Skill Claude CodeCodex
Shapes a loose intent into a well-formed prompt for a Claude Code session that can gather context, use tools, and ask questions. Matches the intent to a validated archetype, fills its slots (objective, context to gather, anchors, clarify-first questions, acceptance criteria, verification, output contract), routes the…
Skill Claude CodeCodex
Rewrites a prompt (or a rough idea) to maximize the escalation-tier model — Fable 5 today — on a hard, ambiguous, long-horizon problem. It commits to that target and applies the "un-prescribe and unleash a smarter collaborator" transform: state the problem and withhold the solution, strip scaffolding inherited from…
Agent Cursor
Checks skill folders against the repository's docs/architecture.md rules (e.g. required frontmatter, progressive disclosure, no bloated logic).
Agent Cursor
Takes clustering and architecture check outputs and scores skill overlaps, proposing explicit actions like adding anti-triggers, renaming, or archiving.
Agent Cursor
Clusters a given set of skill directories heuristically by domain, triggers, and artifact outputs. Use during skill overlap audits to reduce noise.
Skill Claude CodeCodex
This bundled skill has been replaced by the skill-studio-audit bundled skill inside the cursor-skill-studio Cursor pack per ADR-0005.
Agent Cursor
Use when investigating a skill system, workflow framework, subagent bundle, Claude-style plugin, or mixed agentic artifact and you need cheap inventory, classification, trigger extraction, and flow evidence before synthesis.
Skill Claude CodeCodex
Use when explicitly investigating a skill system, workflow framework, subagent bundle, Claude-style plugin, or mixed agentic artifact to understand its roles, trigger points, flows, and use cases.
Agent Cursor
Use proactively when auditing a project's Cursor setup for missing or conflicting subagents, rules, hooks, or MCP configuration.
Agent Cursor
Use when reviewing Cursor hook policies, command blocking behavior, file-read protection, or subagent lifecycle guard-rails.
Agent Cursor
Use when auditing Cursor MCP configuration, server trust boundaries, env interpolation, or safe installation practices.
Cursor rule Cursor
Choose the right Cursor surface: skills for knowledge and routing, rules for persistent guidance, subagents for context isolation, hooks for enforcement, and MCP for external capabilities.
Cursor rule Cursor
Delegate to subagents only for focused, context-heavy, or parallel tasks. Keep descriptions specific and prompts concise.
Cursor rule Cursor
Configure MCP servers conservatively: trust the source, keep scope narrow, prefer env interpolation, and treat example config separately from live config.
Cursor rule Cursor
Use hooks for runtime enforcement and auditing: block dangerous shell commands, protect sensitive file reads, and keep hook behavior easy to understand.
Skill Claude CodeCodex
Summarizes the cursor-companion Cursor pack and how its runtime assets relate to repo-root skills. Use after installing cursor-companion or when deciding whether to use pack subagents, rules, hooks, or a separate skill from skill-registry.json.
Agent Cursor
Use when benchmark or comparison results need a concise evidence-based analysis of what changed, what patterns matter, and which follow-up should happen next.
Agent Cursor
Use when adapting a source tree into a Cursor pack or bundled skill and you need a quick artifact matrix, source classification, or migration concerns before scaffolding.
Agent Cursor
Use when two candidate outputs should be compared blindly without knowing which skill or pack variant produced them.
Agent Cursor
Use when grading eval outputs for an authoring workflow against explicit expectations and collecting evidence into grading.json.
Agent Cursor
Use when comparing two skill source trees for package shape, trigger quality, hot-path size, supporting resources, safety, and repository fit before or alongside behavior evals.
Cursor rule Cursor
When authoring Cursor packs or installed bundled skills, keep skills, packs, rules, subagents, and docs separated by purpose rather than copying mixed source trees directly.
Cursor rule Cursor
After substantive skill or pack-authoring changes, prefer a small eval loop with explicit expectations, evidence-based grading, and review output rather than relying on prose confidence alone.
Skill Claude CodeCodex
Audit and improve existing Cursor skills and packs, and review installed or repository-first-party skill portfolios for overlap, trigger collisions, and compliance with docs/architecture.md. Covers single-skill compliance review, diagnostic improvement recommendations for an existing skill or pack, lightweight…