vscode-review

Review fallow's VS Code extension behavior, activation, commands, views, downloads, and LSP-client integration. Use when changes touch editors/vscode.

Quality

85%

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

82%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.

The content is exceptionally lean and well-structured as a thin pointer skill, with a clear output contract and focus areas. Its main weakness is that nearly all methodology lives in external referenced files, so the body offers little standalone actionable review guidance.

Suggestions

Add 2-3 concrete review checks inline (e.g., verify activation events match contributed commands, confirm downloads are awaited/validated) so the skill is actionable even if the referenced .agents files are unavailable.

Bundle the referenced methodology (`.agents/agents/vscode-reviewer.md`, `.agents/rules/vscode-extension.md`) into the skill's own references/ directory so progressive disclosure is self-contained.

Make the review workflow explicit with a short numbered sequence (read sources → run checks → summarize findings → emit verdict) to strengthen workflow clarity.

Dimension	Reasoning	Score
Conciseness	The ~9-line body is lean and efficient — a Read list, a one-line focus statement, and a required verdict — with no padding or explanation of concepts Claude already knows.	5 / 5
Actionability	Concrete guidance is present (specific files to read, four named focus areas, and an explicit APPROVE/CONCERN/BLOCK output contract), but the actual review methodology is delegated to the referenced files, leaving minor gaps in the body itself.	4 / 5
Workflow Clarity	A clear read → review → verdict sequence is implied and unambiguous for a read-only review task; no validation checkpoints are required since the operation is non-destructive, but the intermediate review steps remain implicit.	4 / 5
Progressive Disclosure	The body is a well-signaled, one-level-deep pointer to two reference files under a clear "Read:" list, but those references are repo-relative paths (`.agents/...`) external to the skill bundle rather than bundled files, a minor organization concern.	4 / 5
	Total	17 / 20 Passed

Description

87%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.

The description is concise, third-person, and clearly states both the review scope and a concrete trigger condition. It lists multiple specific focus areas and is highly distinct, with only minor room for additional trigger synonyms.

Dimension	Reasoning	Score
Specificity	Quotes "behavior, activation, commands, views, downloads, and LSP-client integration" — lists several concrete review focus areas, though the sole action ("Review") is generic, leaving minor coverage gaps relative to a fully comprehensive action list.	4 / 5
Completeness	Explicitly answers both what ("Review fallow's VS Code extension behavior, activation, commands, views, downloads, and LSP-client integration") and when ("Use when changes touch editors/vscode") with a concrete trigger phrase.	5 / 5
Trigger Term Quality	"Use when changes touch editors/vscode" and "VS Code extension" provide good natural trigger coverage for a code-review context, but a few common synonyms (e.g. "extension", "plugin") are missing.	4 / 5
Distinctiveness Conflict Risk	The product-specific "fallow's VS Code extension" and path-scoped trigger "editors/vscode" carve a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	18 / 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: fallow-rs/fallow
Path: .agents/skills/vscode-review/SKILL.md
Commit: 74177e5

Reviewed: 5 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.