griddynamics/docs/schemas
docs/schemas/SKILL.md
--- # Core Identity (Required) name: [Skill Name, must match parent folder name where SKILL.md file is in] description: ["Rosetta" + Brief description of WHEN and WHY to use this skill.] # Licensing & Compatibility (Optional, remove if not needed) license: [License name or reference to bundled license file] [string] [Cursor, OpenCode] [ex: MIT] compatibility: [Environment requirements (system packages, network access, etc.)] [string] [Cursor, OpenCode] [ex: 'Requires docker and kubectl'] depend
$ install --global
skillsauthnpx skillsauth add griddynamics/rosetta docs/schemasInstall 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: Apr 30, 2026, 7:41 AM14.3s7 files scanned
SKILL.md
- name:
- [Skill Name, must match parent folder name where SKILL.md file is in]
- description:
- ["Rosetta" + Brief description of WHEN and WHY to use this skill.]
- license:
- [License name or reference to bundled license file] [string] [Cursor, OpenCode] [ex: MIT]
- compatibility:
- [Environment requirements (system packages, network access, etc.)] [string] [Cursor, OpenCode] [ex: 'Requires docker and kubectl']
- dependencies:
- [Software packages required by your Skill] [string] [Claude Code] [ex: python>=3.8, pandas>=1.5.0]
- disable-model-invocation:
- [When true, the skill is only included when explicitly invoked via /skill-name. The agent will not automatically apply it based on context] [boolean] [Cursor, Claude Code]
- user-invocable:
- [Set to false to hide from the / menu. Use for background knowledge users shouldn't invoke directly. Default: true] [boolean] [Claude Code] [ex: false]
- argument-hint:
- [Hint shown during autocomplete to indicate expected arguments] [string] [Claude Code] [ex: issue-number, filename]
- allowed-tools:
- [Tools Claude can use without asking permission when this skill is active, dangerous, only keep it when you know exactly] [string] [Claude Code] [ex: Bash(git diff:*)]
- model:
- [Model to use when this skill is active] [string] [Claude Code] [ex: claude-3.5-sonnet]
- [Latest Models:
- Anthropic (claude-opus-4-6, claude-sonnet-4-6, claude-haiku-4-5), OpenAI (gpt-5.3-codex-medium, gpt-5.3-codex-high, gpt-5.4-medium, gpt-5.4-high), Google (gemini-3.1-pro-preview, gemini-3-flash-preview), Z.ai (glm-5).]
- [Model families:
- large (smart and slow) {opus, high, pro}, medium (workhorse) {sonnet, medium, glm-5, kimi-k2.5, minimax-m2.5}, small (fast, not smart) {haiku, glm-4.7, flash, mini, low} ]
- context:
- [Set to 'fork' to run in a forked subagent context] [string] [Claude Code]
- agent:
- [Which subagent type to use when context is set to 'fork'] [string] [Claude Code] [ex: code-reviewer]
- hooks:
- [Hooks scoped to this skill's lifecycle. See Hooks in skills and agents for configuration format] [object] [Claude Code]
- tags:
- ["one", "second"]
- baseSchema:
- docs/schemas/skill.md
[ONLY FOR TEMPLATE EXECUTOR: imperative bullet points, shorter lines, distinguish references to repository files vs instructions; skill/subagent names will be in context already, so just reference it. the rest of instruction folder files: rules/templates/workflows/assets/subfolders of skill/etc must be ACQUIRE'd / SEARCH'd / LIST'd to be used]
<[the_skill_name]>
<role>[Optional, Define role with specialization of the agent executing this skill, use expressive language, seniority, brilliant and short]
</role><when_to_use_skill>
[KEEP THIS VERY SHORT. Define a problem and retrospectively introspectively validation proof that this prompt actually solves the problem, explain the scenarios, conditions, or situations where this skill should be used]
</when_to_use_skill>
<core_concepts>
- All Rosetta prep steps MUST be FULLY completed, load-context skill loaded and fully executed
[Optional, KEEP THIS VERY SHORT, Describe the fundamental concepts, principles, definitions and explanations required to properly execute the skill]
</core_concepts>
<process>[Optional, KEEP THIS VERY SHORT, Every line is an ACTION (imperative verb) or a GATE (condition), No explaining what the agent already knows how to do, Define contracts/structures ONCE, DRY, No vague qualifiers, No patronizing, No tautology, No filler words]
</process><validation_checklist>
[Optional, KEEP THIS VERY SHORT, do NOT repeat the rest of the prompt, it must not just restate the same: prompt tells what to do, instead it should be proof-oriented — observable evidence that the output is correct, proof that work was done correctly]
- Checkpoint 1
- Checkpoint 2 ...
</validation_checklist>
<best_practices>
[Optional, KEEP THIS VERY SHORT, do NOT repeat, List recommended practices, tips, and guidelines for effectively using this skill]
- Practice 1
- Practice 2 ...
</best_practices>
<pitfalls>[Optional section, KEEP THIS VERY SHORT, do NOT repeat, provide unexpected mistakes, edge cases, caveats, unusual, errors, gotchas, traps, non-obvious patterns or issues to take into account or avoid]
</pitfalls> <resources>[Optional, List helpful resources, references, or related materials, do not duplicate]
- [Type of object referenced] [Reference] [Description, optional] ...
[Optional, Define what this skill produces and provide templates or examples of the output format]
- [Reference]
</[the_skill_name]>
Related Skills
griddynamics/subagent-contract
data-ai
VerifiedTrustedCommunity
Rosetta MUST skill. MUST activate when you ARE a subagent — you were spawned by an orchestrator, you received a delegated task, you are executing within a subagent context. Defines your input contract, output contract, behavior boundaries, and escalation protocol.
15SKILL.mdUpdated Apr 30, 2026
griddynamics/sensitive-data
development
VerifiedTrustedCommunity
Rosetta CRITICAL MUST skill. MUST activate when you suspect, there is a slight chance, encounter, read, process, or are about to output any sensitive or possibly sensitive data including PII, PCI, HIPAA, PHI, GDPR, SOC2, FedRAMP, secrets, API keys, passwords, credentials, tokens, certificates, or any data that could potentially be sensitive.
15SKILL.mdUpdated Apr 30, 2026
griddynamics/self-organization
development
VerifiedTrustedCommunity
Rosetta MUST skill for proactive planning, large-file restructuring (~500+ lines or 10K+ size), cleanup of stale information. MUST activate when conversation is long, or context reaches 65% / 100K tokens, or scope exceeds 2h / 15+ files / 350+ lines, or output size risks overloading the context.
15SKILL.mdUpdated Apr 30, 2026
griddynamics/self-learning
data-ai
VerifiedTrustedCommunity
Rosetta MUST skill. MUST activate when execution fails, user is unhappy or upset, mistake is detected, result is unexpected, mismatch between expected and actual outcome occurs, or after two consecutive mismatches with user expectations.
15SKILL.mdUpdated Apr 30, 2026