fallow

Codebase intelligence for TypeScript and JavaScript. Static analysis reports changed-code risk, cleanup opportunities, duplication, circular dependencies, complexity hotspots, architecture boundaries, design-system drift, feature flags, and opt-in security candidates. Optional local similar-code discovery finds functions that may implement the same intent despite different syntax. Runtime coverage can merge production execution data. Use when asked to audit PR risk, find unused code or dependencies, compare semantically similar functions, detect duplicates, inspect architecture boundaries, merge runtime coverage, auto-fix supported issues, or run fallow.

Quality

90%

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.

An exemplary tool-skill body: fully executable commands, sequenced workflows with validation for destructive operations, and clean one-level-deep progressive disclosure. The one real weakness is token efficiency — several prose sections (onboarding policy, late agent rules, exit-code repetition) are run-on and redundant and could be cut or compressed.

Suggestions

Rewrite the 'Onboarding And Insight' section as a short bulleted decision list instead of a single run-on paragraph — it is the densest prose block in the file and much of it repeats conditions stated elsewhere.

Compress Agent Rules 9-14 (telemetry, type-aware gating, statusline, similar-code) into shorter rules with detail moved to the relevant reference file (e.g. the similar-code workflow detail in rule 14 largely duplicates references/similar-code.md).

Drop the second full exit-code explanation in 'Exit Codes' — the section restates rule 2 and points at `fallow schema.exit_codes`, so a single sentence plus the JSON error example would suffice.

Dimension	Reasoning	Score
Conciseness	The body is dense with fallow-specific facts Claude cannot know, but sections are noticeably padded: the "Onboarding And Insight" run-on paragraph, Agent Rules 9-14, and repeated exit-code explanations could all be tightened. Anchor 3 ("mostly efficient but... could be tightened") fits; not 4 because the trimming needed is more than minor, not 2 because it never explains concepts Claude already knows.	3 / 5
Actionability	Commands throughout are copy-paste ready with concrete flags (e.g. `fallow dead-code --format json --quiet --workspace 'apps/*,!apps/legacy'`), plus JSON envelope examples, exit-code semantics, and suppression-comment syntax. Fully executable guidance covering the common cases; anchor 5.	5 / 5
Workflow Clarity	Multi-step workflows are explicitly sequenced with validation checkpoints: the destructive fix cycle mandates `--dry-run` preview then `fix --yes` then re-verification, baselines are save-then-gate, and the similar-code workflow fails closed on stale source with explicit abstention rules. The destructive/batch cap does not apply because validation is present.	5 / 5
Progressive Disclosure	The body is an overview with a task-routing matrix, and the bulk catalogues (CLI reference, MCP tools, issue types, gotchas, patterns, similar-code, node bindings) are pushed to real one-level-deep reference files, each verified to exist and clearly signaled with descriptive links plus a References section. Anchor 5.	5 / 5
	Total	18 / 20 Passed

Description

96%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: concrete third-person capability statements paired with an explicit, comprehensive "Use when asked to" trigger clause. The only weakness is minor overlap risk from the breadth of subdomains covered (duplication, security, flags, design drift) relative to single-purpose code-quality skills.

Dimension	Reasoning	Score
Specificity	The description lists multiple specific concrete actions ("audit PR risk, find unused code or dependencies, compare semantically similar functions, detect duplicates, inspect architecture boundaries, merge runtime coverage, auto-fix supported issues") in third person, with comprehensive coverage of the tool's capability surface. Anchor 5 is the closest match; there is no more comprehensive anchor above it.	5 / 5
Completeness	Both halves are explicit: the first three sentences state clearly what the skill does, and "Use when asked to audit PR risk, find unused code or dependencies, ... or run fallow" gives concrete trigger phrases. This matches the anchor-5 example's structure exactly.	5 / 5
Trigger Term Quality	The "Use when asked to..." clause covers natural phrasings users would actually say ("audit PR risk", "find unused code", "detect duplicates", "compare semantically similar functions") plus the tool name itself ("run fallow"), giving comprehensive natural-term coverage. Not a 4, since no commonly-used synonym for the skill's triggers is obviously missing.	5 / 5
Distinctiveness Conflict Risk	The TypeScript/JavaScript static-analysis niche and tool-name trigger ("run fallow") are distinct, but the very broad scope (duplication, complexity, security candidates, feature flags, design drift) overlaps other code-quality and lint skills. Anchor 4 ("mostly distinct; minor overlap risk") fits better than 5, whose examples imply a tighter niche.	4 / 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: fallow-rs/fallow
Path: .claude/skills/fallow/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.