agentleFS
Amine-MhiriAmine-Mhiri/creatorscompanion-plugin/skills/research-then-write/SKILL.md

research-then-write

Skill0 starsChanged 6 days agoMITView on GitHub

Find posts that are working in the user's niche on Instagram, TikTok or YouTube, or look at a creator's recent posts, save the best ones as inspiration, then remake one as an original piece in the user's voice that borrows the structure, not the words. Use when the user asks what is going viral, wants ideas from a competitor or creator, or wants to remake a successful post their own way. Research and writing use credits, so it confirms before each paid step.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

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

    If a search returns a job_id, it is still running: read it later with get_viral_results or get_competitor_results.

    line 36
  2. Distinctive:

    Write a short brief in your own words: the structure to borrow, the user's own topic and angle, and what to leave behind.

    line 52
  3. Very specific:

    Call estimate_cost for the formats the user wants.

    line 54
  4. Very specific:

    Call generate_content with remix pointing at the post: { "saved_key": ...

    line 56
  5. Very specific:

    If you get a job_id, use get_generation until it is done.

    line 61

≈ “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

Research, then write

Research what works, then write something original in the user's voice. Borrow the structure (hook type, pacing, format, angle), never the wording, jokes or personal stories of the original.

1. Choose the research path

  • Viral posts in the niche: find_viral_posts with a platform (instagram, tiktok or youtube). Leave niche out to use the niche from the user's profile, or set it, plus who, keywords (up to 5), window (such as 30d) and language, when the user is specific. load_more_viral with the same job_id gets more results.
  • What tracked creators posted lately: get_feed (free), best first, optionally for one platform.
  • One tracked creator in depth: list_tracked_creators, then get_creator_report with the creator_id for their content pillars and top posts (add a post_id from the report for one post's full script and analysis). Both are free.
  • New creators to track: track_creator with one creator (an @handle or profile link, plus platform for a bare handle) or up to 5 at once in creators. untrack_creator frees a slot.
  • Creators to watch: find_competitors with a platform (plus focus, such as "real estate agents in Dubai", and language when the user is specific), then get_competitor_results with the job_id if it is still running.
  • Posts saved earlier: list_inspiration (free), optionally by status: saved (To remake), used or archived.

find_viral_posts, load_more_viral, track_creator (a new scan costs credits per creator; one scanned recently costs nothing), find_competitors and get_transcript (when the transcript is not stored yet) use credits. Their prices are in get_account. Before any of them, tell the user the cost and ask. Reading results (get_viral_results, get_competitor_results, get_creator_report, list_tracked_creators, get_feed, list_inspiration) is free.

If a search returns a job_id, it is still running: read it later with get_viral_results or get_competitor_results. A first creator scan takes a few minutes.

2. Pick what to learn from

Show the user the three to five most relevant results: a link, the hook, and in one line what made it work. Ask which one to build on.

  • To keep a post for later, save_inspiration (free) with job_id and post_key (a viral search result) or post_id (a tracked creator's post), and a note such as "copy the cold open". It returns a saved_key. unsave_inspiration removes one.
  • For a video, get_transcript gives the spoken words when the structure matters: set job_id and post_key, or a saved_key. Confirm the cost first if it is not free.

3. Remake it as an original piece

  1. Write a short brief in your own words: the structure to borrow, the user's own topic and angle, and what to leave behind.
  2. Call estimate_cost for the formats the user wants. Tell them the cost and ask before writing. Do not call generate_content until the user confirms.
  3. Call generate_content with remix pointing at the post: { "saved_key": ... }, { "job_id": ..., "post_key": ... } or { "post_id": ... }. A remix keeps that post's structure, writes new words in the user's voice and has no link fee. Put the user's angle and what to leave behind in instructions. For a post found elsewhere, send its link as source_url instead, or send the brief as idea.
  4. If you get a job_id, use get_generation until it is done.
  5. Once the remake is written, save_inspiration with the saved_key and status: "used" moves the original off the To remake list.

4. Present and save

Present the draft as the write-in-my-voice skill does (summarize when the app shows a drafts card), with one line on which post inspired it and what was borrowed. Remind the user to make it their own before posting. Offer to save it with save_to_library (free) with the draft_id and the hook they picked.

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.