Use when two numbers that should agree do not, a report against its source, a rollup against its detail, two systems for the same table, to find where they diverge and why.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Reconcile
The job: two numbers that should match, the places where they stop matching, and the reasons. It reads, it changes no number.
Input: the two sides, the report, query or table of each, and the number each one gives.
## Steps
1. Name the two sides: the query, the table and the filter of each, and the number each one gives.
2. Make both sides comparable: the same grain, the same period, the same filters, the same currency and unit, the same time zone.
3. Compare the totals, then split by the dimensions until a difference sits in one slice: a day, a source, a status, a key.
4. In that slice, compare row by row: the rows only on one side, and the rows on both sides with different values.
5. Name the cause: a filter, a join that drops or doubles rows, a late delivery, a type conversion, a rounding, a time zone.
6. After each cause, show what is left of the difference, and go on until it is zero or inside the agreed tolerance.
7. Say which side is right, with the proof from the source.
8. Give the result as one web page.
## Output
…
The line at the top of this page pins the label git:20261029.2e2b6c2, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_y3j3xf2d2mwzrp3r
GET https://markdownregistry.com/api/v1/resolve?ref=datawithbaraa/claude-code-data-engineering-skills/reconcile
GET https://markdownregistry.com/api/v1/blob/3a266b23e9680516650363732adf52b699adb0374cb129ff1f666faaccb8a653
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
datawithbaraa/claude-code-data-engineering-skills · skills/big-review/SKILL.md · Use once a month, or when the platform feels slow, heavy or cluttered, to review the whole platform from the query logs…
datawithbaraa/claude-code-data-engineering-skills · skills/contract/SKILL.md · Use when a new source is connected or a source changes how it delivers, to write the data contract with the source…
datawithbaraa/claude-code-data-engineering-skills · skills/cost-review/SKILL.md · Use for the monthly cost review of the platform, to see where the compute and the storage money goes, per job, pipeline…
datawithbaraa/claude-code-data-engineering-skills · skills/data-product/SKILL.md · Use when a table is served to consumers, released or changed, to build everything a consumer needs as a data product…
datawithbaraa/claude-code-data-engineering-skills · skills/docs/SKILL.md · Use after a change or a release, to write and refresh the runbook and the how-to guides of the project, so the runbook…
datawithbaraa/claude-code-data-engineering-skills · skills/impact/SKILL.md · Use before you change a table, a column or a function, to see what it is built from, what depends on it, who reads it…
datawithbaraa/claude-code-data-engineering-skills · skills/incident/SKILL.md · Use when a job run failed with an error, to walk the incident from the error to the root cause, the workaround, two…
datawithbaraa/claude-code-data-engineering-skills · skills/knowledge-refresh/SKILL.md · Use after a release, to compare the knowledge Claude Code reads, CLAUDE.md, the standards, the source pages and the…
datawithbaraa/claude-code-data-engineering-skills · skills/metadata/SKILL.md · Use when the metadata of a source has to be built or extended, to describe every table and column, the names and types…
datawithbaraa/claude-code-data-engineering-skills · skills/migration/SKILL.md · Use when an old estate of jobs and tables has to move to a new platform, to inventory it, rate it, and write the…
datawithbaraa/claude-code-data-engineering-skills · skills/pr-review/SKILL.md · Use before a pull request or another change goes in, on a file, the current diff or a branch, to review it pass by pass…
kanevry/session-orchestrator · skills/reconcile/SKILL.md · Use this skill when the user wants to reconcile learnings into rules, run /reconcile, propose rules from learnings…
kanevry/session-orchestrator · .codex-plugin/skills/reconcile/SKILL.md · Use this skill when the user wants to reconcile learnings into rules, run /reconcile, propose rules from learnings…
kanevry/session-orchestrator · .cursor/skills/reconcile/SKILL.md · Use this skill when the user wants to reconcile learnings into rules, run /reconcile, propose rules from learnings…
kanevry/session-orchestrator · .agents/skills/reconcile/SKILL.md · Use this skill when the user wants to reconcile learnings into rules, run /reconcile, propose rules from learnings…
jovesun-lab/arcgram · skills/reconcile/SKILL.md · Check that an Arcgram diagram's @spec values still match the code that implements it. Reads each node's desc "@spec…
naimkatiman/continuous-improvement · plugins/continuous-improvement/skills/reconcile/SKILL.md · Enforces Law 1 (Research Before Executing) of the 7 Laws of AI Agent Discipline. Establishes git ground truth — branch…
donald-ada/workinggenius · skills/reconcile/SKILL.md · Check the project's binding documents against the repo they describe — settled decisions, glossary terms, pinned…
