agentleFS
Sign inStart free
press-passpress-pass/journalism-skills/skills/answer-questions/SKILL.md

answer-questions

Skill2 starsChanged 7 months agoMITView on GitHub

Research and answer all unanswered questions for story leads in the pipeline. Answers questions from public sources and identifies human sources for questions requiring interviews.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use the MCP tools to get all story leads: call get_story_leads.

    line 5
  2. Distinctive:

    Read the question and decide:

    line 11
  3. Distinctive:

    Write a concise, factual answer (2-4 sentences) with specific data points when available.

    line 21
  4. Distinctive:

    After processing all questions, summarize:

    line 47

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Use the MCP tools to get all story leads: call get_story_leads.

For each story lead that has questions with status "Pending" or "Approved":

1. Classify each question

Read the question and decide:

  • Public info: The answer can be found from government data, news articles, public records, or other web sources.
  • Human source needed: The question requires a person's perspective, insider knowledge, or an interview to answer properly.

2. Answer public-info questions

For each question that can be answered with public information:

  1. Research the answer using web search, browsing official sources, and cross-referencing data.
  2. Write a concise, factual answer (2-4 sentences) with specific data points when available.
  3. Save the answer using the answer_question MCP tool with:
    • questionId: the question's ID
    • answerText: the researched answer
    • answerSourcesJson: array of {"url": "...", "title": "..."} for each source used

Prioritize authoritative sources: government databases, official reports, established news outlets.

3. Identify human sources for interview questions

For each question that requires a human source:

  1. Identify the best person to answer this question. Consider:
    • People directly involved in or affected by the story
    • Subject matter experts with relevant credentials
    • Public officials or spokespeople with relevant authority
    • Advocates or community leaders connected to the topic
  2. Research their contact information (email, phone, social media).
  3. Save the human source using the add_identified_source MCP tool with:
    • leadId: the story lead's ID
    • questionId: the question's ID (so the editor knows which question this source addresses)
    • name, title, organization, email, phone, socialHandlesJson, relevance
  4. Also save a partial answer using answer_question explaining what is known so far and that a human source has been identified for the full answer.

4. Summarize

After processing all questions, summarize:

  • How many questions were answered from public sources
  • How many human sources were identified
  • Any questions that could not be addressed

Story lead to process (omit to process all): $ARGUMENTS

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free