CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

uml-maintenance

Canonical specification for the project's UML.md file. Every project pi works on keeps a single UML.md at the repo root that captures the current architecture as Mermaid diagrams plus a Last Activity log. Load this skill when creating or updating UML.md.

Quality

79%

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 ./skills/uml-maintenance/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

An instruction-focused skill with concrete, near copy-paste-ready templates for both artifacts and crisp, imperative update rules. Its main gaps are the lack of any verification checkpoint after writing the two files and a slightly malformed nested code fence in the UML.md structure template.

DimensionReasoningScore

Conciseness

The body is lean — it never explains what UML, Mermaid, or HTML are, and templates carry the weight — but the ~8 lines of hand-specified CSS and rules restating template comments ("Copy the raw Mermaid source (no backtick fences)") could be trimmed.

4 / 5

Actionability

Guidance is nearly fully executable: an exact section template, a complete copy-paste UML.html with a CDN Mermaid import, and a concrete creation procedure ("surveying the repo (entry points, top-level directories, exported types)"). The malformed nested code fence in the markdown structure example ("` ``") is a minor gap that keeps it below a 5.

4 / 5

Workflow Clarity

The update rules form a clear numbered sequence with a pre-flight checkpoint ("Read before write... so you preserve hand-edited notes"), but there is no post-write verification loop (e.g. confirming UML.html stayed in sync or the Mermaid renders) — a minor validation gap, not the absent-validation case that would cap at 3.

4 / 5

Progressive Disclosure

Well-organized with clear section headers, no nested references, and at ~150 lines the inline content is mostly appropriate; the ~60-line HTML template is a plausible candidate for an assets/ file, leaving a minor organization gap rather than the clean split of a 5.

4 / 5

Total

16

/

20

Passed

Description

73%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 strong third-person description that clearly defines a niche artifact and includes an explicit load trigger. Its main limitation is narrow trigger coverage — everything keys on "UML.md" itself, with few synonym phrasings and little enumeration of the concrete actions the skill performs.

Suggestions

Broaden the 'when' clause with natural phrasings a user would actually say, e.g. "Use when creating or updating UML.md, when asked to document or diagram the project architecture, or when the user mentions Mermaid or class diagrams."

Name the concrete actions the skill performs (create UML.md from a repo survey, update diagrams when relationships change, append activity-log entries, regenerate UML.html) to lift specificity from one generic action to several specific ones.

DimensionReasoningScore

Specificity

The domain is named concretely ("a single UML.md at the repo root that captures the current architecture as Mermaid diagrams plus a Last Activity log") but the actions stop at "creating or updating UML.md" — one to two concrete actions rather than the several specific actions of a 4.

3 / 5

Completeness

The "what" is clear ("Canonical specification for the project's UML.md file..." with its content spelled out) and the "when" is explicit ("Load this skill when creating or updating UML.md"), so the missing-'Use when' cap does not apply; the trigger clause covers only one phrasing rather than the multiple concrete trigger phrases of a 5.

4 / 5

Trigger Term Quality

"UML.md", "Mermaid diagrams", "architecture", and "Last Activity log" are natural phrasings a user would say, but common variations such as "UML diagrams", "class diagram", or "architecture doc" are missing — good coverage with a few natural terms absent, matching the 4 anchor over the single-keyword 3 anchor.

4 / 5

Distinctiveness Conflict Risk

It targets a uniquely named artifact — "a single UML.md at the repo root" with "Mermaid diagrams" and a "Last Activity log" — a clear niche with distinct triggers and minimal realistic conflict with any other skill.

5 / 5

Total

16

/

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

g23polar/pi-project-memory

Path

skills/uml-maintenance/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.