CtrlK
BlogDocsLog inGet started
Tessl Logo

prompt-architect

Designs clear, testable prompts for agent workflows. Use when creating new prompts, refining weak prompts, or establishing reusable prompting patterns.

68

Quality

83%

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

77%

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

A concise, well-sequenced instruction skill with a clear build process and self-check list. It loses points for actionability (no concrete examples or templates inline) and for a broken progressive-disclosure reference to a missing reference.md file.

Suggestions

Add one concrete inline example (e.g., a sample before/after prompt or a filled-in template) under the Build Sequence to lift actionability from abstract steps to copy-paste-ready guidance.

Create the referenced reference.md (or remove the link) — the body promises templates, anti-patterns, and refinement loops at [reference.md](reference.md) but no such file exists in the bundle.

Optionally fold a compact template snippet directly into the body so the skill is self-contained even if the external reference is unavailable.

DimensionReasoningScore

Conciseness

The body is lean (~25 lines) with no padding or explanation of concepts Claude already knows; every section (Purpose, Build Sequence, Quality Checks, Reference) earns its place, matching the 'lean and efficient' anchor.

3 / 3

Actionability

The Build Sequence gives concrete ordered steps ("Define objective, audience, and success criteria", "Capture hard constraints (format, tools, safety, style)"), but guidance stays abstract with no inline example, template, or sample prompt to make it copy-paste ready; not score 3 because concrete examples are absent, not score 1 because the steps are specific and directive rather than vague.

2 / 3

Workflow Clarity

The Build Sequence is a clearly numbered 5-step process with an explicit feedback loop (step 5: "Iterate using concrete examples and observed errors") and a validation checklist (Prompt Quality Checks), matching the anchor requiring a clear sequence plus checkpoints; not capped at 2 because this is a design process, not a destructive/batch operation.

3 / 3

Progressive Disclosure

Sections are well-organized and the body points one level deep to [reference.md](reference.md) for templates, anti-patterns, and refinement loops, but that referenced file does not exist in the bundle (no references/ directory or reference.md present), so the disclosed content is unreachable; not score 1 because the body itself is well structured rather than monolithic or nested, not score 3 because the single external reference is broken.

2 / 3

Total

10

/

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 an explicit 'Use when' trigger and natural keywords. Its only weakness is specificity: it leads with one general action verb instead of enumerating several concrete capabilities.

DimensionReasoningScore

Specificity

"Designs clear, testable prompts for agent workflows" names the domain and a core action, but stops at a single verb rather than listing multiple concrete actions (e.g., design, test, refactor, templatize), so it sits at the 'some actions, not comprehensive' anchor rather than the multi-action anchor above.

2 / 3

Completeness

It states both what ("Designs clear, testable prompts for agent workflows") and an explicit when ("Use when creating new prompts, refining weak prompts, or establishing reusable prompting patterns"), matching the anchor that requires both with an explicit trigger clause.

3 / 3

Trigger Term Quality

"creating new prompts, refining weak prompts, or establishing reusable prompting patterns" are natural phrases a user would say when needing this skill, giving good coverage of common variations; not score 2 because the terms are user-natural rather than technical jargon.

3 / 3

Distinctiveness Conflict Risk

The prompt-design-for-agent-workflows niche is specific with distinct triggers, making overlap with other skills unlikely; not score 2 because the scope is narrow rather than broadly overlapping.

3 / 3

Total

11

/

12

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

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
repowise-dev/claude-code-prompts
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.