CtrlK
BlogDocsLog inGet started
Tessl Logo

archify

Create polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable standalone HTML with inline SVG, dark/light themes, optional trace motion, and PNG/JPEG/WebP/SVG/WebM export. Accept plain-language requirements or pasted Mermaid flowchart, sequenceDiagram, and stateDiagram input; inspect repository evidence when the diagram must reflect real code. Use when the user asks to visualize system architecture, infrastructure, cloud/security/network topology, technical workflows, API call sequences, request lifecycles, data pipelines, ETL/ELT, data lineage, state machines, or to convert/beautify Mermaid.

75

Quality

94%

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

88%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 tightly structured, highly actionable authoring-and-delivery workflow with explicit validation checkpoints and feedback loops, plus well-gated one-level-deep references. It is slightly verbose in the authoring-invariants prose and cannot be verified against the absent bundle files.

Suggestions

Tighten the 'Authoring invariants' bullet list—convert some of the longest prose specifications into shorter rules or move deep geometry details (e.g. Port Spread axis/offset rules) into references/authoring-contract.md to lift conciseness.

Ensure every referenced path (references/authoring-contract.md, references/viewer-runtime.md, references/delivery-contract.md, renderers/workflow/README.md) resolves to a real bundle file so the progressive-disclosure structure is fully verifiable.

Consider moving the detailed per-type field enums and routing-control rules into a single reference table so the main body stays a lean overview that points to specifics.

DimensionReasoningScore

Conciseness

Largely efficient and information-dense—concrete commands and exact thresholds rather than concept explanation—but the 'Authoring invariants' section is long and a few prose specifications could be tightened, landing just below the leanest anchor.

4 / 5

Actionability

Fully executable, copy-paste-ready guidance: exact commands with flags ('node bin/archify.mjs validate <type> <candidate.json> --quality showcase --json'), specific field names, exact viewport sizes, and exit-code semantics covering the common authoring and delivery cases.

5 / 5

Workflow Clarity

The Fast authoring path is a clear 1–5 sequence with explicit validation checkpoints ('Validate after every candidate edit and immediately before handoff'), showcase acceptance criteria, a fix–rerun feedback loop, and a stop condition ('If two consecutive rounds do not improve that best count, stop and report').

5 / 5

Progressive Disclosure

Clear overview with well-signaled, one-level-deep, conditionally gated references (e.g. 'Read references/viewer-runtime.md only when the user explicitly asks...'), but the referenced bundle files (references/, renderers/) are not present to verify they exist and are well-organized, holding this just below the top anchor.

4 / 5

Total

18

/

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.

The description is exemplary: it states concrete capabilities, enumerates comprehensive natural trigger terms, answers both what and when explicitly, and carves out a distinct niche. Third-person voice is maintained throughout with no over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions—'Create polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable standalone HTML with inline SVG', 'dark/light themes, optional trace motion, and PNG/JPEG/WebP/SVG/WebM export', and 'inspect repository evidence'—with comprehensive coverage.

5 / 5

Completeness

Explicitly answers both 'what' (create validated diagrams as standalone HTML with export) and 'when' via the concrete 'Use when the user asks to visualize...' trigger clause.

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage including synonyms and file-format keywords: 'visualize system architecture, infrastructure, cloud/security/network topology, technical workflows, API call sequences, request lifecycles, data pipelines, ETL/ELT, data lineage, state machines, or to convert/beautify Mermaid'.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche—interactive HTML architecture/workflow/sequence diagram generation with Mermaid conversion—anchored by distinct trigger phrases, giving minimal conflict risk with other skills.

5 / 5

Total

20

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing, 1 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 8 missing

Warning

Total

14

/

16

Passed

Repository
anbeime/skill
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.