Turn a verified Salesforce research packet into a concise, role-aware learning brief with clear objectives, concept sequencing, worked examples, release caveats, checks for understanding, and citations mapped to claims. Trigger keywords: teach me Salesforce, explain Salesforce concept, create learning brief, Salesforce study guide, role-based lesson. NOT for open-ended source discovery or freshness verification — use architect/salesforce-learning-research first. NOT for generating production metadata or changing an org.
Use this skill after evidence has been gathered and classified. The brief teaches a bounded Salesforce outcome without flattening product guarantees, recommendations, org assumptions, preview features, and practitioner judgment into one authoritative voice.
Input Gate
A valid input must provide:
learner role, current level, and concrete learning outcome;
an evidence or research packet with claim-to-source mapping;
release/API/product context for changing behavior;
visible gaps, contradictions, and claims that must not be taught as fact.
When evidence is missing, do not fill the lesson from memory. Route to architect/salesforce-learning-research, remain explicitly source-bounded, or return a partial brief whose unsupported sections are marked.
Brief Shape
Section
Purpose
Maximum useful scope
Outcome
State what the learner can explain or do afterward
One measurable outcome
Prerequisites
Surface concepts or access needed first
Three to five items
Mental model
Give the organizing idea that makes details coherent
One diagram/table or short explanation
Core concepts
Teach only the concepts needed for the outcome
Three to seven concepts
Workflow
Show the order of decisions or actions
Five to nine steps
Worked example
Connect the concepts in one realistic scenario
One end-to-end example
Boundaries and caveats
Preserve release, license, security, limit, and org context
Only load-bearing caveats
Knowledge check
Test understanding, not recall of wording
Three to five questions
Practice task
Let the learner apply the concept safely
One bounded exercise
Sources
Map claims to evidence
Stable citations, not a link dump
Do not reproduce the entire research packet. The packet is evidence; the brief is instruction.
Role-Aware Teaching
Adjust examples and vocabulary without changing the facts.
Learner
Emphasize
Avoid
Administrator
Business outcome, Setup model, permissions, automation interactions, safe validation
State the assumed level—foundation, practitioner, or advanced—and define unfamiliar terms at first use. Do not oversimplify away load-bearing Salesforce constraints.
Claim-to-Teaching Rules
Research state
How the brief may present it
verified-fact
State directly with a citation and applicability qualifier where material
official-recommendation
Attribute as recommended guidance, not a platform guarantee
inference
Label the reasoning and cite the facts it derives from
assumption
Present only inside the stated scenario; never generalize it
unknown
Teach the uncertainty and how to verify it
unsupported
Omit from the lesson or place in Do not teach as fact
Every numeric limit, lifecycle date, feature status, command option, and release-sensitive behavior requires a nearby citation. Stable conceptual explanations can share citations at the paragraph or section level when the mapping remains unambiguous.
Explain in Layers
Use a consistent learning progression:
Definition — what the capability is, in official/current terminology.
Purpose — which problem it solves and which problem it does not solve.
Mental model — the few relationships the learner must keep straight.
Decision points — what changes the correct approach.
Procedure or pattern — the safe sequence to use.
Example — one scenario with explicit assumptions.
Failure modes — the two or three mistakes most likely to mislead this learner.
Verification — how to prove the learner's interpretation or configuration.
For advanced learners, compress definitions and deepen tradeoffs, evidence, and exceptions. For beginners, reduce branching but retain safety and context.
Examples Without Fabrication
A worked example must state:
scenario and learner role;
target product/release assumptions;
object, metadata, or code names that are illustrative rather than claimed to exist;
expected behavior;
verification step;
limits of what the example proves.
Use sample API names such as Priority_Reason__c only when clearly labeled illustrative. Never imply that a field, permission set, package, license, or org feature exists unless the evidence packet proves it.
For procedural lessons, show a dry-run, preview, scratch-org, or read-only verification path before any write. A learning brief does not authorize production mutation.
