IN

Assistant Accountant

International Livestock Research Institute (ILRI)

FULL_TIME Nairobi, 110, KE
Posted 1 day, 20 hours ago 75 views 0 applications

Job Description

Here's a thinking process: 1. **Analyze User Input:** - User is acting as a job listing editor. - I receive raw scraped text from a job website. - Job is to extract ONLY actual job information, return clean, readable format. - Must REMOVE: social sharing, author bylines, "you may also like", navigation, comments, ads, cookie notices, duplicate text, category labels not part of job, stray numbers/formatting artifacts. - Must KEEP and STRUCTURE: job title, company, location, description, requirements, how to apply, salary, deadline, job ID, contract type. - Return ONLY the cleaned job text. No commentary, headers like "Here is the cleaned version", or markdown formatting. Just the clean job listing text. Wait, the actual prompt I receive has two parts: - First part: "You are a job listing editor... Return ONLY the cleaned job text." - Second part: "You receive a plain-text job description. Your ONLY job is to format it as clean semantic HTML." with specific HTML rules. - Then it gives me the job description text in a `

` tag. I need to figure out which format to output. The very first instruction says: "Return ONLY the cleaned job text. Do not add any commentary, headers like "Here is the cleaned version", or markdown formatting. Just the clean job listing text." But then the second section says to format as clean semantic HTML with specific tags. The last instruction says: "Return ONLY the HTML. No markdown fences, no explanation, no preamble." Let me re-read carefully. The user message starts with "You are a job listing editor..." and then has "REMOVE all of the following..." and "KEEP and STRUCTURE:" and "Return ONLY the cleaned job text." Then it says "You receive a plain-text job description. Your ONLY job is to format it as clean semantic HTML." with rules for HTML tags. Then it gives the job description. Then "Return ONLY the HTML. No markdown fences, no explanation, no preamble." This seems like two different tasks merged, but the final explicit instruction is: "Return ONLY the HTML. No markdown fences, no explanation, no preamble." And the HTML rules are given. So I should output the job description formatted as clean semantic HTML using the specified tags, preserving all original content word-for-word, no CSS classes, no inline styles, no divs, no br tags. Let me check the preservation rule: "Preserve ALL original content word-for-word — do not add, remove, summarise, or rephrase". That's tricky with the HTML formatting because I need to wrap things but keep all text exactly as is. Let's look at the job description text. It's already in HTML-ish paragraphs, but I need to convert it to the specified format:

for intro paragraphs,

for section headers,
  • for lists. No
    , no
    , no classes, no inline styles. The text has: - An introductory paragraph about ILRI - Another paragraph about ILRI's mission - Another about CGIAR membership - "About the Position" then a paragraph - "Key Responsibilities" then several

    ...: headings with

    • lists - "Requirements" then
      • list - "Terms of Appointment" then a paragraph - "How to Apply" then a paragraph then
        • list I need to output ONLY the HTML, using the specified tags. I must preserve all content word-for-word. So I'll structure it semantically. Let me outline the structure: - The text starts with three

          paragraphs about ILRI, mission, CGIAR. - Then "About the Position" followed by a

          paragraph. - Then "Key Responsibilities" followed by section. The responsibilities are grouped under sub-headings like "Accounts Payable and Payment Processing:", "Account Reconciliations and Financial Controls:", etc. Each is a

          ...: then a

          • ...
          . But the original has them as

          Accounts Payable and Payment Processing:

          then
          • ...}. I need to keep the content exactly. The rules say: Use

            for section headers (e.g. Responsibilities, Qualifications, Requirements, Education, Experience, Skills, How to Apply, Key Duties, About the Role). Use
            • for list items. But the original has sub-headings within Responsibilities. I need to decide how to handle. The rule says: "If text has no clear sections, just wrap paragraphs in

              tags". But there are clear sections. I should use

              for main sections: maybe "Key Responsibilities", "Requirements", "Terms of Appointment", "How to Apply". The sub-headings like "Accounts Payable and Payment Processing:" could be kept as

              ...: or maybe I should integrate them into the list items? But the rule says preserve ALL original content word-for-word. I cannot remove or rephrase. The sub-headings are part of the text. I think I should keep the structure as close as possible, using

              for the main section titles, and for the sub-headings within, I'll keep them as

              ...: followed by

MJC
ECHO
Your MJC Assistant

I'm ECHO, your MJC career assistant. I can help you find jobs, explore career tools, and connect with opportunities across Africa.

How was your experience with ECHO?