climate-indices-conventions

Repository conventions for the climate_indices Python scientific-computing library — enforces coding style, module boundaries, test placement, and Conventional Commit format. Use when changing climate_indices, writing its tests or docs, preparing commits, or running ruff/mypy validation and pytest tests.

Quality

87%

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

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.

A well-structured, actionable conventions skill with copy-paste validation commands and a clear feature workflow. The main gap is the absence of an explicit validate→fix→retry feedback loop in the workflow section.

Suggestions

Add an explicit feedback loop to the Feature Workflow: after running validation, if ruff/mypy/pytest fail, fix the reported issues and re-run until all checks pass before review.

Tighten the opening by removing the body's "Use this skill when changing climate_indices..." line since it duplicates the frontmatter description.

Clarify what to do when a change crosses module boundaries (the table implies strict boundaries but the workflow doesn't address multi-module changes).

Dimension	Reasoning	Score
Conciseness	The body is efficient — tables and direct command blocks assume Claude's competence — with only minor padding such as the repeated "Use this skill when..." opener and the generated-on provenance line.	4 / 5
Actionability	Copy-paste-ready validation commands (`uv run ruff check`, `mypy`, `pytest`), concrete import examples, and specific Conventional Commit message examples fully cover the common cases.	5 / 5
Workflow Clarity	The Feature Workflow is a clearly sequenced 5-step list ending in a validation checkpoint, but it lacks an explicit fix-and-retry feedback loop on validation failure.	4 / 5
Progressive Disclosure	Content is well-organized into clearly headed self-contained sections with no bundle files and no nested references; it sits just below a 5 because the body exceeds the simple-skill size threshold where structure alone earns top marks.	4 / 5
	Total	17 / 20 Passed

Description

92%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, specific description that clearly states both the skill's purpose and when to invoke it, with concrete trigger phrases tied to a named library. Minor room to add synonyms or file extensions to lift trigger quality to a 5.

Dimension	Reasoning	Score
Specificity	"enforces coding style, module boundaries, test placement, and Conventional Commit format" lists multiple specific concrete enforcement actions with comprehensive coverage of the convention domain.	5 / 5
Completeness	It explicitly states what the skill does (enforces coding style, module boundaries, test placement, Conventional Commit format) and gives a concrete "Use when..." trigger clause covering multiple scenarios.	5 / 5
Trigger Term Quality	"changing climate_indices, writing its tests or docs, preparing commits, or running ruff/mypy validation and pytest tests" provides good natural trigger coverage, though it lacks synonyms and file-extension variants for a 5.	4 / 5
Distinctiveness Conflict Risk	Naming the specific climate_indices library with library-specific triggers carves a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: monocongo/climate_indices
Path: .agents/skills/climate_indices/SKILL.md
Commit: 5c104b3

Reviewed: 15 hours ago

Table of Contents

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.