for paragraphs,

for section headers (e.g. Responsibilities, Qualifications, Requirements, Education, Experience, Skills, How to Apply, Key Duties, About the Role). Use

• for list items. No CSS classes, no inline styles, no
  s, no
  . Preserve ALL original content word-for-word — do not add, remove, summarise, or rephrase. So we must keep exactly the text as given, but we need to format it accordingly. We need to identify sections and map to appropriate headers. The instruction says use

  for section headers (e.g. Responsibilities, Qualifications, Requirements, Education, Experience, Skills, How to Apply, Key Duties, About the Role). So we should use

  for each header that appears. The original text includes headings like "Job Description", "Responsibilities", "Data Collection and Analysis", "Information and Business Advice", etc. But we need to use

  for section headers like "Responsibilities", "Qualifications", "Requirements", "Education", "Experience", "Skills", "How to Apply", "Key Duties", "About the Role". However the original text does not have those exact words as headings? It has "Job Description", "Responsibilities", "Data Collection and Analysis", etc. The instruction says use

  for section headers (e.g. Responsibilities, Qualifications, Requirements, Education, Experience, Skills, How to Apply, Key Duties, About the Role). So we should map the headings we have to these generic categories? Probably we should use

  for each distinct section header present, but we must preserve original content word-for-word. So we cannot rename headings; we must keep the original heading text. But we must use

  tags for section headers. So we can wrap each heading in

  . For example, the text has "

  Responsibilities

  " and also other headings like "

  Data Collection and Analysis

  ", etc. We need to preserve them but use

  instead? The instruction says use

  for section headers (e.g. Responsibilities, Qualifications, Requirements, Education, Experience, Skills, How to Apply, Key Duties, About the Role). It doesn't say we must replace all headings with

  ; but we should use

  for section headers. So we can replace the existing heading tags with

  . But we must preserve the content word-for-word, including the heading text. So we can output

  Responsibilities

  etc. However the original had

  Responsibilities

  . Should we keep the "h1"? The instruction says use

  for section headers. So we should output

  Responsibilities

  instead of

  . That changes the tag but preserves the text inside. That's allowed because we are formatting, not altering content. The content inside remains same. We also have headings like "Data Collection and Analysis", "Information and Business Advice", etc. Those are subheadings within responsibilities. Should we treat them as separate sections? Probably we should keep them as they appear, but they are not top-level section headers like Responsibilities. The instruction only mentions using

  for section headers like Responsibilities, Qualifications, etc. It doesn't say we must use

  for every heading; but we can use

  for each distinct section header. However we must preserve original content word-for-word, so we cannot rename them. So we can output

  Data Collection and Analysis

  etc. That would be okay. But we also have

  tags in original. We need to replace them with

  . Also there are

  tags for competencies list items? Actually the original has

  empty after each competency? Let's examine. The original HTML snippet includes:

  Responsibilities

  Data Collection and Analysis

  ...

  etc. Then later:

  Information and Business Advice

  ...

  ... And later:

  Document Preparation

  ...

  ... And later:

  Insights and Reporting

  ...

  ... And later:

  Customer Relationship Management / Account Management

  ...

  ... And later:

  Financial Advice

  ...

  ... And later:

  Sales

  ...

  ... And later:

  Operational Compliance

  ...

  ... And later:

  Personal Capability Building

  ...

