How do I install the Query skill?

Run npx skillmds@latest add williamcorrea23/query in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Query safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Query?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Query free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

williamcorrea23 (@williamcorrea23) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Query by williamcorrea23 — Agent Skill

Name: Query
Author: williamcorrea23

Query

Queries the abap_wiki knowledge base to answer questions about <COMPANY> custom ABAP code (what an object does, which tables it uses, who calls it, dependencies, bugs). Navigates index -> package -> pages; can extend the answer with the SAP <SAP_DEV_SYSTEM> system via MCP abap-fs in read-only mode, explicitly citing wiki vs. system.

File contents

Query - querying the knowledge base

Answers technical/functional questions about custom ABAP code using the wiki, with traceability via [[wikilink]].

Strategy

Read abap_wiki/index.md to identify the relevant areas.
Narrow down via abap_wiki/_packages/<DEVCLASS>.md.
Open only the necessary object pages (abap_wiki/<DEVCLASS>/<sap_type>-<NAME>.md), not the entire wiki.
Code details (L1 analysis) are inline in the same object page: scroll through the sections (Summary, Functional scope, Form analysis, Performance, Bug candidates...) and, for mains, "Program structure" (includes) and "Dependencies".
Synthesize using [[wikilink]] for every cited object.

You can also query the DB for quick structural queries:

python core/src/tools/pipeline.py progress --json

or read state/exports/progress.json.

MCP extension (`<SAP_DEV_SYSTEM>` system, read-only)

When the wiki is not enough (missing or L0 page, need current data, drift check, enriched metadata) you can query the abap-fs server:

always read-only;
cite the source explicitly: "according to [[program-X]] it uses MSEG; verified via MCP <SAP_DEV_SYSTEM>: also calls MBEW not documented in wiki";
if you discover inconsistencies (wiki says X, system says Y) report them and propose an update.

Value preservation

A precise answer of lasting interest -> propose saving it to output/reports/<topic>-<YYYYMMDD>.md.
Stable knowledge about an object/flow -> propose promotion (L1 analysis via ingest-l1, or the L2 process when available).

Tracking (operational log)

At the end of the query, record the operation in the event log (so it appears in log.md, the append-only history view - CLAUDE.md §13):

python core/src/tools/pipeline.py log-op --type query --note "<question summary>" [--package <DEVCLASS>]

One concise line, not the full answer. This is write-only on the events table (no changes to pages or raw/).

---name: querydescription: Queries the abap_wiki knowledge base to answer questions about <COMPANY> custom ABAP code (what an object does, which tables it uses, who calls it, dependencies, bugs). Navigates index -> package -> pages; can extend the answer with the SAP <SAP_DEV_SYSTEM> system via MCP abap-fs in read-only mode, explicitly citing wiki vs. system.---# Query - querying the knowledge baseAnswers technical/functional questions about custom ABAP code using the wiki,with traceability via `[[wikilink]]`.## Strategy1. Read `abap_wiki/index.md` to identify the relevant areas.2. Narrow down via `abap_wiki/_packages/<DEVCLASS>.md`.3. Open only the necessary object pages (`abap_wiki/<DEVCLASS>/<sap_type>-<NAME>.md`), not the entire wiki.4. Code details (L1 analysis) are **inline** in the same object page: scroll through the sections (Summary, Functional scope, Form analysis, Performance, Bug candidates...) and, for mains, "Program structure" (includes) and "Dependencies".5. Synthesize using `[[wikilink]]` for every cited object.You can also query the DB for quick structural queries:```python core/src/tools/pipeline.py progress --json```or read `state/exports/progress.json`.## MCP extension (`<SAP_DEV_SYSTEM>` system, read-only)When the wiki is not enough (missing or L0 page, need current data, drift check,enriched metadata) you can query the `abap-fs` server:- **always read-only**;- **cite the source explicitly**: "according to [[program-X]] it uses MSEG; verified via MCP `<SAP_DEV_SYSTEM>`: also calls MBEW not documented in wiki";- if you discover inconsistencies (wiki says X, system says Y) report them and propose an update.## Value preservation- A precise answer of lasting interest -> propose saving it to `output/reports/<topic>-<YYYYMMDD>.md`.- Stable knowledge about an object/flow -> propose promotion (L1 analysis via ingest-l1, or the L2 process when available).## Tracking (operational log)At the end of the query, record the operation in the event log (so it appears in`log.md`, the append-only history view - CLAUDE.md §13):```python core/src/tools/pipeline.py log-op --type query --note "<question summary>" [--package <DEVCLASS>]```One concise line, not the full answer. This is write-only on the `events` table(no changes to pages or `raw/`).

Frequently asked questions