sync-locales
Skill1 starsChanged 23 days agoApache-2.0View on GitHub
Review and synchronize English ALPS source documents—the Process Framework, work-system design principles, Process Descriptions, templates, examples, and guidance—with their Japanese counterparts. Report semantic mismatches and unverified pairs. Repository-development Skill.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- zombico/mojulotheir own version, first seen Oct 25, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- zombico/mojulo★ 4same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- review-alpsSkill
- design-agent-work-systemSkill
- design-process-descriptionSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 24
Read localization.yaml to identify source and supported locales.
- Distinctive: line 32
Check that work structure, Outcome judgments, contextual conditions, source identity, change effects, and uncertainty have the same meaning.
- Distinctive: line 33
Check work-system responsibilities, judgment and processing allocation, interfaces, effects, and the distinctions between design review, …
- Very specific: line 34
Use NOTE in English and 注記 in Japanese, preserving the note's attachment, scope, and informative role under the Framework's Markdown rules.
- Very specific: line 41
After confirming a counterpart's correspondence with its English source, update reviewed_source_sha256 for that pair in the manifest.yaml …
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Locale Synchronization
Purpose
Preserve the meaning, normative force, and source identity of English ALPS assets in their supported Japanese counterparts.
Outcomes
- The English source and the supported counterpart for each affected asset are identified.
- Differences in meaning, applicability, normative force, and reference identity are explicit.
- Requested translation corrections preserve source meaning, with unverified correspondence identified.
Activities & Tasks
The following Tasks are required within the requested scope.
Source and counterpart identification
- Read localization.yaml to identify source and supported locales.
- Map repository guidance and documents to
docs/locales/ja/, and distributed Skill content, including its principles and supporting references, to itsreferences/locales/ja/counterparts. - Map the working-example guide to
examples/locales/ja/and the example Skill's documents to itsreferences/locales/ja/. Shared code and fixture data keep their source identifiers. - Identify shared presentation resources and repository-development Skills using AGENTS.md; these do not require separate Plugin translations.
Meaning alignment
- Compare complete semantic units by subject, modality, action or state, object, condition, quantifier, polarity, exceptions, and scope. Assess relationships between elements as well as individual statements.
- Check that work structure, Outcome judgments, contextual conditions, source identity, change effects, and uncertainty have the same meaning.
- Check work-system responsibilities, judgment and processing allocation, interfaces, effects, and the distinctions between design review, component checks, respect for applicable requirements, authority, and limits on effects, and whole-system effectiveness. Preserve each source's independence and its application in the design Skills.
- Use
NOTEin English and注記in Japanese, preserving the note's attachment, scope, and informative role under the Framework's Markdown rules. - Preserve canonical paths, identifiers, and code literals. Localized links may target the corresponding translation when its English source remains identifiable.
- Correct affected translations when synchronization is requested, preserving unrelated work. Keep changes to the English source within the requested scope.
Correspondence evaluation
- Recheck corrected units in context, distinguishing wording differences from added, omitted, strengthened, or weakened obligations.
- After confirming a counterpart's correspondence with its English source, update
reviewed_source_sha256for that pair in themanifest.yamlof the counterpart'slocales/ja/directory, registering new counterparts there. - Report reviewed pairs, remaining mismatches and their effects, and unverified pairs. File existence, locale metadata, and format checks do not establish semantic equivalence.
Controls
The Framework governs Process meaning and Markdown presentation. The work-system principles govern the supporting configuration. Preserve the meaning and normative force of each source and its application in the design Skills. The localization configuration and AGENTS govern source roles and repository paths.
Constraints
A review-only request permits findings, not unsolicited changes. Translation review does not establish successful execution of the described work.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

