# Salesforce Flow > Routes Salesforce Flow Builder requests to the correct skill package among 63 available, covering record-triggered, screen, scheduled, and orchestration flows, bulkification, fault handling, limits, and testing. - Skill: `pranavnagrecha/salesforce-flow` (Agent Skill, multi-file: 2 files) - Install (CLI): `npx skillmds add pranavnagrecha/salesforce-flow` - Raw SKILL.md: https://api.skillmd.com/api/skills/pranavnagrecha/salesforce-flow/raw - Safety review: PASS (external: skill-scanner PASS, skillspector PASS) - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: Productivity - Tags: Bulkification, Fault Handling, Flow Builder, Orchestration, Record Triggered Flow, Salesforce, Scheduled Flow, Screen Flow - Author: PranavNagrecha (https://skillmd.com/u/pranavnagrecha) - Updated: 2026-08-22 - Page: https://skillmd.com/skills/pranavnagrecha/salesforce-flow --- # Salesforce flow — SfSkills domain router Flow Builder: record-triggered, screen, scheduled and orchestration flows, bulkification, fault handling, limits, testing. "My flow" belongs here even when salesforce-apex also names the limit. Nightly scheduling without naming code defaults here; apex takes it when code/class/Apex is named. Flow-vs-Apex choice before anything is built: admin/process-automation-selection. **63 skill packages** live under `${CLAUDE_PLUGIN_ROOT}/skills/flow//SKILL.md`. They are not loaded — reach them by path, on demand. **Generated by `scripts/build_plugin.py`. Do not hand-edit.** ## How to find the right skill Three mechanisms, listed in order of reliability on a fresh install. Use the first one that is available; do not stop at a guess. **1. The shipped roster (always works, no setup).** Read `references/skill-index.md` next to this file. It lists every `flow` skill package with a one-line gloss, generated from `registry/skills.json`. Scan it and pick by name. **2. The MCP server (fast, needs the `sfskills-mcp` server connected).** Call the `search_skill` tool with the user's phrasing and `domain: "flow"`. It returns ranked skill ids. `get_skill` then returns the package contents. **3. The search CLI (fast, needs a locally built index).** ```bash python3 "${CLAUDE_PLUGIN_ROOT}/scripts/search_knowledge.py" "" --domain flow --json ``` This needs `vector_index/`, which is **not shipped** — it is gitignored and must be built once per clone: ```bash 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///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 63. - `${CLAUDE_PLUGIN_ROOT}/skills/flow/record-triggered-flow-patterns/SKILL.md` — before-save vs after-save, entry criteria, and re-entry - `${CLAUDE_PLUGIN_ROOT}/skills/flow/flow-bulkification/SKILL.md` — the Flow equivalent of queries-in-loops, and how to see it in the debug log - `${CLAUDE_PLUGIN_ROOT}/skills/flow/fault-handling/SKILL.md` — fault paths as a design requirement, not an afterthought - `${CLAUDE_PLUGIN_ROOT}/skills/flow/screen-flows/SKILL.md` — screen composition, validation, and reactive components - `${CLAUDE_PLUGIN_ROOT}/skills/flow/scheduled-flows/SKILL.md` — schedule-triggered flows, batch limits, and the scheduled-path alternative - `${CLAUDE_PLUGIN_ROOT}/skills/flow/subflows-and-reusability/SKILL.md` — decomposing a flow before it becomes unmaintainable - `${CLAUDE_PLUGIN_ROOT}/skills/flow/flow-testing/SKILL.md` — Flow tests, coverage expectations, and what they cannot assert - `${CLAUDE_PLUGIN_ROOT}/skills/flow/flow-performance-optimization/SKILL.md` — Get Records tuning, loop cost, and CPU time inside a flow ## 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. - `${CLAUDE_PLUGIN_ROOT}/standards/decision-trees/automation-selection.md` — read FIRST — it decides whether Flow is the right tool at all - `${CLAUDE_PLUGIN_ROOT}/standards/decision-trees/flow-pattern-selector.md` — read SECOND — which kind of Flow to build - `${CLAUDE_PLUGIN_ROOT}/standards/decision-trees/async-selection.md` — read when the work should leave the transaction ## Canonical templates Do not hand-roll an idiom that already exists. Copy from `${CLAUDE_PLUGIN_ROOT}/templates/flow/` and rename in the consuming project; never edit the template in place. - `${CLAUDE_PLUGIN_ROOT}/templates/flow/RecordTriggered_Skeleton.flow-meta.xml` - `${CLAUDE_PLUGIN_ROOT}/templates/flow/FaultPath_Template.md` - `${CLAUDE_PLUGIN_ROOT}/templates/flow/Subflow_Pattern.md` - `${CLAUDE_PLUGIN_ROOT}/templates/flow/README.md` — the full list ## Run-time agents for this domain Invoke one of these subagents when the ask is a whole workflow rather than a single question: - `flow-analyzer` — Flow vs Apex routing + bulkification review - `flow-builder` — Design a Flow (any type) from a business requirement - `flow-orchestrator-designer` — Design or audit a Flow Orchestration ## Rules 1. Answer from the opened `flow` 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.