Salesforce data — SfSkills domain router

Data model, data movement and data quality: migrations, bulk loads, query optimisation, deduplicating at volume, archival. Ordinary-volume duplicate cleanup and prevention use salesforce-admin; come here for hundreds-of-thousands+ dedup or third-party tools. LDV architecture uses salesforce-architect.

101 skill packages live under ${CLAUDE_PLUGIN_ROOT}/skills/data/<slug>/SKILL.md. They are not loaded — reach them by path, on demand.

Generated by scripts/build_plugin.py. Do not hand-edit.

How to find the right skill

Three mechanisms, listed in order of reliability on a fresh install. Use the first one that is available; do not stop at a guess.

1. The shipped roster (always works, no setup). Read references/skill-index.md next to this file. It lists every data skill package with a one-line gloss, generated from registry/skills.json. Scan it and pick by name.

2. The MCP server (fast, needs the sfskills-mcp server connected). Call the search_skill tool with the user's phrasing and domain: "data". It returns ranked skill ids. get_skill then returns the package contents.

3. The search CLI (fast, needs a locally built index).

python3 "${CLAUDE_PLUGIN_ROOT}/scripts/search_knowledge.py" "<the user's question>" --domain data --json

This needs vector_index/, which is not shipped — it is gitignored and must be built once per clone:

cd "${CLAUDE_PLUGIN_ROOT}" && python3 -m pip install -r requirements.txt && python3 scripts/build_index.py

If the command errors or reports Coverage: NONE, fall back to mechanism 1 rather than telling the user the topic is uncovered.

Then read the package. Open the exact ${CLAUDE_PLUGIN_ROOT}/skills/<domain>/<slug>/SKILL.md the lookup returned, plus its references/gotchas.md and references/llm-anti-patterns.md. Do not answer from this router: it is a map, not the territory.

Featured entry points

Curated starting points when the request is broad or the lookup is ambiguous. This is a shortlist, not the catalogue — the roster at references/skill-index.md has all 101.

• ${CLAUDE_PLUGIN_ROOT}/skills/data/data-model-design-patterns/SKILL.md — relationship choices, junctions, and normalisation on a multi-tenant platform
• ${CLAUDE_PLUGIN_ROOT}/skills/data/data-migration-planning/SKILL.md — sequencing, dependencies, and the dry runs that keep a cutover honest
• ${CLAUDE_PLUGIN_ROOT}/skills/data/bulk-api-and-large-data-loads/SKILL.md — batch sizing, parallel vs serial, and lock contention during a load
• ${CLAUDE_PLUGIN_ROOT}/skills/data/external-id-strategy/SKILL.md — upsert keys, idempotency, and cross-system record identity
• ${CLAUDE_PLUGIN_ROOT}/skills/data/soql-query-optimization/SKILL.md — selective filters, index usage, and reading the query plan
• ${CLAUDE_PLUGIN_ROOT}/skills/data/data-quality-and-governance/SKILL.md — ownership, standards, and the metrics that keep quality from decaying
• ${CLAUDE_PLUGIN_ROOT}/skills/data/large-scale-deduplication/SKILL.md — deduplicating at volume without a merge storm
• ${CLAUDE_PLUGIN_ROOT}/skills/data/data-archival-strategies/SKILL.md — Big Objects, off-platform archives, and storage-limit relief

Decision trees

Read the tree before activating a skill when the request could be solved more than one way, and cite the branch that decided it.

• ${CLAUDE_PLUGIN_ROOT}/standards/decision-trees/integration-pattern-selection.md — read before moving data in or out at volume
• ${CLAUDE_PLUGIN_ROOT}/standards/decision-trees/performance-tuning.md — SOQL, indexing, sharing recalculation and LDV symptoms
• ${CLAUDE_PLUGIN_ROOT}/standards/decision-trees/sharing-selection.md — read when a data model change moves record visibility

Run-time agents for this domain

Invoke one of these subagents when the ask is a whole workflow rather than a single question:

• data-loader-pre-flight — Go/no-go checklist for a planned data load
• data-migration-reconciler — Data Migration Reconciliation
• data-model-reviewer — Review a data-model domain
• duplicate-rule-designer — Design a Matching Rule + Duplicate Rule pair

Rules

1. Answer from the opened data package, never from this router.
2. Cite the skill id and, where one applied, the decision-tree branch.
3. Never claim a topic is uncovered without pasting lookup output.
4. Never deploy to an org.