trainhop-adv-target

End-to-end New Tab train-hop targeting for the Experimenter repo. From a single trainhop version string, files the GitHub targeting issue, branches, adds the NimbusTargetingConfig entry, lints, and stages a drafted commit. Use for "newtab trainhop targeting" requests.

Quality

87%

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

82%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.

A highly actionable, well-sequenced skill body with concrete commands and templates throughout. The main improvements would be adding an explicit ruff-fail recovery loop and trimming minor repetition.

Suggestions

Add an explicit feedback loop after the ruff step: 'If `ruff check` or `ruff format --check` reports issues, fix constants.py and re-run until both pass.'

Remove the redundant restatement of the single-input requirement (e.g. 'That is the only input needed.' in step 1) since the Input section already covers it.

Consider extracting the long `gh issue create` body template into a references file (e.g. references/issue-body.md) so the main flow stays a lean overview.

Dimension	Reasoning	Score
Conciseness	Mostly lean with exact commands and a copy-paste code template, but includes minor repetition (e.g. 'That is the only input needed.' restates the Input section) and small asides that could be trimmed.	4 / 5
Actionability	Provides fully executable, copy-paste-ready guidance — the exact `gh issue create` invocation with full body, git branch command, a complete NimbusTargetingConfig code template, version-pinned ruff commands, and a drafted commit message.	5 / 5
Workflow Clarity	A clear 7-step numbered sequence with checkpoints (grep to confirm the latest entry, ruff lint and format checks), but it lacks an explicit error-recovery feedback loop (fix and re-run if ruff fails), leaving a minor validation gap.	4 / 5
Progressive Disclosure	Well-organized into Input, numbered Steps, and Reference examples with clear headers and no nested references, though the large inline issue-body and commit-message templates keep it just short of a clean overview-plus-reference split.	4 / 5
	Total	17 / 20 Passed

Description

92%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, specific description that clearly states concrete capabilities and an explicit trigger phrase for a narrow niche. The only minor gap is synonym coverage of trigger terms beyond the single quoted phrase.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'files the GitHub targeting issue, branches, adds the NimbusTargetingConfig entry, lints, and stages a drafted commit' — covering the whole end-to-end task with no real gaps.	5 / 5
Completeness	Explicitly states what it does and provides an explicit 'when' with a concrete quoted trigger phrase ('Use for "newtab trainhop targeting" requests.'), satisfying both halves clearly.	5 / 5
Trigger Term Quality	Includes the natural quoted trigger 'newtab trainhop targeting' plus domain terms (trainhop version string, Experimenter repo, NimbusTargetingConfig), but offers limited synonym/variation coverage beyond that one phrase.	4 / 5
Distinctiveness Conflict Risk	Targets a very specific niche (New Tab train-hop targeting in the Experimenter/Nimbus context) with distinct triggers, so conflict with other skills is minimal.	5 / 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: mozilla/firefox-aidev-plugins
Path: plugins/newtab/skills/trainhop-adv-target/SKILL.md
Commit: 6821231

Reviewed: 1 day 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.