Skill Claude CodeCodex
Use when you need to understand, review, or curate GitHub Copilot's repository-level memory — the persistent facts Copilot reuses across CLI, cloud agent, and code review for the same repository.
Skill Claude CodeCodex
Use when monitoring a curated ecosystem source and you need to turn new items into concrete adopt/adapt/reject backlog candidates — combines GitHub-native reading with SQL triage and repository-fit scoring.
Skill Claude CodeCodex
Use when you need to run the same task across many files, components, or contexts in parallel — triggers /fleet mode for batch refactoring, mass testing, or bulk review. NOT when sequential order matters.
Skill Claude CodeCodex
Use when you need real-world implementation examples or cross-repository context — search GitHub's global code index with the built-in MCP tools and reuse the results as grounded context.
Skill Claude CodeCodex
Use when optimizing GitHub Codespaces — faster startup times, lower spend, slimmer devcontainers, right-sizing machines, or scoping prebuilds.
Skill Claude CodeCodex
Use when you have a backlog of unorganized GitHub Issues — bulk-reads, labels, prioritizes, and assigns issues at scale using Copilot's built-in GitHub MCP tools.
Skill Claude CodeCodex
Use when repeated lessons, pitfalls, or decisions should move from temporary session context into durable project guidance — curate what to keep, what to discard, and where it belongs.
Skill Claude CodeCodex
Use when you need to build a new MCP server — plan the tool surface, implement the server, register it in Copilot CLI, inspect the config, and test the tools end to end.
Skill Claude CodeCodex
Use when Copilot CLI's built-in tools do not cover a service you need — for example PostgreSQL, Redis, Jira, Slack, or an internal API — and you need to add an MCP server beyond the default GitHub MCP. NOT when the built-in tools already cover the task.
Skill Claude CodeCodex
Use when choosing which AI model to use for a task — pick the right model family and tier based on cost, speed, context needs, and reasoning depth.
Skill Claude CodeCodex
Use when a task must stay inside a narrow file or directory boundary, or when risky commands need an explicit stop rule — define the writable surface first so the agent does not drift.
Skill Claude CodeCodex
Use when delegated work needs runtime guardrails — constrain sub-agents with loop detection, circuit breakers, and escalating sandbox levels before accepting their output.
Skill Claude CodeCodex
Use when a request arrives and the right execution path is unclear — routes the work to the correct mode, agent type, model tier, and delegation pattern before implementation starts.
Skill Claude CodeCodex
Use when a task is too large or multi-domain for a single agent — assemble a specialist team, assign work via SQL tracking, dispatch with /fleet or task tool, and synthesize results.
Skill Claude CodeCodex
Use before a large Copilot task when model choice, context size, or parallelism could drive up billed usage — estimate cost pressure early and apply Copilot-specific reduction tactics before you run.
Skill Claude CodeCodex
Use when defining a public API, CLI, webhook, or SDK surface — lock the contract first so compatibility, validation, and versioning stay intentional instead of accidental.
Skill Claude CodeCodex
Use when reviewing code changes for quality, correctness, and security — runs a structured checklist with severity-rated findings.
Skill Claude CodeCodex
Use when designing prompts or agent tasks to optimize information delivery — minimize noise, maximize signal for AI agents.
Skill Claude CodeCodex
Use when a C++ failure involves memory lifetime, undefined behavior, native crashes, or debugger-only state — debug with symbols, sanitizers, and platform-native debuggers before patching symptoms.
Skill Claude CodeCodex
Use when removing old APIs, migrating to new patterns, or cleaning up legacy code — treats code as liability and follows a structured removal process.
Skill Claude CodeCodex
Use when a bug or performance issue is still fuzzy — build the fastest feedback loop first, rank the leading hypotheses, and instrument only what narrows the search.
Skill Claude CodeCodex
Use when a build, compilation, or type-check fails — diagnose the error, identify root cause, and apply the minimal fix to get green.
Skill Claude CodeCodex
Use when you have a GitHub Issue number or link and want it resolved end-to-end — reads the issue, locates the bug, applies a fix, writes tests, and opens a PR from the terminal.
Skill Claude CodeCodex
Use when starting implementation work from a PRD, spec, or set of issues — to follow a structured TDD → validate → review → commit loop.