CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

69

Quality

87%

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

The canonical home for this skill is fallow in fallow-rs/fallow

SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

Highly actionable, workflow-safe content with excellent validation loops and a well-wired reference bundle. Its main cost is length: duplicated guidance and several dense sections that belong in the reference files keep it from full token efficiency.

Suggestions

State exit-code semantics (0/1 success, others via fallow schema.exit_codes) once — in the Exit Codes section — and reference it from Agent Rule 2 instead of repeating it; do the same for the fix --yes non-TTY rule already covered in Key Gotchas.

Move the detailed flags --retirement option prose (reason codes, --flag-state, baseline gating) and the CODEOWNERS --group-by owner workflow into references/cli-reference.md or references/patterns.md, keeping one summary line plus the core command inline.

Trim the walkthrough-judgment workflow's JSON example to its required fields and point to a full example in a reference file, shortening one of the longest inline sections.

DimensionReasoningScore

Conciseness

The body is dense and free of known-concept padding, but guidance is duplicated (exit-code semantics in both Agent Rule 2 and the Exit Codes section; the fix --yes requirement in both Common Workflows and Key Gotchas) and long prose walls for flags --retirement and CODEOWNERS health largely duplicate references/cli-reference.md and could be tightened or outboarded.

3 / 5

Actionability

Nearly every section gives copy-paste-ready commands with concrete flags (e.g. the full dry-run/apply/verify fix cycle and the walkthrough judgment-file JSON example), fully covering the common cases.

5 / 5

Workflow Clarity

Multi-step processes are explicitly sequenced with validation checkpoints and error-recovery loops: "Always --dry-run before fix", "Report only the accepted judgments", and "On stale: true, fetch the guide again".

5 / 5

Progressive Disclosure

A clear References section maps to seven real one-level-deep files, and bulky catalogues are properly outboarded; however, the ~440-line body inlines several complete workflow recipes (CODEOWNERS tracking, walkthrough review, flags retirement detail) that read as reference material rather than overview.

4 / 5

Total

17

/

20

Passed

Description

88%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, comprehensive, third-person, with an explicit and specific Use-when clause. Its only weakness is trigger-synonym coverage (notably the absent "dead code" phrasing) and minor overlap risk with general review/security skills.

DimensionReasoningScore

Specificity

The description enumerates many concrete capabilities ("reports changed-code risk, cleanup opportunities, duplication, circular dependencies, complexity hotspots, architecture boundaries, design-system drift, feature flags, and opt-in security candidates"; "merge production execution data"), giving comprehensive, non-vague coverage of what the tool does.

5 / 5

Completeness

It explicitly answers both "what" (the static-analysis capability list) and "when" (an explicit Use-when clause with eight concrete trigger phrases including the tool name), matching the top anchor.

5 / 5

Trigger Term Quality

The "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" clause gives good natural-phrase coverage, but misses common synonyms users would actually say such as "dead code" and "refactor".

4 / 5

Distinctiveness Conflict Risk

Scoping to "TypeScript and JavaScript" plus the distinct "run fallow" trigger gives a mostly distinct niche, but "audit PR risk" and the security-candidate wording carry minor overlap risk with generic code-review and SAST skills.

4 / 5

Total

18

/

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

fallow-rs/fallow

Path

.agents/skills/fallow/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.