CtrlK
BlogDocsLog inGet started
Tessl Logo

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linking a decision to a TRaSH Guides upstream source; changing a decision's status (proposed, accepted, deprecated, superseded).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/`.

72

Quality

89%

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 tight, well-structured procedural skill that assumes Claude's knowledge and gives concrete commands and examples. It is held back by directive-prose rules instead of copy-paste templates, the absence of an explicit pre-finalize validation loop, and references to template paths that are not present in the skill bundle.

Suggestions

Add a brief pre-finalize validation checklist (e.g., verify NNN numbering, status field present, upstream link present for PDRs) to turn the implicit sequence into an explicit feedback loop.

Include a minimal inline ADR/PDR frontmatter skeleton or a one-line pointer to the template's exact section so the most common action is copy-paste ready without opening the template.

Ship the referenced TEMPLATE.md files in the skill bundle (e.g. under references/) or clearly state they live in the repo, so the one-level-deep references resolve.

DimensionReasoningScore

Conciseness

Lean and efficient throughout; assumes Claude's competence, avoids explaining what ADRs/PDRs or git are, and every line delivers procedural guidance that earns its place.

5 / 5

Actionability

Provides concrete executable guidance — the `git log --format="%ai" <commit> -1` command and the reference-style-link markdown snippet — but most rules are directive prose rather than copy-paste-ready templates, leaving minor gaps.

4 / 5

Workflow Clarity

Sections give a clear sequence (read template → write one decision → set status → link upstream) with a concrete date-verification checkpoint via git, but there is no explicit validate-and-retry feedback loop around status/naming before finalizing.

4 / 5

Progressive Disclosure

Sections are clearly signaled and templates are referenced by concrete one-level-deep paths, but no bundle files exist to confirm the referenced TEMPLATE.md paths and the inline reference-style-link example is the only navigable detail; content that could live in the templates is referenced rather than shown.

3 / 5

Total

16

/

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.

A highly specific, well-triggered description that clearly delineates the skill's niche with both positive triggers and a negative-boundary clause. It comprehensively answers what the skill does and when to invoke it.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'creating, editing, superseding, or reviewing', '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 operations.

5 / 5

Completeness

Explicitly answers both 'what' (the enumerated create/edit/supersede/review actions) and 'when' (a 'Use when...' clause plus concrete trigger phrases and a file-path trigger), matching the score-5 anchor.

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage including synonyms and path patterns: 'ADR', 'PDR', 'write an ADR', 'new PDR', 'document this decision', 'decision record', 'add an architecture decision', plus the `docs/decisions/**/*.md` glob trigger.

5 / 5

Distinctiveness Conflict Risk

Clear niche scoped to `docs/decisions/` ADR/PDR records with a negative boundary ('Do NOT use for general architecture documentation under docs/architecture/'), giving minimal conflict risk.

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
recyclarr/recyclarr
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.