plankton-code-quality

Write-time code quality enforcement using Plankton — auto-formatting, linting, and Claude-powered fixes on every file edit via hooks.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./skills/plankton-code-quality/SKILL.md

Quality

Content

77%

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 and presents a clear, well-validated workflow with concrete commands and configuration. It is slightly verbose and would benefit from splitting the inline configuration reference into a separate bundled file now that progressive disclosure is available.

Suggestions

Move the full '.claude/hooks/config.json' reference and the language-dependency table into a separate REFERENCE.md bundle file, leaving a concise summary inline with a clearly signaled link.

Tighten the ECC pairing section — the comparison table is useful but the surrounding prose repeats its content and could be trimmed.

Consider bundling a setup script under scripts/ so the documented installation steps are directly executable rather than copy-pasted manually.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with well-organized tables and a clear architecture diagram, but the inline full config JSON and the ECC pairing/comparison prose add bulk that could be tightened or delegated.	2 / 3
Actionability	Provides concrete, executable guidance — 'brew install jaq ruff uv', 'uv sync --all-extras', a full config.json, and an environment-override table — that is copy-paste ready.	3 / 3
Workflow Clarity	The three-phase architecture is clearly sequenced with an explicit verification loop ('Re-runs Phase 1+2 to verify fixes') and exit-code semantics, and setup steps are numbered.	3 / 3
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent), and the body is a single monolithic document; external Plankton docs are signaled one level deep, but the large inline config and API-style reference could be split into separate files.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 and distinct, naming concrete enforcement actions and a clear niche, but it omits any explicit 'Use when...' trigger guidance, which caps completeness and weakens trigger-term coverage. Adding a natural trigger clause would bring it to the top band.

Suggestions

Add an explicit 'Use when ...' trigger clause naming situations a user would naturally voice (e.g., 'Use when you want formatting and linting enforced on every file edit, or when the user mentions code quality hooks or Plankton').

Broaden trigger-term coverage with natural user phrasings like 'code quality', 'lint on save', 'format on edit', and 'hook-based linting'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'auto-formatting, linting, and Claude-powered fixes on every file edit via hooks' — rather than vague language.	3 / 3
Completeness	Clearly answers what the skill does but has no explicit 'when to use' clause; per rubric guidelines a missing 'Use when...' trigger caps completeness at 2.	2 / 3
Trigger Term Quality	Contains relevant terms like 'formatting', 'linting', and 'code quality' but lacks a natural 'Use when...' trigger phrasing and omits common user variations.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear niche — 'write-time code quality enforcement ... via hooks' — with distinct triggers unlikely to conflict with other skills.	3 / 3
	Total	10 / 12 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Commit: 754b8dd

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.