/init-workspace-verification
Verify init completeness.
$ npx -y skills add griddynamics/rosetta --skill init-workspace-verification --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/init-workspace-verification
Context preview
The summary Claude sees to decide when to auto-load this skill.
Verify init completeness.
SKILL.md
init-workspace-verification.SKILL.mdname: init-workspace-verification
description: "Verify init completeness."
license: Apache-2.0
disable-model-invocation: true
user-invocable: false
model: claude-sonnet-5, gpt-5.4-medium
tags: ["init", "workspace", "verification", "validation"]
baseSchema: docs/schemas/skill.md
<init_workspace_verification>
<role>Senior workspace initialization auditor</role>
<when_to_use_skill> Final phase of workspace initialization. Consolidates all init-phase outputs into a single completeness audit, runs catch-up for gaps, and revalidates assumptions. </when_to_use_skill>
<core_concepts>
- All Rosetta prep steps MUST be FULLY completed, load-context skill loaded and fully executed
</core_concepts>
<process>
Run every checkpoint. Each must pass or have documented justification.
FILE EXISTENCE (non-empty, correct scope):
1. TECHSTACK.md — detected technologies, frameworks, build tools 2. CODEMAP.md — markdown headers, 3-4 levels, recursive children counts 3. DEPENDENCIES.md — direct dependencies only (project, package, version) 4. CONTEXT.md — business context only, no technical details 5. ARCHITECTURE.md — technical architecture, references CODEMAP.md, no business context 6. IMPLEMENTATION.md — current state, DRY references 7. ASSUMPTIONS.md — unknowns with forward references 8. AGENT MEMORY.md — self-defined purpose and initial entries 9. Each document includes self-definition (purpose, content type, style)
INIT INTEGRITY:
10. Init mode: exactly one of install, upgrade, plugin 11. Composite workspace: top-level docs as registries if composite 12. File inventory built before creation/update decisions 13. Shell files: frontmatter + single ACQUIRE, zero inline logic 14. load-context shell and bootstrap rule installed 15. Shells match schema — no structural deviations, no absolute paths 16. docs/PATTERNS/ with INDEX.md; each pattern in 2+ locations; INDEX.md is consistent
CROSS-FILE CONSISTENCY:
17. TECHSTACK frameworks appear in ARCHITECTURE 18. CONTEXT, ARCHITECTURE, IMPLEMENTATION complement — no duplication 19. coding.md ACQUIRED FROM KB and used as file creation reference 20. greppable headers used in all files
CONDITIONAL (if rules requested, N/A otherwise):
21. KB SEARCHED for IDE/Agent rules — agent's built-in knowledge is obsolete, verify KB was queried 22. Existing rules checked before creating new 23. Root agents file uses bootstrap.md template 24. Tech-specific agent files created 25. Local instructions with MoSCoW emphasis 26. Weekly check mechanism with release version 27. Subagents/commands initialized via KB instructions if supported
QUESTIONS:
28. HIGH priority gaps addressed via targeted questions
---
CATCH-UP: For failed checkpoints — identify owning skill, execute, re-verify.
ASSUMPTIONS REVALIDATION:
- Resolved entries: mark with evidence
- Duplicates: keep most detailed
- Forward references: verify target files exist
- New assumptions: track any discovered during verification
DEPRECATED ARTIFACTS (notify user, do NOT auto-delete):
- `agents/init-rosetta-shells-flow-state.md` — r1 state file
- Local `init-rosetta-shells-flow.md` — replaced by init-workspace-shells skill
</process>
</init_workspace_verification>
Read more
name: init-workspace-verification description: "Verify init completeness." license: Apache-2.0 disable-model-invocation: true user-invocable: false model: claude-sonnet-5, gpt-5.4-medium tags: ["init", "workspace", "verification", "validation"] baseSchema: docs/schemas/skill.md
<init_workspace_verification>
<role>Senior workspace initialization auditor</role>
<when_to_use_skill> Final phase of workspace initialization. Consolidates all init-phase outputs into a single completeness audit, runs catch-up for gaps, and revalidates assumptions. </when_to_use_skill>
<core_concepts>
- All Rosetta prep steps MUST be FULLY completed, load-context skill loaded and fully executed
</core_concepts>
<process>
Run every checkpoint. Each must pass or have documented justification.
FILE EXISTENCE (non-empty, correct scope):
1. TECHSTACK.md — detected technologies, frameworks, build tools 2. CODEMAP.md — markdown headers, 3-4 levels, recursive children counts 3. DEPENDENCIES.md — direct dependencies only (project, package, version) 4. CONTEXT.md — business context only, no technical details 5. ARCHITECTURE.md — technical architecture, references CODEMAP.md, no business context 6. IMPLEMENTATION.md — current state, DRY references 7. ASSUMPTIONS.md — unknowns with forward references 8. AGENT MEMORY.md — self-defined purpose and initial entries 9. Each document includes self-definition (purpose, content type, style)
INIT INTEGRITY:
10. Init mode: exactly one of install, upgrade, plugin 11. Composite workspace: top-level docs as registries if composite 12. File inventory built before creation/update decisions 13. Shell files: frontmatter + single ACQUIRE, zero inline logic 14. load-context shell and bootstrap rule installed 15. Shells match schema — no structural deviations, no absolute paths 16. docs/PATTERNS/ with INDEX.md; each pattern in 2+ locations; INDEX.md is consistent
CROSS-FILE CONSISTENCY:
17. TECHSTACK frameworks appear in ARCHITECTURE 18. CONTEXT, ARCHITECTURE, IMPLEMENTATION complement — no duplication 19. coding.md ACQUIRED FROM KB and used as file creation reference 20. greppable headers used in all files
CONDITIONAL (if rules requested, N/A otherwise):
21. KB SEARCHED for IDE/Agent rules — agent's built-in knowledge is obsolete, verify KB was queried 22. Existing rules checked before creating new 23. Root agents file uses bootstrap.md template 24. Tech-specific agent files created 25. Local instructions with MoSCoW emphasis 26. Weekly check mechanism with release version 27. Subagents/commands initialized via KB instructions if supported
QUESTIONS:
28. HIGH priority gaps addressed via targeted questions
---
CATCH-UP: For failed checkpoints — identify owning skill, execute, re-verify.
ASSUMPTIONS REVALIDATION:
- Resolved entries: mark with evidence
- Duplicates: keep most detailed
- Forward references: verify target files exist
- New assumptions: track any discovered during verification
DEPRECATED ARTIFACTS (notify user, do NOT auto-delete):
- `agents/init-rosetta-shells-flow-state.md` — r1 state file
- Local `init-rosetta-shells-flow.md` — replaced by init-workspace-shells skill
</process>
</init_workspace_verification>
Repo: griddynamics/rosetta
Other skills on rosetta.
- /collect-github-stats
Collect GitHub repo health/usage stats into merged JSON.
Open skill - /compress-prompt
Compress a Rosetta KB prompt artifact (skill · workflow · phase · rule · agent · template · generic) by stripping structural tautology and ineffective scaffolding while preserving every importance-bearing token. Use when the user asks to compress, shorten, tighten, densify, or
Open skill - /documentation
To write, design, review, simplify, restructure, or standardize OSS project documentation
Open skill - /merge-main
To merge main branch, exact context and instructions
Open skill - /sync-web-site
To synchronize web site with changes made to local *.md files
Open skill - /update-change-log
To synchronize CHANGELOG.md with changes made last week (mon - sun)
Open skill

