CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

typer

Typer best practices and conventions. Use when working with Typer CLIs. Keeps Typer code clean and up to date with the latest features and patterns, updated with new versions. Write new code or refactor and update old code.

Quality

78%

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 ./typer/.agents/skills/typer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 highly actionable, with complete executable examples, explicit anti-patterns, and current version guidance (vendored Click, deprecated packages) placed in appropriate 'deprecated' sections. Its weaknesses are token cost from repeated boilerplate across examples and a monolithic single-file structure where the Rich and advanced option content could be split into referenced files.

Suggestions

Strip repeated boilerplate (imports, 'app = typer.Typer()', 'if __name__ == "__main__": app()') from all but the first example, and drop comments that restate what the code already shows, to reduce token cost.

Move the Rich / Rich-markdown and Click-deprecation sections into a one-level-deep reference file (e.g., references/rich.md) linked from a short overview section, keeping SKILL.md as a lean index.

Add brief decision guidance for when to use rich_markup_mode='rich' vs 'markdown' vs None so the reader can pick a pattern without guessing.

DimensionReasoningScore

Conciseness

The guidance is Typer-specific and avoids explaining general concepts, but every one of ~8 code examples repeats full boilerplate ('import typer', 'app = typer.Typer()', 'if __name__ == "__main__": app()') and redundant comments like '# Note that name is an optional Argument, as a default is provided' that restate the code. This matches 'mostly efficient but includes some unnecessary explanation or could be tightened' — not a 4 because the trimming opportunities are repeated throughout, not minor.

3 / 5

Actionability

Every section provides complete, copy-paste-ready executable code with the exact CLI invocations ('python main.py --name "Morty"') and explicit anti-patterns marked 'DO NOT DO THIS: old style'. Coverage spans the common cases (app creation, Annotated arguments/options, multi-value options, Rich markup), matching the 'fully executable, copy-paste ready, covers common cases' anchor.

5 / 5

Workflow Clarity

This is a conventions skill, not a sequential workflow, and each topic gives an unambiguous do/don't pair (Annotated vs old default style, Typer() vs typer.run, vendored-Click options to avoid). No destructive or batch operations exist, so no validation cap applies. Not a 5 because there is no decision flow for choosing between patterns (e.g., when rich_markup_mode 'rich' vs 'markdown' is appropriate) and the note is inferred rather than stated.

4 / 5

Progressive Disclosure

No bundle files exist and the ~290-line body is well-sectioned with headers, but everything — including the substantial Rich/Rich-markdown and Click-deprecation sections — is inlined in SKILL.md. This matches 'some structure but could be better organized; content that should be separate is inline' rather than 4, since 290 lines exceeds the 'under 50 lines with no need for external references' case and topics like Rich formatting would naturally live in a one-level-deep reference file.

3 / 5

Total

15

/

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 solid, third-person description with a clear niche and an explicit 'Use when' trigger clause. Its main weaknesses are mild generic padding ('best practices', 'clean code') and a trigger clause that could name more natural variations like 'command-line app' or 'Python CLI'.

DimensionReasoningScore

Specificity

The description names the domain ('Typer CLIs') and a couple of actions ('Write new code or refactor and update old code'), but phrases like 'Keeps Typer code clean and up to date' and 'best practices and conventions' are generic padding rather than concrete capabilities. It sits at the 'names domain and 1-2 concrete actions, but not comprehensive' anchor — not a 4 because the action list is thin and partly abstract, not a 2 because real actions are stated.

3 / 5

Completeness

Both parts are present: what ('Write new code or refactor and update old code', 'Keeps Typer code clean and up to date') and when ('Use when working with Typer CLIs'). The 'when' clause could be more explicit with concrete trigger phrases (e.g., 'when the user mentions Typer or asks to build a command-line app'), which keeps it at anchor 4 rather than 5.

4 / 5

Trigger Term Quality

'Typer' and 'Typer CLIs' are exactly the natural terms a user would say when needing this skill, plus 'refactor' signals the maintenance use case. Not a 5 because common variations like 'command-line app', 'CLI tool', or 'Python CLI' are missing; not a 3 because the core natural keyword is present and repeated, going beyond 'some relevant keywords'.

4 / 5

Distinctiveness Conflict Risk

'Typer' is a specific named library with distinct triggers ('Use when working with Typer CLIs'), giving it a clear niche with minimal conflict risk against general Python or other library skills. Re-reading the anchor 4 example ('Works with PDF and Word document files'), this description is more precisely scoped, so 5 is the best fit.

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

drew-tessl/typer-not-a-fork

Path

typer/.agents/skills/typer/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.