CtrlK
BlogDocsLog inGet started
Tessl Logo

python-review

Python code review guidelines for the Cog SDK

64

Quality

75%

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 ./.opencode/skills/python-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

100%

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 tight, well-organized code-review checklist that assumes Claude's competence and gives concrete file-level and rule-level guidance without padding. It fully satisfies the simple-skill exceptions for workflow clarity and progressive disclosure.

DimensionReasoningScore

Conciseness

The body is a lean bulleted checklist with no padding or explanations of concepts Claude already knows; the brief intro sentence earns its place by giving concrete path context, matching 'lean and efficient; every token earns its place'.

3 / 3

Actionability

Guidance is concrete and specific for an instruction-only review skill, citing exact files (base_predictor.py, types.py, python/cog/server/) and explicit rules (no bare except, from __future__ import annotations, Python 3.10-3.13), so absent executable code is not penalized.

3 / 3

Workflow Clarity

As a single-purpose, under-50-line review skill the action is unambiguous and well-organized into 'skip these (linters)' then category-based 'what to look for', qualifying for the simple-skills workflow_clarity exception.

3 / 3

Progressive Disclosure

The skill is under 50 lines, needs no external references (none present in references/scripts/assets), and is organized into clear sections, satisfying the under-50-lines progressive_disclosure exception.

3 / 3

Total

12

/

12

Passed

Description

50%

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 correctly states the skill's purpose and domain in concise third person, but lacks any 'Use when...' trigger guidance and lists no concrete review actions. Adding explicit trigger terms and specific capabilities would raise specificity, completeness, and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when reviewing Python code in the Cog SDK (python/cog/)'.

List concrete review actions (e.g. checking type annotations, async correctness, backward compatibility) instead of the generic 'guidelines'.

Include natural trigger variations such as 'code review', 'check Python code', or 'lint Cog SDK changes'.

DimensionReasoningScore

Specificity

"Python code review guidelines for the Cog SDK" names a concrete domain (Python, Cog SDK) and the activity (code review), but lists no specific review actions, matching the 'names domain and some actions, but not comprehensive' anchor rather than the multi-action level 3.

2 / 3

Completeness

It states what the skill provides ("Python code review guidelines for the Cog SDK") but has no 'Use when...' trigger guidance, so per the judging guideline completeness is capped at 2 ('has what, but when is missing or only implied').

2 / 3

Trigger Term Quality

"Python code review" and "Cog SDK" are relevant terms a user might say, but common variations like "check code", "lint", or "code quality" are missing, fitting 'some relevant keywords but missing common variations'.

2 / 3

Distinctiveness Conflict Risk

The Cog SDK scoping gives it a niche, but the absence of explicit triggers means it could still overlap with a generic Python review skill, matching 'somewhat specific but could still overlap with similar skills'.

2 / 3

Total

8

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
replicate/cog
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.