  ... Then after that there is a paragraph with Skills etc. Then there is a list of skills separated by commas? Actually it's a long string: "Action Planning, Client Management, Computer Literacy, ..." all in one paragraph. That is not a list; but we could treat it as a list? The instruction says use

  • for list items (duties, requirements, qualifications, skills). So we need to convert any list items into
    • . The original does not have bullet points; it's just a comma-separated list. Should we convert that into
      • items? The instruction says use
        • for list items (duties, requirements, qualifications, skills). So we should convert the skills list into
          • items. But we must preserve the content word-for-word. If we split the comma-separated list into separate
          • items, we are altering the content (adding line breaks and
          • tags). However the instruction says preserve ALL original content word-for-word — do not add, remove, summarise, or rephrase. But we are allowed to wrap in
            • for list items. That implies we can transform the comma-separated list into
              • items, but we must keep the same words. So we can take the text "Action Planning, Client Management, Computer Literacy, Data Analysis, Database Reporting, Data Compilation, Data Interpretations, Evaluating Information, Management Reporting, Numerical Aptitude, Oral Communications, Professional Presentation, Report Review, Sales Software, Statistical Analysis Techniques" and split by commas and spaces, then output each as
              • Item
              within
              . That would be adding
              and
              • tags but not altering the words. That's permissible. Similarly for competencies list: they have headings like "Builds Networks
                Business Insight
                ..." Actually the original shows:

                Competencies

                Business Insight
                Communicates Effectively
                Customer Focus
                Decision Quality
                Ensures Accountability
                Manages Complexity
                Plans and Aligns
                But the snippet shows:

                Competencies

                Business Insight
                Communicates Effectively
                Customer Focus
                Decision Quality
                Ensures Accountability
                Manages Complexity
                Plans and Aligns
                Actually the snippet shows:

                Competencies

                Business Insight
                Communicates Effectively
                Customer Focus
                Decision Quality
                Ensures Accountability
                Manages Complexity
                Plans and Aligns
                But the earlier part shows:

                Skills

                Action Planning, Client Management, ... (comma separated) Then later:

                Competencies

                Builds Networks
                Business Insight
                Communicates Effectively
                Customer Focus
                Decision Quality
                Ensures Accountability
                Manages Complexity
                Plans and Aligns
                So we have a list of competency items each followed by
                empty? Actually they have
                after each competency? The snippet shows "Builds Networks
                " then a line break? Actually it's "Builds Networks
                " then next line "Business Insight
                " etc. So the competency items are just plain text with an empty

                tag after them. That seems odd. But we need to preserve content word-for-word. So we must keep "Builds Networks

                " exactly as is. But we need to use

                for section headers. "Competencies" is a section header, so we should wrap it in

                Competencies

                . Then the following lines are the competency items; they are not headings but plain text with
                tags. Should we keep them as is? Probably yes, but we need to wrap them in

                maybe? The instruction says use

                for introductory paragraphs and general text. Use

                • for list items. So we could treat each competency item as a list item? But they are not bullet points; they are just text with
                  tags. The instruction says preserve all original content word-for-word, do not add, remove, summarise, or rephrase. So we must keep the
                  tags as they appear. But we also need to use

                  for section headers. So we can output:

                  Competencies

                  Builds Networks
                  Business Insight
                  ... But that would be mixing tags. That's okay. But we also have "Skills" section with a long comma-separated list. That should be wrapped in
                  • items. But we must preserve the original content word-for-word. The original content includes the commas and spaces. If we split into
                  • items, we are adding line breaks and
                  • tags, but not altering the words. That's allowed. Now we need to produce clean semantic HTML with only

                    ,

                    ,

                    ,
                    • . No other tags. So we cannot use

                      ,

                      ,

                      ,

                      ,
                      , etc. So we must replace all heading tags with

                      . Also we must not use any inline styles or classes. So we need to strip the style attributes and class attributes. The original has many style attributes like "style="text-align:left"". We must remove them entirely. Also class attributes like "class="emphasis-2"". Remove them. We must preserve all original content word-for-word, but we are removing style attributes and class attributes. Does that count as altering content? The instruction says preserve ALL original content word-for-word — do not add, remove, summarise, or rephrase. Removing style attributes might be considered removing content? The style attribute is part of the markup, not visible content. The visible content is the text. The instruction likely refers to visible text content, not markup attributes. It says "Preserve ALL original content word-for-word — do not add, remove, summarise, or rephrase". That probably means the visible text, not the markup. So we can remove style attributes and class attributes as they are not part of the content. That should be fine. We must also remove any empty paragraphs

                      etc. But those are empty; we can just output nothing? The instruction says preserve all original content word-for-word, but empty paragraphs contain no text, so we can omit them. That's okay. We must also remove any stray numbers or formatting artifacts. There's a stray " " (non-breaking space) maybe. We can ignore. Now let's parse the original text and produce cleaned HTML. First, the initial part:

                      Let's Write Africa's Story Together!

