CtrlK
BlogDocsLog inGet started
Tessl Logo

shogun-readme-sync

README.md(英語)とREADME_ja.md(日本語)の同期を確認・実行するスキル。README変更時に両言語版を必ず同時更新するために使用。「README更新」「README同期」「readme sync」で起動。

64

Quality

75%

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 ./skills/shogun-readme-sync/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 well-structured, concise, and actionable sync workflow with concrete translation mappings and a final validation checklist. The main gaps are the lack of an explicit re-validate-on-failure feedback loop and a pseudo rather than executable diff step.

Suggestions

Add an explicit feedback loop after Step 4: if any consistency check fails, return to Step 3 to fix and re-run the Step 4 checks until all pass.

Replace or supplement the pseudo 'Read README.md' block with an executable diff command (e.g., a grep/diff snippet counting '###' headers) so the core detection step is copy-paste ready.

Consider moving the 11-row EN→JA translation table into a references file (e.g., references/translation_table.md) and linking to it from the body to improve navigation and token efficiency.

DimensionReasoningScore

Conciseness

Lean, table-driven content that assumes Claude's competence and avoids explaining concepts Claude already knows. Not a 5 because the example diff-report block and the Overview workflow list partly echo the detailed Steps, offering minor trim opportunities; not a 3 because there is no real padding or over-explanation.

4 / 5

Actionability

Provides concrete, copy-paste-ready guidance: an 11-row EN→JA translation table, a check-item table, and explicit translation policy rules. Not a 5 because the only code block is pseudo `Read README.md` rather than executable diff logic, leaving a minor gap; not a 3 because the structured guidance is specific and actionable for an instruction-only skill.

4 / 5

Workflow Clarity

Four clearly sequenced steps with a Step 4 validation checklist (4 items), so validation is present and the destructive/batch cap does not apply. Not a 5 because there is no explicit fix→re-validate feedback loop for the batch two-file edit; not a 3 because checkpoints are present rather than missing.

4 / 5

Progressive Disclosure

Well-organized into Overview, When to Use, Instructions (Steps), and Guidelines with no nested references; self-contained with no bundle files, which is appropriate here. Not a 5 because at ~105 lines the sizeable translation table is inlined where a separate reference file could aid navigation; not a 3 because structure is clean and clearly signaled.

4 / 5

Total

16

/

20

Passed

Description

75%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 a strong, third-person statement that clearly answers both what the skill does and when to use it, with a distinct bilingual-README niche and minimal conflict risk. Its main weakness is trigger-term coverage limited to the single sync/update concept and only two high-level actions.

Suggestions

Add natural synonym trigger terms such as '翻訳', '多言語README', or '.md' so users phrasing the need as translation rather than sync still surface the skill.

Expand the 'what' beyond check/execute to one or two more concrete actions (e.g., '不足セクションの追加', 'セクション番号のズレ修正') to lift specificity.

DimensionReasoningScore

Specificity

Names the domain (EN/JA README sync) and two concrete actions ('同期を確認・実行する', '両言語版を必ず同時更新'), but the actions are high-level check/execute rather than a comprehensive list. Not a 4 because it does not list several specific actions, and not a 2 because it goes beyond naming the domain with generic actions.

3 / 5

Completeness

Explicitly answers 'what' (sync README.md and README_ja.md) and 'when' (on README change, launched via the named trigger phrases) with concrete trigger phrases. Clearly matches the 5 anchor; not downgraded since both what and when are explicit and specific.

5 / 5

Trigger Term Quality

Provides three trigger phrases ('README更新', 'README同期', 'readme sync') but they all express the same sync/update concept, missing common synonyms such as 翻訳, 多言語, or the .md extension. Not a 4 because coverage is narrow to one concept rather than good multi-term coverage.

3 / 5

Distinctiveness Conflict Risk

Targets a clear niche (two specific bilingual README files) with distinct triggers, giving minimal conflict risk with other skills. Matches the 5 anchor; no broader overlap to push it down.

5 / 5

Total

16

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
yohey-w/multi-agent-shogun
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.