Tessl • The management layer for AI agent skills

SkillPublic

litestar-project-starter

Scaffold a production-ready Litestar 2.x application with class-based controllers, DTOs, guards, SQLAlchemy plugin, and auto-generated OpenAPI docs.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./backend-python/litestar-project-starter/SKILL.md

Quality

Content

57%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 code for every architectural layer, but it is a monolithic single-file skill: full source templates are inlined instead of progressively disclosed, the workflow lacks validation checkpoints, and there is duplicated content plus unpinned-version-sensitive material. Splitting templates into reference files and closing the alembic/env gaps would raise most dimensions.

Suggestions

Move the full per-file source templates ("Essential Patterns") into references/ files (e.g., references/templates.md or one file per layer) and keep SKILL.md as a concise overview with clearly signaled links.

Remove the duplicated internal_server_error_handler (keep it only in the main.py example) and place dependency version pins in a dedicated, clearly dated section to avoid time-sensitive drift.

Add validation checkpoints to the workflow: scaffold alembic config before instructing "alembic upgrade head", provide the .env.example contents, and add a "verify" step (e.g., run pytest / curl the health endpoint) after starting the server.

Dimension	Reasoning	Score
Conciseness	Prose is lean, but the exception handler is fully duplicated (standalone section plus again inside main.py), and multiple pinned version numbers ("litestar[standard]>=2.14", "advanced-alchemy>=0.28") sit outside any deprecated/old-patterns section, which the guidelines penalize. This fits anchor 3 (mostly efficient but could be tightened) rather than 4 (duplication plus version pins exceed minor over-explanation).	3 / 5
Actionability	Scaffold commands, a complete pyproject.toml, full per-file code for every layer, and numbered first steps are copy-paste ready, matching anchor 4. Not anchor 5 because of real gaps: "First Steps" says "alembic upgrade head" yet no alembic init/config is ever scaffolded, and ".env.example" appears in the tree but its contents are never provided.	4 / 5
Workflow Clarity	The scaffold-to-first-steps sequence is present and ordered, but validation checkpoints are absent — no step confirms the server is running, no test-run verification, and step 4 (alembic) will fail as written. This matches anchor 3 (sequence present, checkpoints missing or implicit), not 4.	3 / 5
Progressive Disclosure	No bundle files exist; roughly 260 lines of complete source files under "Essential Patterns" are inlined in a single 450-line SKILL.md — content that clearly belongs in references/ files. Section structure is good, fitting anchor 3 (content that should be separate is inline) rather than 2 (it is well-sectioned, not a wall of text).	3 / 5
	Total	13 / 20 Passed

Description

70%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, framework-scoped, and highly distinguishable, but it omits any explicit "when to use" trigger guidance, which caps completeness. Adding a "Use when..." clause with natural trigger phrases would lift it to the top band.

Suggestions

Append a trigger clause such as "Use when starting a new Litestar project, scaffolding a Litestar/ASGI backend, or when the user mentions Litestar, advanced-alchemy, or building a Python API service."

Add natural trigger synonyms users would actually say (e.g., "set up", "bootstrap", "Python backend API") to broaden keyword coverage beyond the framework name.

Optionally mention adjacent capabilities the body already covers (testing, migrations, CI) to close the minor specificity gaps.

Dimension	Reasoning	Score
Specificity	"Scaffold a production-ready Litestar 2.x application with class-based controllers, DTOs, guards, SQLAlchemy plugin, and auto-generated OpenAPI docs" names one concrete action plus five specific components, matching anchor 4 (several specific items, minor coverage gaps). It falls short of anchor 5 because there is only one verb (scaffold) rather than multiple distinct concrete actions.	4 / 5
Completeness	The "what" is clear and concrete (scaffold a Litestar app with the listed features), but there is no "Use when..." clause or equivalent explicit trigger guidance, which the judging guidelines cap at anchor 3. It is not anchor 2 because the "what" is specific rather than vague.	3 / 5
Trigger Term Quality	Terms like "Litestar", "scaffold", "controllers", "DTOs", "guards", "SQLAlchemy", and "OpenAPI" are natural phrases a user would say when needing this skill, fitting anchor 4. Not anchor 5 because common variations such as "set up a Litestar project", "bootstrap", or "backend API" are missing.	4 / 5
Distinctiveness Conflict Risk	Naming the specific niche framework "Litestar 2.x" alongside distinctive feature terms gives a clear niche with distinct triggers and minimal conflict risk, matching anchor 5 — only other Litestar-specific skills could overlap.	5 / 5
	Total	16 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: achreftlili/deep-dev-skills
Path: backend-python/litestar-project-starter/SKILL.md
Revision: 181fcbc

Reviewed: 7 days ago

Discovery Implementation Validation

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.

litestar-project-starter

Table of Contents

Is this your skill?