CtrlK
BlogDocsLog inGet started
Tessl Logo

bun-file-io

Use this when you are working on file operations like reading, writing, scanning, or deleting files. It summarizes the preferred file APIs and patterns used in this repo. It also notes when to use filesystem helpers for directories.

68

Quality

82%

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

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, well-organized Bun file-I/O reference that respects the token budget and is easy to navigate. It loses points for lacking executable code examples and for presenting a destructive delete operation without any verification guidance.

Suggestions

Add one or two complete runnable snippets (e.g. a full Bun.Glob scan-and-read example) to lift actionability to copy-paste-ready.

For the destructive Bun.file(...).delete() operation, add a brief validation/verification step (e.g. check exists() and confirm intent) so workflow clarity is not capped.

DimensionReasoningScore

Conciseness

Lean bullet reference that assumes Claude's competence — it never explains what Bun or a FileSink is, and every bullet earns its place; this matches the lean-and-efficient anchor rather than the level below which includes unnecessary explanation.

3 / 3

Actionability

Concrete API names and signatures are given (e.g. "Array.fromAsync(glob.scan({ cwd, absolute, onlyFiles, dot }))"), but there are no complete executable code blocks, so it lands at "some concrete guidance but incomplete" rather than copy-paste-ready examples.

2 / 3

Workflow Clarity

A "Quick checklist" supplies loose ordering, but there is no sequenced multi-step workflow and the destructive Bun.file(...).delete() operation appears with no validation checkpoint, capping this at 2 per the destructive-operations guideline.

2 / 3

Progressive Disclosure

Under 50 lines with no external bundle files (none of references/scripts/assets exist) and well-organized sections (Use this when, Bun file APIs, When to use node:fs, Repo patterns, Quick checklist), meeting the simple-skill allowance for a 3 on organization alone.

3 / 3

Total

10

/

12

Passed

Description

92%

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 with explicit "Use when" triggers and concrete action verbs, cleanly answering both what and when. Its main weakness is distinctiveness: the trigger is generic file I/O that could collide with other file skills.

Suggestions

Add a distinguishing keyword (e.g., "Bun file APIs" or "OpenScience CLI") to the description so it is unlikely to trigger for unrelated file-handling skills.

Consider trimming "It also notes when to use filesystem helpers for directories" which is implementation detail rather than a trigger cue.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "reading, writing, scanning, or deleting files" — matching the anchor for listing several specific concrete actions; not merely naming a domain.

3 / 3

Completeness

Explicitly answers both what ("summarizes the preferred file APIs and patterns used in this repo") and when ("Use this when you are working on file operations like reading, writing, scanning, or deleting files"), satisfying the explicit-trigger anchor.

3 / 3

Trigger Term Quality

Natural terms a user would say ("file operations", "reading, writing, scanning, or deleting files", "directories") give good coverage; it is not the level below which only names a domain with no common variations.

3 / 3

Distinctiveness Conflict Risk

The trigger "file operations like reading, writing, scanning, or deleting files" is broad and could overlap with general file-handling skills; it does not name Bun or a distinct niche, so it sits at "somewhat specific but could still overlap" rather than the clear-niche anchor.

2 / 3

Total

11

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
synthetic-sciences/openscience
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.