# Microsoft Bcquality Assets Al Query Review > Imported BCQuality skill from microsoft/skills/review/al-query-review.md - **Type:** Skill - **Install:** `agentstack add skill-louage-frw-agentic-coding-al-query-review-microsoft-skills-review-al-query-review-md` - **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior - **Seller:** [Louage](https://agentstack.voostack.com/s/louage) - **Installs:** 0 - **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills) - **Latest version:** 0.1.0 - **License:** MIT - **Upstream author:** [Louage](https://github.com/Louage) - **Source:** https://github.com/Louage/frw-agentic-coding/tree/main/assets/generated/microsoft-bcquality-assets/skills/al-query-review-microsoft-skills-review-al-query-review-md ## Install ```sh agentstack add skill-louage-frw-agentic-coding-al-query-review-microsoft-skills-review-al-query-review-md ``` Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent. ## About # AL Query review Source: microsoft/skills/review/al-query-review.md > **Bundled consumption note.** This extension packages BCQuality as VS Code chat skills and chat instructions under `assets/generated/microsoft-bcquality-assets`. Do not probe an external clone, `skills/entry.md`, `skills/read.md`, `skills/do.md`, or `knowledge-index.json` when using this bundled copy. Treat this `SKILL.md` plus the bundled BCQuality instruction files whose `Source:` paths match the active domain as the packaged knowledge surface. This note overrides upstream clone-oriented path references preserved below for provenance. # AL Query review Reviews AL source changes against the `query` knowledge domain in BCQuality. This is a leaf action skill composed by `al-code-review`. ## Source Read `knowledge-index.json` once and take entries whose `domain` is `query` across enabled layers. Open an article body only after it enters the Worklist. If the index is unavailable, discover `*/knowledge/query/*.md` by path. ## Relevance Apply READ's frontmatter matching rules against the task context. Use the target version from `app.json` when available and `[al]` for technologies. Retain conditionally applicable files only when configured; cap resulting confidence at `medium` and name every unknown dimension in the finding message. Return `not-applicable` when the input contains no Query object declaration and no Query variable method call. ## Worklist Match relevant entries against changed `query` objects, variables typed as `Query`, and the tokens `QueryType`, `dataitem`, `column`, `DataItemLink`, `SqlJoinType`, `SetFilter`, `SetRange`, `Open`, `Read`, `Close`, and `Clear`. The following targeted checks cover every current `query` article: - `SetFilter` or `SetRange` occurs after `Open()` without a new `Open()` before the next `Read()`, `set-query-filters-before-open`. - An already-open query is opened again as if that advanced the cursor, or a query variable is reused for an independent operation without `Clear` even though old filters must not carry over, `reopening-query-resets-cursor-but-keeps-filters`. Resolve layer conflicts per READ. When no query knowledge exists, emit `no-knowledge`; when knowledge exists but no article matches the changed Query usage, emit `completed` with no findings. ## Action Evaluate every worklist article against the diff's Query call order and surrounding control flow. - Emit `major` for an unambiguous Anti Pattern that can close the dataset, restart processing, or retain an unintended filter. - Emit `minor` when code contradicts a Best Practice but the resulting behavior depends on unseen control flow. - Do not emit applicability-only information. A Query article produces a finding only when the changed code violates its normative guidance. Set confidence to `high` for a locally visible call sequence and `medium` when aliases, helper calls, or missing context obscure the sequence. Domain-scoped agent findings follow DO's precision bar and remain capped at `minor`/`medium`. Provide `suggested-code` only when moving a filter before `Open()` or adding `Clear` is a complete, local, unambiguous replacement. Otherwise set `suggested-code-omission-reason`. Outcome selection follows DO: `completed`, `no-knowledge`, `not-applicable`, `partial`, or `failed`. ## Output Output conforms to the DO findings-report contract. Every finding this skill emits MUST set `findings[].domain` to `"Query"`. ## Source & license This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code. - **Author:** [Louage](https://github.com/Louage) - **Source:** [Louage/frw-agentic-coding](https://github.com/Louage/frw-agentic-coding) - **License:** MIT Install and usage instructions live in the source repository linked above. ## Pricing - **Free** — Free ## Security capabilities Automated source analysis of v0.1.0 — what this tool can access: - **Network access:** no - **Filesystem access:** no - **Shell / process execution:** no - **Environment & secrets:** no - **Dynamic code execution:** no *"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.* ## Versions - **0.1.0** — security scan: passed — Imported from the upstream source. ## Links - Listing page: https://agentstack.voostack.com/l/skill-louage-frw-agentic-coding-al-query-review-microsoft-skills-review-al-query-review-md - Seller: https://agentstack.voostack.com/s/louage - Browse the marketplace: https://agentstack.voostack.com/browse --- Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.