Knowledge Checks
Prefer questions that expose misconceptions:
distinguish two neighboring concepts;
choose an approach under a changed constraint;
identify which statement is a guarantee versus a recommendation;
identify missing org/release evidence;
predict a failure mode and verification step.
Provide answers separately so the learner can self-test. Do not write trivia about UI label location unless the UI path is the learning outcome.
Recommended Workflow
Validate the packet and learner context with architect/salesforce-learning-research; preserve claim IDs and confirm role, level, outcome, time budget, and source boundary.
Select and sequence concepts from mental model to decision points to application, deferring neighboring topics that do not support the outcome.
Draft with claim discipline by mapping every material statement to evidence and retaining release, product, edition/license, API, org, and lifecycle qualifiers.
Demonstrate transfer with one worked example, explicit assumptions, failure modes, and a safe verification path.
Assess and practice with changed-constraint knowledge checks, answers, and one bounded practice task with acceptance checks and a stop condition.
Expose uncertainty and validate by listing unsupported/context-dependent claims under Do not teach as fact, running the bundled checker, and reviewing that every citation supports the claim attached to it.
Completion Checklist
One measurable learner outcome is stated
Role, level, time budget, and product/release context are explicit
Prerequisites and official terminology are clear
Facts, recommendations, inferences, assumptions, and unknowns remain distinguishable
Release-sensitive and numeric claims have nearby citations
One example declares assumptions and verification
Security, permissions, limits, and target identity remain visible where relevant
Knowledge checks test application and misconceptions
A bounded practice task is included
Unsupported claims are omitted or listed under Do not teach as fact
The brief does not authorize or perform production changes
Output and Validation
Draft with templates/salesforce-learning-brief-template.md, then run:
The checker validates structure and citation signals; a human or independent reviewer must still confirm that each citation supports the associated claim.
Related Skills
architect/salesforce-learning-research — required evidence acquisition, freshness, and contradiction handling.
Domain skill for the topic — supplies practitioner workflow and Salesforce-specific gotchas after source verification.
architect/salesforce-decision-analysis — use when the learner's real need is to choose among viable approaches rather than understand one topic.
Agent output-format skills — convert a completed brief to other artifacts without changing its claims.
See the bundled references for beginner/advanced variants, teaching gotchas, and LLM failure modes.
1---2name: salesforce-learning-brief3description: "Turn a verified Salesforce research packet into a concise, role-aware learning brief with clear objectives, concept sequencing, worked examples, release caveats, checks for understanding, and citations mapped to claims. Trigger keywords: teach me Salesforce, explain Salesforce concept, create learning brief, Salesforce study guide, role-based lesson. NOT for open-ended source discovery or freshness verification — use architect/salesforce-learning-research first. NOT for generating production metadata or changing an org."4category: admin5salesforce-version: "Summer '26+"6well-architected-pillars:7 - Reliability8 - User Experience9 - Operational Excellence10triggers:11 - "teach me this Salesforce topic using verified current sources"12 - "turn these Salesforce sources into a beginner-friendly learning brief"13 - "create a role-based Salesforce study guide with knowledge checks"14 - "explain this Salesforce feature and distinguish facts from recommendations"15 - "prepare a cited lesson for an admin developer architect or release manager"16tags:17 - learning-brief18 - teaching19 - study-guide20 - citations21 - role-aware22 - knowledge-check23inputs:24 - "Verified research packet from architect/salesforce-learning-research or equivalent source-bounded evidence"25 - "Learner role, current level, desired outcome, time budget, and preferred depth"26 - "Release, API, org, product, and license context when material"27outputs:28 - "Learner-facing brief with objectives, prerequisites, mental model, workflow, example, caveats, citations, and checks for understanding"29 - "Practice task and next-step reading tied to the learner's outcome"30 - "Explicit list of unsupported or context-dependent claims not taught as fact"31dependencies:32 - architect/salesforce-learning-research33version: 1.0.034author: Pranav Nagrecha35updated: 2026-09-0136metadata:37 source: https://skillmd.com/skills/pranavnagrecha/salesforce-learning-brief38---3940# Salesforce Learning