CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

settings

Use when the user asks what Repowise can be configured to do, how to turn a feature on or off, what it costs in tokens or model calls, why Repowise behaves a certain way in this repository, or asks you to change a Repowise option.

Quality

86%

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 settings in repowise-dev/repowise

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.

An exemplary instruction-only skill: dense with executable tool-specific commands, a clearly sequenced workflow with a user-confirmation checkpoint and structured error-recovery guidance, and no wasted tokens. The absence of code examples is appropriate for a CLI-driven task and the guidance is fully actionable without them.

DimensionReasoningScore

Conciseness

Every line carries tool-specific facts Claude cannot know (`repowise config` subcommands and flags, the `--format json` output shape, the refusal error taxonomy) with zero explanation of generic concepts and no padding. This matches "every token earns its place"; there is nothing to trim without losing information.

5 / 5

Actionability

Provides executable commands with flags and arguments (`repowise config list --changed`, `explain <key> --format json`, `set <key> <value>`), exact value formats ("A switch takes `true`/`false`, a list takes `a,b` or `[a, b]`"), the JSON field list, and per-error remediation (`invalid_value` — "`accepts` says what fits"). Fully copy-paste-ready instruction covering the common cases.

5 / 5

Workflow Clarity

A clear Inspect → Recommend → Change sequence with numbered steps, explicit checkpoints ("Ask the user first, naming the key, the new value and the effect. Never change a setting on your own initiative"), and feedback loops for error recovery (refusals exit 1 with structured errors whose messages steer the fix). Validation is built in via `set` validating the value.

5 / 5

Progressive Disclosure

A single-command, single-task skill with no external references needed: all content is appropriately inline and organized under scannable headers (When to use it, Inspect, Recommend, Change). Nothing that belongs in a separate file is inlined, satisfying the simple-skill exception for well-organized sections.

5 / 5

Total

20

/

20

Passed

Description

66%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 trigger-focused description with specific, natural phrasing and low conflict risk, weakened by the absence of an explicit capability statement — the "what" must be inferred from the "when" clauses. One sentence naming what the skill does (inspect, explain, set and reset Repowise settings via `repowise config`) would bring it to top level.

Suggestions

Lead with an explicit capability statement (e.g., "Lists, explains and changes Repowise settings through `repowise config`.") before the "Use when" clause so the "what" is stated rather than inferred.

Include the bare nouns users naturally say — "settings", "config", "configuration" — as trigger terms, not only the verb form "configured".

Name the concrete operations the skill performs (list, explain, set, reset) so the capability coverage matches the specificity of the trigger phrases.

DimensionReasoningScore

Specificity

Enumerates several concrete request types — "how to turn a feature on or off", "what it costs in tokens or model calls", "why Repowise behaves a certain way", "change a Repowise option" — but frames them all as triggers rather than stating the skill's actions (inspect, explain, set, reset). It exceeds anchor 3 (only 1-2 concrete actions) with four distinct capabilities, but stops short of anchor 5's comprehensive listing of the operations the skill actually performs.

4 / 5

Completeness

The "when" is explicit and rich ("Use when the user asks what Repowise can be configured to do..."), but the "what" is never explicitly stated — there is no capability sentence like "Explains and changes Repowise settings"; it must be inferred from the trigger list. This is the inverse of anchor 3 (clear what, weak when) and does not reach anchor 4, which requires both explicitly.

3 / 5

Trigger Term Quality

Phrases like "turn a feature on or off", "what it costs", and "change a Repowise option" closely mirror what a user would naturally say. Not anchor 5 because the bare nouns a user would utter — "settings", "config", "configuration" — appear only indirectly via the verb "configured", and no synonym coverage is offered.

4 / 5

Distinctiveness Conflict Risk

Scoping every trigger to the named tool ("Repowise") gives a clear niche with low conflict risk against unrelated skills. Not anchor 5 because "why Repowise behaves a certain way in this repository" could also fire for a closely related Repowise troubleshooting or usage skill, leaving minor overlap risk.

4 / 5

Total

15

/

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/codex/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.