nerd-smart
01Skill Codex
Use when a focused, ambiguous, or multi-goal request needs alignment on intention, endpoint, scope, or working role before substantive work.
Skill Codex
Use when a focused, ambiguous, or multi-goal request needs alignment on intention, endpoint, scope, or working role before substantive work.
Skill Codex
Use when answering, explaining, comparing, or guiding conversationally, or when generating and choosing among possible directions, before creating artifacts or mutating state.
Skill Codex
Use when establishing why behavior is broken, unexpected, or inconsistent and reporting a confirmed, probable, or unknown cause without performing repair.
Skill Codex
Create, simplify, compact, expand, split, or coordinate human-friendly documentation from established information without changing product behavior.
Skill Codex
Use when implementing an approved written plan or confirmed coding outcome in an existing repository, including requests to build, add, change, or write code.
Skill Codex
Use when discovering codebase facts, context, patterns, constraints, or unknowns through focused, incremental, read-only investigation without diagnosing a failure or modifying state.
Skill Codex
Use when explicitly invoked or when a concrete latency constraint requires minimizing wall-clock agent time without reducing accuracy.
Skill Codex
Use when the user explicitly asks for Nerd Loop or wants a cost-proportional, behavior-aware task-completion controller that selects the cheapest adequate loop profile and iterates toward an explicit Definition of Done through focused work, automatic verification, and bounded stopping rules.
Skill Codex
Use when the installed Nerd hook activates behavioral memory, the user invokes $nerd-memory or /nerd-memory, or Nerd Smart selects longitudinal behavioral advice.
Skill Codex
Use when observing and rechecking an ongoing process or state until a requested condition, deadline, or meaningful change occurs without mutation.
Skill Codex
Use when examining a confirmed code, pull request, module, application, endpoint, dependency, or configuration scope for vulnerabilities, unsafe behavior, or exploitability.
Skill Codex
Use when turning a confirmed outcome into actionable, ordered implementation steps with file-level changes and proof, then stopping before execution.
Skill Codex
Review existing code, documents, products, tests, and hotfixes with relevant companion skills and evidence-backed, severity-ranked findings, without editing reviewed content.
Skill Codex
Use when explicitly invoked, when reducing agent-workflow cost, or when a concrete deliverable requires no narration, final only, code only, findings only, or minimal output.
Skill Codex
Use when a request needs fast alignment on outcome, endpoint, or scope before handing work to exactly one endpoint route, including ambiguous or materially multi-goal requests.
Skill Codex
Use when defining requirements, observable behavior, boundaries, or system design and stopping before implementation planning or execution.
Skill Codex
Use when code, integrations, automation, infrastructure, or runtime behavior is broken, unexpected, inconsistent, or probably misimplemented and the user wants diagnosis, root-cause analysis, repair, or hotfix review.
Skill Codex
Use only when explicitly invoked for a concrete output or authorized file or code change where latency is worth reduced exploration, accuracy, completeness, and proof breadth.
Skill Codex
Use when the installed Nerd hook activates persisted Context, the user invokes $nerd-context or /nerd-context, or Nerd Smart resumes an exact contextid supplied in the current activation.
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: