CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

plankton-code-quality

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

Quality

71%

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 ./skills/plankton-code-quality/SKILL.md

The canonical home for this skill is plankton-code-quality in affaan-m/ECC

SKILL.md
Quality
Evals
Security

Quality

Content

63%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, largely actionable reference whose core architecture and setup sections carry real executable detail. It is dragged down by a padded "ECC v1.8 Additions" section, a missing repository URL despite requiring manual installation, and dangling named references with no paths or bundled files behind them.

Suggestions

Trim or remove the "ECC v1.8 Additions" section — its hook-profile exports, gate table, and health-metrics bullets are too vague to act on; either make them concrete (exact commands, exact gate behavior) or move them to a reference file.

Add the actual Plankton repository URL to the Quick Start note so "requires manual installation from its repository" is actionable, and include a one-command verification step (e.g. how to confirm hooks fired after an edit).

Resolve the dangling references: link REFERENCE.md and SETUP.md as real bundled files (or drop them), and consider moving the full config JSON and env-var tables into a reference file so SKILL.md stays a lean overview.

DimensionReasoningScore

Conciseness

The core sections (three-phase diagram, dependency tables, config JSON) are dense and useful, but the "ECC v1.8 Additions" section pads with vague, non-actionable lists ("Track: edits flagged by gates, average remediation time...") and a three-line "Language Gate Table", fitting the mostly-efficient-but-could-be-tightened anchor.

3 / 5

Actionability

Provides mostly executable guidance — "brew install jaq ruff uv", "uv sync --all-extras", a real config.json with key settings explained, an env-var table, and numbered integration steps — with a minor gap: "requires manual installation from its repository" gives no URL or path to actually obtain the tool.

4 / 5

Workflow Clarity

The three-phase architecture is clearly sequenced with an explicit verification loop ("Re-runs Phase 1+2 to verify fixes... Exit 0 if clean, Exit 2 if violations remain") and exit-code semantics, matching the clear-sequence-most-checkpoints anchor; not 5 because setup and per-project integration lack any step to verify hooks are actually active.

4 / 5

Progressive Disclosure

No bundle files exist and the References section only names external documents ("Plankton REFERENCE.md — Full architecture documentation", "Plankton SETUP.md") without links or paths, while the full configuration reference is inlined in SKILL.md — some structure, but references are not clearly signaled and separate-worthy content is inline.

3 / 5

Total

14

/

20

Passed

Description

66%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, third-person description with concrete named actions and good natural keywords, anchored by a distinct named tool. Its main weakness is the complete absence of "when to use" trigger guidance, which caps completeness and leaves invocation conditions entirely implicit.

Suggestions

Add an explicit trigger clause, e.g. "Use when setting up automatic formatting/linting on file edits, or when the user wants write-time code quality enforcement instead of commit-time checks."

Include a few natural synonyms such as "code style" or "lint on save/edit" alongside "auto-formatting" and "linting" to broaden trigger-term coverage.

Name the supported languages (Python, TypeScript, Shell, etc.) briefly to sharpen the what-portion and further reduce overlap with generic linting skills.

DimensionReasoningScore

Specificity

Lists several concrete actions — "auto-formatting, linting, and Claude-powered fixes" — plus the trigger mechanism "on every file edit via hooks", matching the several-specific-actions anchor; not 5 because coverage has gaps (no languages, linters, or file types named).

4 / 5

Completeness

The "what" is clear (write-time enforcement via formatting, linting, and Claude-powered fixes), but there is no "Use when..." clause or equivalent explicit trigger guidance — "on every file edit via hooks" describes the mechanism, not when to invoke the skill — which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

"auto-formatting", "linting", "fixes", and "code quality" are natural user phrases, giving good keyword coverage; a few natural terms ("code style", "tidy", "clean up") are missing and "write-time" is jargon, so it falls short of the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

The named tool "Plankton" and the "write-time" framing carve a mostly distinct niche versus commit-time/CI lint skills, with only minor overlap risk against generic formatter/linter skills; not 5 because "code quality enforcement" still overlaps with broader code-quality skills.

4 / 5

Total

15

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

valeriibeck-star/claude-skills

Path

skills/plankton-code-quality/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.