Brief4142Use this skill after evidence has been gathered and classified. The brief teaches a bounded Salesforce outcome without flattening product guarantees, recommendations, org assumptions, preview features, and practitioner judgment into one authoritative voice.4344---4546## Input Gate4748A valid input must provide:4950- learner role, current level, and concrete learning outcome;51- an evidence or research packet with claim-to-source mapping;52- release/API/product context for changing behavior;53- visible gaps, contradictions, and claims that must not be taught as fact.5455When evidence is missing, do not fill the lesson from memory. Route to `architect/salesforce-learning-research`, remain explicitly source-bounded, or return a partial brief whose unsupported sections are marked.5657---5859## Brief Shape6061| Section | Purpose | Maximum useful scope |62|---|---|---|63| Outcome | State what the learner can explain or do afterward | One measurable outcome |64| Prerequisites | Surface concepts or access needed first | Three to five items |65| Mental model | Give the organizing idea that makes details coherent | One diagram/table or short explanation |66| Core concepts | Teach only the concepts needed for the outcome | Three to seven concepts |67| Workflow | Show the order of decisions or actions | Five to nine steps |68| Worked example | Connect the concepts in one realistic scenario | One end-to-end example |69| Boundaries and caveats | Preserve release, license, security, limit, and org context | Only load-bearing caveats |70| Knowledge check | Test understanding, not recall of wording | Three to five questions |71| Practice task | Let the learner apply the concept safely | One bounded exercise |72| Sources | Map claims to evidence | Stable citations, not a link dump |7374Do not reproduce the entire research packet. The packet is evidence; the brief is instruction.7576---7778## Role-Aware Teaching7980Adjust examples and vocabulary without changing the facts.8182| Learner | Emphasize | Avoid |83|---|---|---|84| Administrator | Business outcome, Setup model, permissions, automation interactions, safe validation | Assuming source-control or Apex fluency |85| Developer | Runtime behavior, metadata/code boundary, limits, testing, debugging, deployment | Treating every problem as code-first |86| Architect | Alternatives, NFRs, product boundaries, lifecycle, evidence, governance | A click-by-click tutorial with no tradeoffs |87| Analyst | Data meaning, joins, filters, security, freshness, interpretation limits | Presenting returned rows as complete business truth |88| Release/operations | Dependency order, gates, rollback, monitoring, audit evidence | Equating deploy success with outcome success |89| Consultant | Target identity, edition/package differences, handoff, client assumptions | Reusing one client's org facts in another context |9091State the assumed level—foundation, practitioner, or advanced—and define unfamiliar terms at first use. Do not oversimplify away load-bearing Salesforce constraints.9293---9495## Claim-to-Teaching Rules9697| Research state | How the brief may present it |98|---|---|99| `verified-fact` | State directly with a citation and applicability qualifier where material |100| `official-recommendation` | Attribute as recommended guidance, not a platform guarantee |101| `inference` | Label the reasoning and cite the facts it derives from |102| `assumption` | Present only inside the stated scenario; never generalize it |103| `unknown` | Teach the uncertainty and how to verify it |104| `unsupported` | Omit from the lesson or place in `Do not teach as fact` |105106Every numeric limit, lifecycle date, feature status, command option, and release-sensitive behavior requires a nearby citation. Stable conceptual explanations can share citations at the paragraph or section level when the mapping remains unambiguous.107108---109110## Explain in Layers111112Use a consistent learning progression:1131141. **Definition** — what the capability is, in official/current terminology.1152. **Purpose** — which problem it solves and which problem it does not solve.1163. **Mental model** — the few relationships the learner must keep straight.1174. **Decision points** — what changes the correct approach.1185. **Procedure or pattern** — the safe sequence to use.1196. **Example** — one scenario with explicit assumptions.1207. **Failure modes** — the two or three mistakes most likely to mislead this learner.1218. **Verification** — how to prove the learner's interpretation or configuration.122123For advanced learners, compress definitions and deepen tradeoffs, evidence, and exceptions. For beginners, reduce branching but retain safety and context.124125---126127## Examples Without Fabrication128129A worked example must state:130131- scenario and learner role;132- target product/release assumptions;133- object, metadata, or code names that are