Skill Claude Code
To orchestrate parallel coding-agent farms (Claude, Codex, Copilot, Gemini, etc.) on isolated git worktrees.
not rated 360
+6 yesterday B SkillSpector: warn 32 tokens
original Apache-2.0
360Stars on the repository
189Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
Apache-2.0Licence, which decides whether bodies are shown
Skill Claude Code
To author, register, and test Rosetta hooks, add a SemanticKind, or debug a hook that won't fire.
not rated 360
+6 yesterday A SkillSpector: warn 31 tokens
original Apache-2.0
Skill Claude Code
To author, adapt, review, and validate prompts (skills, agents, workflows, rules, etc.) with brief, contracts, and a validation pack.
not rated 360
+6 yesterday A SkillSpector: warn 39 tokens
original Apache-2.0
coding
04Skill Claude Code
To implement features, fix bugs, and refactor with KISS/SOLID/DRY and systematic validation.
not rated 360
+6 yesterday A SkillSpector: warn 25 tokens
original Apache-2.0
Skill Claude Code
Rosetta CRITICAL MUST skill. MUST activate when action or its consequence is potentially dangerous, potentially irreversible, potentially destructive, or HIGH RISK. MUST activate when consequence MAYBE dangerous even if action itself seems safe. This is enterprise environment — the cost of dangerous activities is…
not rated 360
+6 yesterday A SkillSpector: pass 94 tokens
original Apache-2.0
debugging
06Skill Claude Code
To investigate errors, test failures, and unexpected behavior — root cause before fix.
not rated 360
+6 yesterday A SkillSpector: pass 19 tokens
original Apache-2.0
deviation
07Skill Claude Code
Rosetta CRITICAL MUST skill. MUST activate when intent is unclear, you cannot follow original intent, you cannot easily or reliably solve the problem, something came as SURPRISE or UNEXPECTED, you cannot bet $100 on your solution, you detect unknowns or assumptions that critically affect the solution, you detect…
not rated 360
+6 yesterday A SkillSpector: pass 81 tokens
original Apache-2.0
hitl
08Skill Claude Code
Rosetta CRITICAL MUST skill to load as Prep Step 3 Step 2 — immediately after orchestrator-contract, right before loading any workflow. Loads the session-wide approval-gate protocol governing when to stop and wait vs proceed. WITHOUT IT decisions proceed silently, violating enterprise policy. Activate it for ALL tasks…
not rated 360
+6 yesterday A SkillSpector: warn 168 tokens
original Apache-2.0
Skill Claude Code
Classify workspace mode.
not rated 360
+6 yesterday A SkillSpector: warn 10 tokens
original Apache-2.0
Skill Claude Code
Skill "init-workspace-discovery" from griddynamics/rosetta, covering dependencies.md, techstack.md and codemap.md.
not rated 360
+6 yesterday A SkillSpector: warn 10 tokens
original Apache-2.0
Skill Claude Code
Skill "init-workspace-documentation" from griddynamics/rosetta, covering agent memory.md, agent memory, preventive rules, what worked and what failed.
not rated 360
+6 yesterday A SkillSpector: warn 10 tokens
original Apache-2.0
Skill Claude Code
Extract code patterns.
not rated 360
+6 yesterday A SkillSpector: warn 10 tokens
original Apache-2.0
Skill Claude Code
Create agent rules.
not rated 360
+6 yesterday A SkillSpector: warn 10 tokens
original Apache-2.0
Skill Claude Code
Generate shell files.
not rated 360
+6 yesterday A SkillSpector: warn 10 tokens
original Apache-2.0
Skill Claude Code
Verify init completeness.
not rated 360
+6 yesterday A SkillSpector: warn 10 tokens
original Apache-2.0
Skill Claude Code
To partition large workspaces (100+ files) into scoped subagent tasks when context is insufficient.
not rated 360
+6 yesterday A SkillSpector: pass 26 tokens
original Apache-2.0
load-context
17Skill Claude Code
To load the most current project context; MUST during prep.
not rated 360
+6 yesterday A SkillSpector: pass 15 tokens
original Apache-2.0
Skill Claude Code
To rewrite text in a clear, natural, honest human tone — no AI slop, hype, or robotic phrasing.
not rated 360
+6 yesterday A SkillSpector: pass 28 tokens
original Apache-2.0
Skill Claude Code
MUST activate when you ARE an orchestrator — you are the top-level agent, you spawn subagents, you delegate work, you coordinate parallel or sequential execution. Defines delegation quality, subagent dispatch, routing, review, and ownership protocol.
not rated 360
+6 yesterday A SkillSpector: warn 54 tokens
original Apache-2.0
planning
20Skill Claude Code
To build execution-ready plans from approved intent/specs with EARS, sequenced WBS, and HITL checkpoints.
not rated 360
+6 yesterday A SkillSpector: warn 26 tokens
original Apache-2.0
post-mortem
21Skill Claude Code
Diagnose instruction defects and optionally submit Rosetta GitHub issue.
not rated 360
+6 yesterday A SkillSpector: pass 17 tokens
original Apache-2.0
questioning
22Skill Claude Code
To ask targeted clarification questions only when high-impact unknowns block safe execution.
not rated 360
+6 yesterday A SkillSpector: pass 18 tokens
original Apache-2.0
reasoning
23Skill Claude Code
To apply structured 8D meta-cognitive reasoning thinking to complex problems, then answer clearly with caveats. Must use when asked to think or reason.
not rated 360
+6 yesterday A SkillSpector: warn 34 tokens
original Apache-2.0
Skill Claude Code
To author, update, and validate functional/non-functional requirements as atomic units with user approval.
not rated 360
+6 yesterday A SkillSpector: warn 0 tokens
original Apache-2.0
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: