CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

70

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

The risk profile of this skill

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

SKILL.md
Quality
Evals
Security

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.

The body is a highly actionable, well-structured reference with strong workflows and clean progressive disclosure into verified bundle files. Its main weakness is conciseness: a redundant opening paragraph and several over-long table cells repeat or over-explain material that a competent reader already has.

Suggestions

Remove or shrink the opening prose paragraph, which duplicates the frontmatter description almost verbatim and adds no new guidance.

Trim the long inline prose in the Commands and Issue Types table cells (e.g. framework-template suppression details, security rule-family caveats) into one-line summaries and defer the full explanations to references/cli-reference.md or references/gotchas.md.

Consider moving the large Commands and Issue Types tables into references/cli-reference.md, leaving the body with the task-matrix and Common Workflows sections that an agent actually acts on first.

DimensionReasoningScore

Conciseness

Mostly efficient reference content, but the opening prose paragraph restates the frontmatter description verbatim and several table cells (e.g. the `health` and `security` command descriptions) carry long inline explanations that could be trimmed or pushed to references; this is 'mostly efficient but could be tightened' rather than lean.

3 / 5

Actionability

Copy-paste-ready, executable bash throughout — the 'Safe auto-fix cycle' (dry-run → fix --yes → verify) and dozens of specific flagged commands cover the common cases exactly as the top anchor requires.

5 / 5

Workflow Clarity

Multi-step workflows are clearly sequenced with explicit validation checkpoints and feedback loops, including the dry-run/apply/verify fix cycle and the similar-code status→discovery→inspect→verdict→review flow with fail-closed staleness checks.

5 / 5

Progressive Disclosure

A clear overview body with well-signaled, one-level-deep references to six real bundle files (cli-reference.md, mcp.md, gotchas.md, patterns.md, similar-code.md, node-bindings.md), keeping detailed material off the main page while retaining key inline examples.

5 / 5

Total

18

/

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.

The description is specific, complete, and well-triggered, pairing a comprehensive capability list with an explicit 'Use when...' clause of natural phrases. It is highly distinct for TS/JS analysis with only minor overlap risk against general-purpose audit/lint skills.

DimensionReasoningScore

Specificity

Lists multiple specific concrete analysis actions — 'reports changed-code risk, cleanup opportunities, duplication, circular dependencies, complexity hotspots, architecture boundaries, design-system drift, feature flags, and opt-in security candidates' plus similar-code discovery and runtime-coverage merging — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers both 'what' (the static-analysis, similar-code, and runtime-coverage capabilities) and 'when' via a concrete 'Use when asked to audit PR risk, find unused code or dependencies, ... or run fallow' clause with multiple trigger phrases.

5 / 5

Trigger Term Quality

Strong natural trigger phrases ('audit PR risk', 'find unused code or dependencies', 'compare semantically similar functions', 'detect duplicates', 'auto-fix supported issues', 'run fallow') that users would plausibly say; stops short of 5 because synonym/extension variants beyond this enumerated set are sparse.

4 / 5

Distinctiveness Conflict Risk

A clear TS/JS codebase-intelligence niche with fallow-specific triggers ('run fallow', 'compare semantically similar functions') keeps conflict risk low; not a 5 because several trigger phrases (audit PR, find duplicates) overlap with adjacent lint/audit skills.

4 / 5

Total

18

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (503 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
fallow-rs/fallow
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.