CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

settings

Repowise options, what they cost, and changing them.

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/claude-code/skills/settings/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

100%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 an exemplary instruction-only skill: lean, dense with executable commands and exact output/error semantics, and organized as a clear inspect-recommend-change workflow with an ask-first safety checkpoint. Nothing is padded, and every section earns its place.

DimensionReasoningScore

Conciseness

Every sentence is tool-specific operational detail — source precedence (default/repository/user/environment), value formats, JSON output shapes, and error semantics — with no explanation of concepts Claude already knows and no padding. Nothing could be cut without losing information, matching the 'every token earns its place' anchor.

5 / 5

Actionability

Fully executable guidance throughout: exact commands (`repowise config list --changed`, `explain <key> --format json`, `set <key> <value>`), accepted value formats (`true`/`false`, `a,b`, `[a, b]`), the JSON output schema with per-setting fields, and enumerated error codes (`unknown_setting`, `invalid_value`, `env_only`, `config_unreadable`) each with a remediation. This is copy-paste ready and covers the common cases.

5 / 5

Workflow Clarity

The Inspect → Recommend → Change flow is clearly sequenced with an explicit ask-first checkpoint before any mutation, validation via `set`, before/after state in JSON output, and explicit error-recovery guidance per error code. Settings changes are not destructive or batch operations, and validation and feedback loops are present anyway, so no cap applies.

5 / 5

Progressive Disclosure

This is a single-purpose, ~64-line instruction skill with no bundle files (no references/, scripts/, or assets/ exist) and no content that warrants splitting out — the inline areas list and error-code table are each short and load-bearing where they sit. Sections (When to use it, Inspect, Recommend, Change) are well-organized, matching the simple-skill allowance for a top score without external references.

5 / 5

Total

20

/

20

Passed

Description

48%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 clearly identifies its niche (Repowise configuration, costs, and changes) but is underbuilt as a trigger document: no 'Use when' guidance, generic action verbs, and missing the natural synonyms (settings, config, turn on/off) a user would actually say. It would reliably be found when someone names Repowise explicitly, but easily missed for phrasing like "change this setting" or "why is this so expensive".

Suggestions

Add a 'Use when...' clause with explicit triggers, e.g. 'Use when the user asks about Repowise settings or configuration, what an option costs in tokens or model calls, or asks to turn an option on/off or change its value.'

Replace generic phrasing with concrete verbs and synonyms: 'Lists, explains, and changes Repowise settings (config options): what each costs and when it takes effect' — this lifts both specificity and trigger coverage.

Include the natural terms users would say — 'settings', 'config', 'configuration', 'environment variables', 'turn on/off' — so the skill triggers even when 'Repowise' is only implied by context.

DimensionReasoningScore

Specificity

The description names its domain ("Repowise options") and a cost framing, but the only stated action is the generic "changing them" — no concrete verbs like list, explain, set, or reset. This matches the anchor 'Names the domain but actions are minimal or generic' rather than score 3, which requires 1-2 concrete actions.

2 / 5

Completeness

It gives a clear 'what' (Repowise options, their costs, and changing them) but has no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Score 4 is ruled out because 'when' is entirely absent, and score 2 because the 'what' is clear rather than vague.

3 / 5

Trigger Term Quality

"Repowise", "options", "cost", and "changing" are relevant keywords, but common natural variations users would say — "settings", "config", "configuration", "turn on/off" — are missing. Keyword coverage is partial rather than good, so it sits at the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

It is scoped to one specific tool's configuration — a clear niche with only minor overlap risk against sibling Repowise skills. It falls short of score 5 because the generic phrasing "options... changing them" lacks distinct triggers that would fully separate it from other Repowise tooling skills.

4 / 5

Total

12

/

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

repowise-dev/repowise

Path

plugins/claude-code/skills/settings/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.