                      Old Mutual is a firm believer in the African opportunity and our diverse talent reflects this.

                      Job Description

                      Then there is a paragraph: "Provides specialist knowledge and executes account development strategies and sales business plans in order to achieve medium-sized sales targets." This is inside

                      but we can just output as a paragraph. Then there are many headings and paragraphs. We need to output only the cleaned job text, not the initial promotional text? The instruction says "Return ONLY the cleaned job text." The job description includes the promotional text? The raw scraped text includes some promotional intro "Let's Write Africa's Story Together!" and "Old Mutual is a firm believer...". Those are part of the job posting? Probably they are part of the job description. The instruction says "Your ONLY job is to format it as clean semantic HTML." So we must output the entire HTML with all content, preserving everything. So we must include those introductory paragraphs as well. Thus we need to output HTML that includes: - The first paragraph with bold text "Let's Write Africa's Story Together!" (note the ' is an apostrophe escaped; we should output as is? The original has '? Actually it's ' which is apostrophe. In HTML we can output as Let's (the apostrophe). But we must preserve word-for-word, including the HTML entity? The original shows ' which is the HTML entity for apostrophe. Should we output the literal apostrophe or the entity? The instruction says preserve ALL original content word-for-word. The entity is part of the content? It is markup, not visible text. The visible text is "Let's Write Africa's Story Together!"? Actually the original shows "Let's Write Africa's Story Together!" inside tags. That is the visible text with HTML entity for apostrophe. If we output plain text, we could output "Let's Write Africa's Story Together!" but that would be rephrasing (replacing entity with character). The instruction says preserve word-for-word, but does not specify about HTML entities. Probably we should output the literal characters as they appear in the source? The source uses ' which is an entity; but the visible text is "Let's". In the HTML, the entity is used to represent the apostrophe. If we output the entity, it's still the same representation. But the instruction says "preserve ALL original content word-for-word". The entity is part of the content? It's markup, not visible text. I think we can output the literal apostrophe character, as that is the same content. But to be safe, we could output the entity as is: "Let's Write Africa's Story Together!". That would be preserving the exact string including the entity. However that would be weird in HTML; the browser would render the apostrophe anyway. But we are not using any markup to render; we are just outputting HTML. If we output "Let's", the browser will render as "Let's". That's fine. So we can keep the entity. But the instruction says "Return ONLY the HTML." So we can output the entity. Now we need to produce the HTML. Let's outline sections: 1. Intro paragraph with bold text:

                      Let's Write Africa's Story Together!

                      (but we need to preserve the tags? The original has Let's Write Africa's Story Together!. We need to preserve the content word-for-word, including the tags? The instruction says preserve ALL original content word-for-word — do not add, remove, summarise, or rephrase. The tags are markup; they are not visible content. But they are part of the original markup. Should we preserve them? The instruction says "Preserve ALL original content word-for-word — do not add, remove, summarise, or rephrase". That likely includes the markup as well? But the instruction also says "Use

                      for introductory paragraphs and general text". So we need to output

                      for paragraphs. The original has

                      Let's Write Africa's Story Together!

                      . We need to output a

                      that contains the same visible text, but we can drop the span and b tags? That would be removing markup, which might be considered removing content? The instruction says "do not add, remove, summarise, or rephrase". Removing the tag is removing markup, but not visible content. I think it's allowed because we are formatting, not altering visible text

  Translated by AI — may not be perfect

  Show original