agentleFS
ai-search-guruai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tool/skills/new-report/SKILL.md

new-report

Skill432 starsChanged 12 days agoMITView on GitHub

Builds a one-off report on the brand and keeps it in Reports, to open, share or download.

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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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. Distinctive:

    Read only what the report needs, for the chat's brand:

    line 17
  2. Very specific:

    Use list_brands only when no brand is selected, and open_page to link Reports.

    line 26
  3. Distinctive:

    When the request gives neither, ask who the report is for and which period, together in one question.

    line 32
  4. Distinctive:

    When no template fits (an AI traffic report, say), write the report in the answer instead, in short sections with a table, so the person …

    line 39
  5. Distinctive:

    Keep it truthful: report drops as plainly as gains, and never claim one change caused another.

    line 52

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Reports

The playbook of the /new-report shortcut ("Create a report on …"): a one-off report on the brand, kept in the Reports module. The Weekly report skill is /report; this is any other report the person asks for.

Data plan

Read only what the report needs, for the chat's brand:

  1. get_overview_summary, or get_visibility_summary and get_visibility_trend: visibility and its trend.
  2. get_competitor_comparison: share of voice against the brand's competitors.
  3. get_mentions_summary: mentions and sentiment.
  4. list_citations: the pages and domains AI cites.
  5. get_ai_traffic_summary, when the report is about AI traffic.
  6. get_reports: the reports already made, so the new one doesn't repeat one from the same period.

Use list_brands only when no brand is selected, and open_page to link Reports.

Scope: the period the person names, else the last 30 days, with the brand's competitors and every platform the plan tracks.

Questions

  • When the request gives neither, ask who the report is for and which period, together in one question.

Steps

  1. Pick the report's template from what it is about: weekly_visibility for visibility, its trend and share of voice; executive_summary for leadership; competitor_benchmark for competitors; citation_sources for cited sources.
  2. Make it with build_report over the period; the app asks the person first when it should.
  3. Sum up its three most important findings in the answer, with their numbers.
  4. When no template fits (an AI traffic report, say), write the report in the answer instead, in short sections with a table, so the person keeps it with Save to Files or downloads it.

Output

The report in Reports, and three findings in the answer. Without a template: the report itself, in the answer.

Next moves

Two or three, such as opening the report in Reports, or the same report for the period before.

Don't

  • Chat doesn't email or schedule the report: the person shares or downloads it from Reports.
  • Keep it truthful: report drops as plainly as gains, and never claim one change caused another.

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.