steelmorgan/skills-i18n-sync
framework_eng/skills/framework-meta/skills-i18n-sync/SKILL.md
Use for managing synchronization of framework/ (RU source) → framework_eng/ (EN mirror). Helps check status, run manual translation, or diagnose commit blocking.
$ install --global
skillsauthnpx skillsauth add steelmorgan/1c-agent-based-dev-framework skills-i18n-syncInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 13, 2026, 5:53 AM84.1s1 file scanned
SKILL.md
- name:
- skills-i18n-sync
- description:
- Use for managing synchronization of framework/ (RU source) → framework_eng/ (EN mirror). Helps check status, run manual translation, or diagnose commit blocking.
skills-i18n-sync — RU→EN skill synchronization
framework/ (RU, source of truth) → framework_eng/ (EN, automatic mirror). IDE symlinks point to framework_eng/. Never edit framework_eng/ directly.
When to use
| Trigger | Action |
|---------|--------|
| You changed any file in framework/ (except README.md) | Immediately synchronize the changed file via /sync-skills <path> |
| You see a dirty or pending status in the registry | Run /sync-skills before using the skill |
| A commit is blocked by a translation error in the hook | Run python3 tools/sync-skill.py --all, then retry the commit |
| A new file was added to framework/ | Run /sync-skills <path> to create the EN version |
| You need to check the state of all skills | Run /sync-skills check |
Commands
/sync-skills check
Shows a table of statuses for all files:
✓ synced— RU and EN are synchronized○ pending— the EN version has not been created yet✗ dirty— RU was changed, EN is outdated! error— the last translation failed with an error
python3 tools/sync-skill.py --check
/sync-skills
Synchronize all pending and dirty files:
python3 tools/sync-skill.py --all
/sync-skills <path>
Synchronize a specific file:
python3 tools/sync-skill.py framework/skills/bsl-practices/coding-standards/SKILL.md
/sync-skills init-all
Initial synchronization — translate everything that still lacks an EN mirror. Run once during setup or after adding a large batch of files:
python3 tools/sync-skill.py --init-all
Rules for agents
-
After any change to a file in
framework/— run synchronization immediately. Do not wait until commit: the hook will block it if the EN version is missing. -
Exception:
README.mdfiles are not translated or synchronized. -
Before using the skill — make sure its status is
synced. If it isdirty, the data in.claude/skills/is outdated. -
framework_eng/is read-only; never write there directly. -
If RU and EN content conflict — RU always wins (source of truth).
How the pre-commit hook works
git commit
↓
.git/hooks/pre-commit runs
↓
Finds staged files in framework/ (except README.md)
↓
Invokes: python3 tools/sync-skill.py <list of files>
↓
sync-skill.py calls the Codex CLI (gpt-5.1-codex-mini) to translate each file
↓
Writes the result to framework_eng/ (mirror path)
Updates .skills-sync-state.json
↓
Hook adds framework_eng/ files and state to the commit (git add)
↓
Commit continues (RU + EN always in the same commit)
↓
On error: BLOCKS the commit with instructions on how to fix
Synchronization registry
The .skills-sync-state.json file at the repo root stores the statuses and hashes of each file.
depends_on: []
Related Skills
steelmorgan/source-of-truth
testing
VerifiedTrustedCommunity
MUST use BEFORE making a judgment about the cause of a conflict, a test failure, or an artifact dispute. Defines the end-to-end verification method L1→L6 and the classification of the first broken link.
69SKILL.mdUpdated Jun 13, 2026
steelmorgan/skill-learning
development
VerifiedTrustedCommunity
MUST use AFTER a work cycle with ≥2 iterations (wrote → error → fixed → success). Provides the retrospective procedure and the format for recording practice/anti-patterns in references/learned-patterns.md or {project}/.context/learned-patterns.md.
69SKILL.mdUpdated Jun 13, 2026
steelmorgan/rlm-workflow
tools
VerifiedTrustedCommunity
MUST use WHEN you are writing reusable knowledge into RLM (pattern / architectural decision / stable domain fact) OR reading it before a non-trivial task/solution in the domain. Provides the breakdown of native-push vs RLM-pull, tools for writing and reading RLM, H-MEM levels, and hygiene.
69SKILL.mdUpdated Jun 13, 2026
steelmorgan/quick-fix
testing
VerifiedTrustedCommunity
MUST use WHEN the task is classified as simple (< 20 lines, 1 file, no new metadata objects, no architectural decisions). Provides a short cycle of 3 steps with a guard on the self path and mandatory verify.
69SKILL.mdUpdated Jun 13, 2026