CtrlK
BlogDocsLog inGet started
Tessl Logo

design-orchestration

Orchestrates design workflows by routing work through brainstorming, multi-agent review, and execution readiness in the correct order.

52

Quality

59%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/design-orchestration/SKILL.md

The canonical home for this skill is design-orchestration in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

60%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.

The body is a well-structured, clearly sequenced routing workflow with explicit gates and a readiness-check feedback loop. It loses points for redundancy across the Purpose/Operating/Enforcement sections, risk assessment without concrete thresholds, and a circular "When to Use" section.

Suggestions

Collapse the overlapping Purpose, Operating Model, and Enforcement Rules sections into one statement of role and one consolidated rules list to remove redundancy.

Give the Step 2 risk assessment concrete thresholds or a scoring rubric so Low/Moderate/High classification is reproducible rather than subjective.

Replace the circular "When to Use" with concrete entry triggers (e.g. "user proposes a new feature or change", "design decision carries meaningful risk") instead of self-reference.

DimensionReasoningScore

Conciseness

Mostly efficient with clear sections, but Purpose/Operating Model/Enforcement Rules overlap ("controls the flow between other skills" vs "routing and enforcement skill") and the Design Philosophy section ("Good systems fail early. Bad systems fail in production.") is motivational padding.

3 / 5

Actionability

Routing steps name concrete skills and required artifacts (Understanding Lock, Decision Log) with hard gates, but risk assessment offers only factors with no thresholds, and the closing "When to Use" ("applicable to execute the workflow... described in the overview") is circular and unactionable.

3 / 5

Workflow Clarity

The five routing steps are clearly sequenced with explicit gating and a Step 5 Execution Readiness Check that blocks and returns on failure (a feedback loop); just short of 5 because risk classification lacks an explicit validation checkpoint.

4 / 5

Progressive Disclosure

Well-organized into clearly headed sections appropriate for a single-file routing skill with no bundle files to navigate; the misplaced, weak "When to Use" section at the end is a minor organization gap.

4 / 5

Total

14

/

20

Passed

Description

58%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.

The description is specific and distinct but incomplete: it states what the skill does without an explicit "Use when..." trigger clause, capping completeness. Trigger terms are partly jargon-heavy rather than natural user phrasing.

Suggestions

Add an explicit "Use when..." clause, e.g. "Use when a user proposes a feature or change where design risk matters more than speed."

Replace jargon ("orchestrates", "execution readiness") with natural user phrasing like "coordinate", "review", and "approve designs".

Include synonyms/file-context triggers ("design review", "brainstorm a design", "validate before implementation") to broaden natural keyword coverage.

DimensionReasoningScore

Specificity

"routing work through brainstorming, multi-agent review, and execution readiness" names several concrete actions in the design domain; not a 5 because coverage is limited to orchestration rather than a comprehensive action set.

4 / 5

Completeness

The description gives a clear "what" but no "Use when..." trigger clause, which the guidelines explicitly cap at 3; the "when" is only weakly implied.

3 / 5

Trigger Term Quality

"brainstorming" and "design" are natural terms, but "orchestrates", "multi-agent review", and "execution readiness" lean technical and omit common synonyms a user would actually say.

3 / 5

Distinctiveness Conflict Risk

It carves a distinct meta-skill niche (design-workflow routing) with minimal overlap, though it shares trigger space with the brainstorming skills it coordinates.

4 / 5

Total

14

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.