADR/PDR templates) are clearly signaled one-level-deep references marked MANDATORY. Content that would warrant splitting (the templates) already lives outside the body, so navigation is easy.

5 / 5

Total

17

/

20

Passed

Description

100%Weight 40%Scale 1-5

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

An exemplary description: concrete capabilities, natural trigger phrases with synonyms and file globs, an explicit use-when clause, and a negative boundary to prevent mis-triggering. Third-person voice is used throughout with no fluff or over-claims.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete actions — 'creating, editing, superseding, or reviewing' ADRs/PDRs, 'writing MADR-formatted decision documents', 'recording rationale', 'linking a decision to a TRaSH Guides upstream source', 'changing a decision's status' — with comprehensive coverage of the skill's scope. Not 4 because coverage is complete rather than having minor gaps.

5 / 5

Completeness

Both 'what' (the enumerated create/edit/supersede/review actions) and 'when' (an explicit 'Use when' clause plus a 'Triggers on phrases like' list) are clearly stated with concrete trigger phrases. Matches the top anchor exactly.

5 / 5

Trigger Term Quality

Provides comprehensive natural trigger phrases ('write an ADR', 'new PDR', 'document this decision', 'decision record', 'add an architecture decision') plus synonyms (ADR/PDR expansions) and file-path patterns ('docs/decisions/**/*.md'). A user needing this skill would naturally say one of these.

5 / 5

Distinctiveness Conflict Risk

Clear niche (decision records under docs/decisions/) with distinct triggers, and an explicit exclusion — 'Do NOT use for general architecture documentation under docs/architecture/' — that minimizes conflict risk with adjacent documentation skills.

5 / 5

Total

20

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

recyclarr/recyclarr

Path

.opencode/skills/decisions/SKILL.md

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.