illustrative rather than claimed to exist;134- expected behavior;135- verification step;136- limits of what the example proves.137138Use sample API names such as `Priority_Reason__c` only when clearly labeled illustrative. Never imply that a field, permission set, package, license, or org feature exists unless the evidence packet proves it.139140For procedural lessons, show a dry-run, preview, scratch-org, or read-only verification path before any write. A learning brief does not authorize production mutation.141142---143144## Knowledge Checks145146Prefer questions that expose misconceptions:147148- distinguish two neighboring concepts;149- choose an approach under a changed constraint;150- identify which statement is a guarantee versus a recommendation;151- identify missing org/release evidence;152- predict a failure mode and verification step.153154Provide answers separately so the learner can self-test. Do not write trivia about UI label location unless the UI path is the learning outcome.155156---157158## Recommended Workflow1591601. **Validate the packet and learner context** with `architect/salesforce-learning-research`; preserve claim IDs and confirm role, level, outcome, time budget, and source boundary.1612. **Select and sequence concepts** from mental model to decision points to application, deferring neighboring topics that do not support the outcome.1623. **Draft with claim discipline** by mapping every material statement to evidence and retaining release, product, edition/license, API, org, and lifecycle qualifiers.1634. **Demonstrate transfer** with one worked example, explicit assumptions, failure modes, and a safe verification path.1645. **Assess and practice** with changed-constraint knowledge checks, answers, and one bounded practice task with acceptance checks and a stop condition.1656. **Expose uncertainty and validate** by listing unsupported/context-dependent claims under `Do not teach as fact`, running the bundled checker, and reviewing that every citation supports the claim attached to it.166167---168169## Completion Checklist170171- [ ] One measurable learner outcome is stated172- [ ] Role, level, time budget, and product/release context are explicit173- [ ] Prerequisites and official terminology are clear174- [ ] Facts, recommendations, inferences, assumptions, and unknowns remain distinguishable175- [ ] Release-sensitive and numeric claims have nearby citations176- [ ] One example declares assumptions and verification177- [ ] Security, permissions, limits, and target identity remain visible where relevant178- [ ] Knowledge checks test application and misconceptions179- [ ] A bounded practice task is included180- [ ] Unsupported claims are omitted or listed under `Do not teach as fact`181- [ ] The brief does not authorize or perform production changes182183---184185## Output and Validation186187Draft with `templates/salesforce-learning-brief-template.md`, then run:188189```bash190python3 skills/admin/salesforce-learning-brief/scripts/check_salesforce_learning_brief.py --input path/to/learning-brief.md191```192193The checker validates structure and citation signals; a human or independent reviewer must still confirm that each citation supports the associated claim.194195---196197## Related Skills198199- `architect/salesforce-learning-research` — required evidence acquisition, freshness, and contradiction handling.200- Domain skill for the topic — supplies practitioner workflow and Salesforce-specific gotchas after source verification.201- `architect/salesforce-decision-analysis` — use when the learner's real need is to choose among viable approaches rather than understand one topic.202- Agent output-format skills — convert a completed brief to other artifacts without changing its claims.203204See the bundled references for beginner/advanced variants, teaching gotchas, and LLM failure modes.
Run npx get-skill add pranavnagrecha/salesforce-learning-brief 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.
Turn a verified Salesforce research packet into a concise, role-aware learning brief with clear objectives, concept sequencing, worked examples, release caveats, checks for understanding, and citations mapped to claims. Trigger keywords: teach me Salesforce, explain Salesforce concept, create learning brief, Salesforce study guide, role-based lesson. NOT for open-ended source discovery or freshness verification — use architect/salesforce-learning-research first. NOT for generating production metadata or changing an org. It is listed under Product & Planning on SkillMD.
This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: executes scripts. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
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.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
PranavNagrecha (@pranavnagrecha) published this skill. Their other Agent Skills are listed on their SkillMD profile.