메뉴
use only in Claude Code as an explicit provider router when Graphify, code-mapper, or selective CodeQL availability must be assessed. do not install or auto-trigger for Codex GPT-5.6 Sol; native direct inspection, Plan Mode, explorer work, and subagents cover this routing without an added analyzer.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
native microsoft excel automation for windows .xlsx/.xlsm/.xls/.csv/.tsv workflows. use when chatgpt, codex, or claude code is running on windows with microsoft 365 excel installed and needs to refresh, recalculate, validate, or route a workbook through excel com automation. trigger for workbook connections, cached values, pivottables, calculation correctness, refreshing an existing power query connection, data model-aware routing, chart-ready data, no-template spreadsheet deliverables, or excel environment self-test. does not support authoring or editing power query m code, or macro execution -- see "known gaps" below. do not use for cloud execution, non-windows environments, google sheets api workflows, or machines without excel desktop installed.
Archived. Do not install or invoke for Claude Code or Codex GPT-5.6 Sol. Use the repository's scaffolds/agent-project-scaffold for the maintained scaffold or native Codex planning and execution controls.
Create a comprehensive project archive and handoff package — curated workfolder copy, evidence and state, agent context, and dark-mode HTML memo — from Claude Code or Codex projects. Use for milestone archives, cold-start continuation packages, or comprehensive handoffs; use a lightweight session-handoff skill for a short continuation note.
Generate deterministic Python import, reference, artifact, contract, catalog, OpenLineage, and explicitly authorized local CodeQL maps. Use for explicit Python blast-radius, callers, inputs/outputs, APIs/schemas, Backstage relationships, lineage, or local value/taint evidence; do not use for ordinary code search, broad repository exploration, or simple edits.
Deprecated for GPT-5.6 Sol. Use native Codex Plan Mode, with focused verification or adversarial review skills when needed.
Use when Codex is building, revising, or reviewing a frontend UI, web app screen, responsive layout, component surface, dashboard view, form flow, visual system, or no-template product interface that needs visual polish, accessibility, screenshots, or browser QA.
| name | code-intelligence |
| description | use only in Claude Code as an explicit provider router when Graphify, code-mapper, or selective CodeQL availability must be assessed. do not install or auto-trigger for Codex GPT-5.6 Sol; native direct inspection, Plan Mode, explorer work, and subagents cover this routing without an added analyzer. |
Use only as a Claude Code provider router. Choose the least expensive installed provider that can answer the question reliably, preserve evidence provenance, and verify material conclusions against current source and tests.
Do not install or auto-trigger this skill for Codex GPT-5.6 Sol. Native direct inspection, Plan Mode, explorer work, and subagents already cover the routing function without adding an analyzer.
Keep providers independent. This skill does not vendor or absorb Graphify, code-mapper-skill, or CodeQL.
code-mapper-skill — Python imports, callers, cycles, blast radius, artifacts, contracts, APIs, catalogs, and lineage.code-mapper-skill — Python security or value-flow questions when CodeQL is available and the mapper's documented trigger applies.Codebase-Memory is a benchmark candidate, not an active provider. Serena, Joern/codebadger, SCIP/Sourcegraph, Semgrep, and Aider-style maps are not part of the MVP routing surface.
scripts/preflight.py only when Graphify freshness or local capability matters. It must not parse graph.json merely to choose a route.references/routing-policy.md. Prefer the known-target fast path and do not build an index unless repeated discovery justifies it.references/freshness-policy.md before graph-backed work. Graph existence is not proof of freshness.references/provider-contract.md and record route, freshness, latency, evidence, warnings, and fallback use.code-mapper-skill, without Graphify I/O.code-mapper-skill.code-mapper-skill with selective CodeQL when available; otherwise report the limitation.The direct route to code-mapper-skill must not read or parse Graphify's graph and must not spawn Graphify. The router itself adds no runtime overhead: routing is a decision tree applied in-context, not a process. route.py is an importable policy function (decide_route), never a subprocess in the request path — there is no CLI to spawn between the request and the selected provider.
references/architecture.mdreferences/routing-policy.mdreferences/freshness-policy.mdreferences/provider-contract.mdreferences/alternatives.mdreferences/implementation-plan.mdreferences/adversarial-review.mdscripts/route.py — importable routing policy (decide_route); no CLI, not spawned at runtimescripts/preflight.py — Graphify freshness / capability check, run only when graph-backed work is in scopescripts/test_route.pyscripts/test_preflight.pyRun scripts with Python 3.10 or newer. Do not report repository work complete until the PR's required checks have concluded successfully.