fallow

Codebase intelligence for JavaScript and TypeScript. Free static layer reports quality, changed-code risk, cleanup opportunities (unused files, exports, types, dependencies), code duplication, circular dependencies, complexity hotspots, architecture boundary violations, feature flag patterns, and opt-in security candidates. Runtime coverage merges production execution data into the same health report for hot-path review, cold-path deletion confidence, and stale-flag evidence, with a single local capture available by default and continuous/cloud runtime monitoring available as an optional mode. 118 framework plugins, zero configuration, sub-second static analysis. Use when asked to analyze code health, audit PR risk, find cleanup opportunities or unused code, detect duplicates, check circular dependencies, audit complexity, check architecture boundaries, detect feature flags, surface security candidates, clean up the codebase, auto-fix issues, merge runtime coverage, or run fallow.

Quality

81%

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

71%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 highly actionable, well-structured reference manual with concrete commands, validation-gated destructive workflows, and clearly signaled bundle files. Its main weakness is density: the body inlines substantial reference-grade detail and repeats the description, blurring the overview/reference boundary.

Suggestions

Trim or remove the opening paragraph that restates the frontmatter description; the body's own 'When to Use' / 'When NOT to Use' sections already orient the reader.

Move the long inline asides in table cells (Angular template suppression in the health row, the security CWE catalogue) into references/cli-reference.md or references/gotchas.md, leaving a one-line summary plus a link in the table.

Relocate the full Commands, Issue Types, and MCP Tools tables (or their exhaustive flag columns) into references/cli-reference.md so SKILL.md reads as an overview pointing to detail, lifting the progressive_disclosure score.

Dimension	Reasoning	Score
Conciseness	Most tokens are concrete flags and commands that earn their place, but the opening paragraph restates the frontmatter description verbatim and several table cells embed tutorial-length asides (e.g. Angular template suppression rules, the security CWE catalogue) that could be tightened or moved to references.	3 / 5
Actionability	Fully executable guidance throughout: copy-paste bash workflows, complete command/flag tables, MCP tool signatures with required params, Node.js binding code samples, and explicit exit-code semantics covering the common cases.	5 / 5
Workflow Clarity	The 'Safe auto-fix cycle' gives an explicit dry-run → review → apply → verify sequence with a validation checkpoint for the destructive fix operation, and the Instructions section numbers the high-level process; minor error-recovery guidance gaps keep it just below a 5.	4 / 5
Progressive Disclosure	Three real reference files (cli-reference.md, gotchas.md, patterns.md) are clearly signaled one level deep in a dedicated References section, but the ~400-line body inlines large reference-grade material — full command/flag, issue-type, and MCP-tool tables — that would more naturally live in cli-reference.md.	3 / 5
	Total	15 / 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, concrete description that names the domain, enumerates specific capabilities, and provides an explicit 'Use when...' trigger clause with many natural phrases. Slightly jargony in places, but highly distinct and complete.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'reports quality, changed-code risk, cleanup opportunities (unused files, exports, types, dependencies), code duplication, circular dependencies, complexity hotspots, architecture boundary violations, feature flag patterns, and opt-in security candidates' — covering the tool's surface comprehensively.	5 / 5
Completeness	Explicitly answers both 'what' (free static layer reports ... runtime coverage merges production execution data ...) and 'when' ('Use when asked to analyze code health, audit PR risk, ... or run fallow') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural trigger phrases are present and numerous ('find cleanup opportunities or unused code', 'detect duplicates', 'audit PR risk', 'clean up the codebase', 'auto-fix issues', 'run fallow'), but a few terms lean technical and some common synonyms a lay user might say are not exhaustively covered.	4 / 5
Distinctiveness Conflict Risk	Scoped to 'JavaScript and TypeScript' codebase intelligence with a named tool ('fallow') and a distinct, specialized trigger list, giving it a clear niche with minimal overlap risk.	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: RaquelSousa/kel-portfolio-2.0
Path: .claude/skills/fallow/SKILL.md
Commit: ee820de

Reviewed: 10 hours 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.