CtrlK
BlogDocsLog inGet started
Tessl Logo

android-check-pr-translations

Audit changed Android translations in a GitHub PR.

57

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/android-check-pr-translations/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a real, well-documented extraction script and a clear two-step workflow, but it carries some redundancy in restating the schema and lacks a final verification checkpoint for the batch review. Tightening the schema restatement and adding a completion check for step 2 would lift it.

Suggestions

Remove or consolidate the trailing bullet list that re-explains the JSON schema fields already documented in the schema block.

Add a verification checkpoint to step 2, e.g. confirm every locale in `locales` and every file in `files` has been reviewed before finishing.

De-duplicate the script usage command, which appears both in the Workflow section and the Extraction Script section.

DimensionReasoningScore

Conciseness

The body is mostly efficient, but the trailing bullet list re-explains the JSON output schema fields (e.g. "locales.*.added", "files[].english") already shown in the schema block, which could be tightened.

2 / 3

Actionability

It gives an exact, copy-paste-ready command ("python3 scripts/extract_pr_strings.py <pr-number> --output /tmp/pr-strings.json"), a concrete output schema, and a named downstream skill (/translation-review).

3 / 3

Workflow Clarity

Step 1 has an explicit completion checkpoint ("This step is complete when the output includes..."), but this is a batch operation over many locales/files with no final verification that all were reviewed and no checkpoint on step 2, capping clarity at 2.

2 / 3

Progressive Disclosure

Content is organized into clear sections (Workflow, Extraction Script, output schema) with a single one-level-deep, real bundle reference ("scripts/extract_pr_strings.py") that is clearly signaled.

3 / 3

Total

10

/

12

Passed

Description

57%

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 and distinctive but stops short of listing multiple actions or providing an explicit trigger clause, so it lands in the middle of the scale. Adding a "Use when..." clause and a few natural trigger terms would raise it.

Suggestions

Add an explicit trigger clause, e.g. "Use when reviewing a GitHub PR that changes Android string resources or localized guide files."

Include natural trigger variations users might say, such as localization, i18n, locale, or strings.xml.

Name the concrete audit actions (e.g. extract changed strings, compare against English sources, flag inaccurate translations) to broaden specificity.

DimensionReasoningScore

Specificity

"Audit" is one concrete action and the domain ("changed Android translations in a GitHub PR") is named, but only a single action is given rather than a comprehensive list.

2 / 3

Completeness

It states what the skill does ("Audit changed Android translations") but the "when" is only implied by the PR context, with no explicit "Use when..." trigger clause, which caps completeness at 2.

2 / 3

Trigger Term Quality

"Android translations" and "GitHub PR" are natural terms a user might say, but common variations like localization, i18n, locale, or strings.xml are missing.

2 / 3

Distinctiveness Conflict Risk

The combination of Android, translations, and GitHub PR is a clear niche with distinct triggers, making it unlikely to fire for unrelated skills.

3 / 3

Total

9

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
kylecorry31/Trail-Sense
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.