CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

python-tests

Write regression tests for FastMCP changes using its pytest fixtures, in-memory clients, and protocol boundaries.

Quality

80%

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 ./.agents/skills/python-tests/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 exceptionally dense, expert-level instruction skill: every token delivers non-obvious repository-specific rules, the regression-test workflow has genuine validation checkpoints, and external detail is correctly deferred to repo docs. Remaining gaps are minor — a concrete test-run command, an example snippet, and light grouping of the bullet conventions.

DimensionReasoningScore

Conciseness

Every line carries repo-specific knowledge Claude cannot infer ("asyncio_mode = \"auto\" is configured globally", "pythonpath in pyproject shadows PYTHONPATH", "The default timeout is five seconds"), with no padding or explanation of known concepts. It is lean and fully assumes Claude's competence.

5 / 5

Actionability

Guidance names exact APIs and procedures ("Use `Client(server)` for real MCP dispatch", "capture the outgoing request with `httpx2.MockTransport`") and is actionable despite having no code, which the rubric does not penalize for instruction-only skills. Minor gaps: no example test snippet and no concrete command for running the tests.

4 / 5

Workflow Clarity

The workflow is clearly sequenced (read existing tests/guide first, place the test, "run the regression against unchanged code and confirm it fails for the reported reason, then run it with the fix", run checks before committing) with explicit validation and error-recovery guidance ("reproduce it on the unchanged base"). The sequence lives in prose rather than an explicit ordered checklist, a minor gap versus anchor 5.

4 / 5

Progressive Disclosure

At 26 lines with no bundle files, the skill appropriately keeps everything inline and clearly signals external repo docs ("[testing guide](../../../docs/development/tests.mdx)", "Follow AGENTS.md"). The flat bullet list mixes setup conventions with assertion guidance where light grouping would help, which is a minor organization gap.

4 / 5

Total

17

/

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.

A specific, lean, third-person description that clearly conveys the niche (FastMCP regression testing with named tooling). Its main weakness is the absence of any "when to use" trigger clause, which both caps completeness and limits trigger-term coverage.

Suggestions

Add an explicit trigger clause, e.g. "Use when writing or updating tests for FastMCP changes, adding regression tests for bug fixes, or modifying test fixtures."

Include natural trigger variations users might say, such as "unit tests", "test suite", or "testing", to broaden keyword coverage.

Consider mentioning the verification side of the skill (running tests and static checks before committing) so the "what" covers the full scope.

DimensionReasoningScore

Specificity

"Write regression tests for FastMCP changes" names the domain and action, and "pytest fixtures, in-memory clients, and protocol boundaries" lists several concrete mechanisms. Minor gaps in coverage (running and verifying tests) keep it below anchor 5, but it exceeds the 1-2 concrete actions of anchor 3.

4 / 5

Completeness

It clearly answers "what" (write regression tests using pytest fixtures, in-memory clients, protocol boundaries) but contains no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Natural terms like "regression tests", "pytest", "fixtures", and "FastMCP" are ones users would actually say when needing this skill. Common variations such as "unit tests", "test suite", or "testing" are missing, so it does not reach comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

"FastMCP changes", "in-memory clients", and "protocol boundaries" carve out a clear niche that only a generic Python-testing skill could overlap with. The triggers are distinct and conflict risk is minimal.

5 / 5

Total

16

/

20

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository

PrefectHQ/fastmcp

Path

.agents/skills/python-tests/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.