CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

syntax-text-handling

Use this skill when extracting or storing Biome AST/CST source text, working with any `SyntaxNode`, `SyntaxToken`, `TokenText`, quoted strings, token-relative ranges, or embedded-language attribute values, or diagnosing trivia, allocation, range, and temporary-borrow problems. Do not use for parser implementation or formatter comment placement.

77

Quality

97%

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 dense, expert-level practices guide: an exact API accessor table, executable Rust patterns for quote stripping, token-backed substrings, and borrow-safe owner binding, bracketed by an inspect-first step and an 8-item review checklist. Its only weakness is the 'Use Strongly Typed Nodes' section, whose core principle is largely prior knowledge and could be trimmed to the declare_node_union! pointer.

DimensionReasoningScore

Conciseness

The body is dense and assumes competence — it never explains what trivia, green tokens, or an AST is, and the accessor table plus short Rust snippets carry high information per line. The 'Use Strongly Typed Nodes' section spends 12 lines on preferring typed parameters over generic ones, a practice Claude already knows (only the declare_node_union! pointer is new), which is exactly anchor 4's 'minor instances of over-explanation that could be trimmed' rather than anchor 5's every-token-earns-its-place.

4 / 5

Actionability

Fully concrete and executable: exact APIs with return types (text_trimmed(), token_text_trimmed(), inner_string_text(), slice()/relative_range()/source_range()), copy-paste-ready Rust patterns for the common cases (quote stripping via inner_string_text(), token-backed substrings, owner-binding for borrows), a GOOD/BAD pair, and named repo files for deeper reference. Not anchor 4 — no key details are missing.

5 / 5

Workflow Clarity

Checkpoints at all stages: 'Inspect Before Implementing' verifies AST shape via the parser quick test and generated node definitions before coding; the Temporary Borrows section is error-recovery guidance tied to the actual failure signal ("Do not solve a temporary-borrow error by converting to String") with the fix pattern inline; and the 8-item 'Review Checklist' validates the result. This matches the checklist-with-error-recovery anchor; no destructive or batch operations are involved, so no cap applies.

5 / 5

Progressive Disclosure

No bundle files exist and none are needed: the ~115-line body stays overview-level with nothing that belongs in a separate file inlined, and the 'References' section is a clearly annotated, one-level-deep pointer list (e.g., 'Token text: crates/biome_rowan/src/token_text.rs'). Well-organized sections with easy navigation match the top anchor rather than anchor 4's minor organization gaps.

5 / 5

Total

19

/

20

Passed

Description

100%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 model skill description: concrete capabilities stated in the domain's own vocabulary, an explicit 'Use this skill when' trigger clause, named types and constructs that map directly to compiler errors, and negative scope that both bounds the niche and prevents conflicts with parser or formatter skills.

DimensionReasoningScore

Specificity

Names multiple concrete actions with comprehensive coverage: "extracting or storing Biome AST/CST source text", "working with any SyntaxNode, SyntaxToken, TokenText, quoted strings, token-relative ranges, or embedded-language attribute values", and "diagnosing trivia, allocation, range, and temporary-borrow problems". It is not anchor 4 because there are no coverage gaps — the diagnosis classes enumerate the domain's failure modes explicitly.

5 / 5

Completeness

Explicitly answers both questions: the what is "extracting or storing Biome AST/CST source text ... diagnosing trivia, allocation, range, and temporary-borrow problems", and the when is the explicit trigger clause "Use this skill when ..." with concrete triggers, further reinforced by negative triggers "Do not use for parser implementation or formatter comment placement". Mirrors the anchor-5 example pattern.

5 / 5

Trigger Term Quality

Uses exactly the natural terms a Biome contributor would say when hitting these problems: "quoted strings", "trivia", "allocation", "temporary-borrow", "token-relative ranges", plus the type names (SyntaxNode, SyntaxToken, TokenText) that appear in compiler errors and API calls, with near-synonyms covered via "AST/CST source text". Matches the comprehensive-synonyms anchor rather than anchor 4's "a few natural terms missing".

5 / 5

Distinctiveness Conflict Risk

Clear niche (Biome syntax-text handling) with distinct triggers, and the explicit exclusion "Do not use for parser implementation or formatter comment placement" actively prevents mis-triggering on adjacent parser/formatter skills. Minimal conflict risk, matching the clear-niche anchor.

5 / 5

Total

20

/

20

Passed

Validation

100%

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

biomejs/biome

Path

.agents/skills/syntax-text-handling/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.