biome-complete

Complete Biome toolchain guidance for real repository workflows. Use when users ask to configure biome.json, run lint or format commands, migrate from ESLint or Prettier, tune rule severity, fix formatter drift, or replace mixed ESLint+Prettier pipelines with Biome-only workflows.

Quality

88%

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

85%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.

Highly actionable and well-structured content with an exemplary validated workflow and clean progressive disclosure into four real reference files. The main drag on token efficiency is redundancy: the Quick Commands section duplicates four commands already given in the workflow, and anti-pattern Consequence lines repeat their WHY rationale.

Suggestions

Collapse the Quick Commands section so each command appears only once — either fold the two unique entries (format --write, single-file check) into the workflow/Quick Commands and drop the four duplicates, saving roughly 30 lines.

Drop or merge the "Consequence" line of each anti-pattern with its "WHY" line, since they restate the same rationale (e.g., "Competing rules create contradictory output" vs "Duplicate diagnostics and unstable CI outcomes").

Add the missing natural trigger phrases from the body's "When to Apply" ("set up Biome", "run Biome in CI") to the frontmatter description to round out trigger coverage.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean (no explanations of what Biome is or how linters work), but the "Quick Commands" section repeats `bunx @biomejs/biome init`, `check .`, `check . --write`, and `check . --error-on-warnings` verbatim from the "Deterministic Workflow", and the "Consequence" lines largely restate each anti-pattern's "WHY". This matches anchor 3 ("mostly efficient but… could be tightened") better than 4, where trimming would be only minor.	3 / 5
Actionability	Every command is fully executable and copy-paste ready (`bunx @biomejs/biome init`, `check .`, `check . --write`, `format . --write`, single-file check, `--error-on-warnings` for CI), each paired with an expected result. Coverage of the common cases matches the top anchor.	5 / 5
Workflow Clarity	The six-step "Deterministic Workflow" has a clear sequence with explicit Verify checkpoints at steps 3, 4, and 6, and an "Error Recovery" passage providing a feedback loop (disable rule groups, re-enable one at a time) for the repository-wide `--write` batch operation. This matches anchor 5: explicit validation plus error-recovery guidance.	5 / 5
Progressive Disclosure	SKILL.md stays an overview and splits detail across four references that all exist, are one level deep (no nested references found in them), and are each annotated with their scope in the References section; one is also linked contextually inline in the workflow. This matches the top anchor for clear, well-signaled one-level-deep navigation.	5 / 5
	Total	18 / 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 description that clearly states what the skill does and when to use it, with concrete trigger phrases and a well-defined niche. The only weakness is a handful of missing natural trigger variations (setup, CI usage) that keep trigger-term coverage just short of comprehensive.

Dimension	Reasoning	Score
Specificity	The description enumerates six concrete actions — "configure biome.json", "run lint or format commands", "migrate from ESLint or Prettier", "tune rule severity", "fix formatter drift", "replace mixed ESLint+Prettier pipelines" — giving comprehensive coverage of the skill's capabilities. It matches the top anchor (multiple specific concrete actions) rather than 4, since there are no meaningful coverage gaps for the Biome domain.	5 / 5
Completeness	It explicitly answers both questions: the "what" ("Complete Biome toolchain guidance for real repository workflows" with enumerated capabilities) and the "when" ("Use when users ask to…" followed by concrete trigger phrases). This matches the top anchor exactly.	5 / 5
Trigger Term Quality	Good keyword coverage with natural phrases users would say ("migrate from ESLint", "fix formatter drift", "configure biome.json", "tune rule severity"). A few natural terms are missing — e.g., "set up Biome", "run Biome in CI", "biome check" — which appear in the body but not the description, placing it at anchor 4 rather than the comprehensive synonym/extension coverage of anchor 5.	4 / 5
Distinctiveness Conflict Risk	Clear niche (Biome toolchain) with distinct, tool-specific triggers; the explicit ESLint/Prettier migration framing makes confusion with linter- or formatter-specific skills unlikely. Minimal conflict risk, matching anchor 5.	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: pantheon-org/tekhne
Path: skills/development/biome-complete/SKILL.md
Commit: a1083f4

Reviewed: 1 hour 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.