load-context
25Skill Claude CodeCodex
To load the most current project context; MUST during prep.
Skill Claude CodeCodex
To load the most current project context; MUST during prep.
Skill Claude CodeCodex
To rewrite text in a clear, natural, honest human tone — no AI slop, hype, or robotic phrasing.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
To build execution-ready plans from approved intent/specs with EARS, sequenced WBS, and HITL checkpoints.
Skill Claude CodeCodex
Diagnose instruction defects and optionally submit Rosetta GitHub issue.
Skill Claude CodeCodex
To ask targeted clarification questions only when high-impact unknowns block safe execution.
Skill Claude CodeCodex
To apply structured 8D meta-cognitive reasoning thinking to complex problems, then answer clearly with caveats. Must use when asked to think or reason.
Skill Claude CodeCodex
To author, update, and validate functional/non-functional requirements as atomic units with user approval.
Skill Claude CodeCodex
To consume approved requirements for planning, implementation, and validation, with traceability and HITL.
Skill Claude CodeCodex
To run systematic deep research via meta-prompting — grounded references, incremental tracking, self-validation.
Skill Claude CodeCodex
To reverse-engineer code into a spec: extract behavior and domain logic — WHAT and WHY, not HOW.
Skill Claude CodeCodex
MUST activate before execution when environment has access to databases, cloud services, S3, or similar external systems, and when assessing environment risk level. SHOULD be invoked manually before any new environment interaction.
Skill Claude CodeCodex
MUST activate on: execution failure/error, mistake, wrong/unexpected result, expected≠actual mismatch, 2 consecutive mismatches, unhappy/upset user, user asks why something failed/didn't work.
Skill Claude CodeCodex
For proactive planning, large-file restructuring (500+ lines or 10K+ size), and stale-information cleanup. 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.
Skill Claude CodeCodex
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…
Skill Claude CodeCodex
To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
To define clear, testable tech specs from requirements — target-state architecture, contracts, interfaces.
Skill Claude CodeCodex
To write thorough, isolated, idempotent tests — 80%+ coverage, external-only mocking, scenario-driven.
Skill Claude CodeCodex
To validate story readiness for a sprint or to break work into a human WBS.
Skill Claude CodeCodex
To generate, populate, and use a project codemap.
Skill Claude CodeCodex
To gather QA source artifacts from issue tracker, wiki, test management system.
Skill Claude CodeCodex
To decide architecture — alternatives, tradeoffs, committed decision with rationale, boundaries, domain-specific concerns.
Skill Claude CodeCodex
To establish what exists — affected areas, behavior, prior attempts, dependencies, data.
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: