docstring

Document a Python module and its classes using Google style

Quality

68%

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 ./.claude/skills/docstring/SKILL.md

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.

The body is a strong, highly actionable reference: concrete docstring templates with real examples for every construct, explicit application order, skip rules, and a verification checklist with a `/prose-review` feedback loop. Its main weaknesses are minor — a numbering gap in the workflow steps and template-plus-example duplication that could be tightened.

Suggestions

Fix the instruction numbering: the ordered list jumps from step 2 to step 4, skipping step 3.

For each format section, merge the generic template and the worked example into one block to cut duplicated content and reduce token cost.

Consider moving the longer format examples (class docstring, deprecation) into a references/ file if the skill grows, keeping SKILL.md as a compact overview.

Dimension	Reasoning	Score
Conciseness	The body is composed almost entirely of concrete format templates and real examples with no padding about concepts Claude already knows, but each format section repeats a generic template followed by a full worked example, which could be tightened into one. This fits anchor 4 (efficient, minor over-explanation that could be trimmed) rather than anchor 5's every-token-earns-its-place.	4 / 5
Actionability	Every docstring format (module, class, `__init__`, method, dataclass, enum, deprecation) has a copy-paste-ready template plus a concrete real-world example, plus explicit skip rules and Good/Bad style pairs. This matches anchor 5's fully executable, copy-paste-ready coverage of common cases.	5 / 5
Workflow Clarity	The sequence is clear — disambiguate the target (prompting the user when multiple matches), read the module, apply in a stated order, honor skip rules — and ends with a verification feedback loop (run `/prose-review`, fix flags, verify checklist). It falls short of anchor 5 because the numbered instruction list skips from step 2 to step 4 (no step 3), leaving a small gap in an otherwise explicit sequence.	4 / 5
Progressive Disclosure	There are no bundle files (no references/, scripts/, assets/), so the skill is a single ~253-line file whose cohesive format templates are appropriately inline and organized under clear section headers. This fits anchor 4 (good structure, content appropriately placed); the length of the format-example material borders on reference-file content, keeping it from anchor 5.	4 / 5
	Total	17 / 20 Passed

Description

53%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 states a clear, concrete capability in a distinct niche but lacks any "Use when..." trigger guidance and omits the key term "docstring" along with the function/method coverage the skill actually provides. It is functional but noticeably below the good examples' standard of pairing a what-clause with explicit when-triggers.

Suggestions

Add an explicit trigger clause, e.g. "Use when asked to add or improve docstrings/documentation on Python code, or when the user mentions Google-style or Sphinx docstrings."

Include the natural keyword "docstring(s)" and broaden object coverage to "modules, classes, and methods" so trigger terms match what users actually say.

Mention the completion criterion (leave already-documented code unchanged) or the verification step to sharpen the boundary with generic writing-review skills.

Dimension	Reasoning	Score
Specificity	"Document a Python module and its classes using Google style" names the domain plus two concrete actions (module, classes), but omits functions, methods, dataclasses, and enums that the body actually covers. It is more concrete than anchor 2's generic actions but does not list the several specific actions required for anchor 4.	3 / 5
Completeness	The description clearly answers "what" (document Python modules and classes in Google style) but contains no "Use when..." clause or equivalent explicit trigger guidance, capping completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Relevant keywords like "Document", "Python module", "classes", and "Google style" are present, but the most natural trigger term users would say — "docstring" — is missing, along with common variations like "documentation" and "functions/methods". This matches anchor 3 (some relevant keywords, missing common synonyms) rather than anchor 4's good coverage.	3 / 5
Distinctiveness Conflict Risk	Python plus Google-style docstring conventions is a clear niche with minor overlap risk against generic writing or prose-review skills, fitting anchor 4. It is not anchor 5 because the missing "when" triggers leave the boundary with adjacent documentation skills slightly soft.	4 / 5
	Total	13 / 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: pipecat-ai/pipecat
Path: .claude/skills/docstring/SKILL.md
Commit: baf1f16

Reviewed: 3 days 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.