watch-competitors
Skill4 starsChanged 10 days agoMITView on GitHub
Watch an AI plugin's competitors over time: ranks, installs, featuring, listing rewrites, MCP tool changes and the countries that list them, side by side, and what changed since last time. Use when naming rivals in the ChatGPT, Claude or Cursor stores, comparing who's gaining in a category, or for a weekly check or monitor. Not for a one-off chart lookup.
In this repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- audit-discoverabilitySkill
- design-widgetsSkill
- find-openingSkill
- optimize-listingSkill
- plugin-stackSkill
- submit-pluginSkill
- track-launchSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 20
Start from the file's listing and competitor refs when it's there.
- Distinctive: line 21
Search matches words one at a time, so check each hit's name against the name asked for before taking it.
≈ “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.
Files
Watch competitors
Read at each step
| Step | Read |
| 1 | .agents/plugin-stack.md if present, references/data.md |
| 2 | references/pull.md |
Steps
- Fix the set. Up to 10 refs, including the user's plugin.
- Start from the file's listing and competitor refs when it's there.
- Search matches words one at a time, so check each hit's name against the name asked for before taking it.
- A plugin on two stores is two refs; its other stores are in
linked. A plugin with no listing stays out, and the report covers its competitors. - With no names, propose a set for the user to confirm. For a category, take the top of
charts_get store=<store> chart=<chart> limit=20;stores_getlists the charts. For a plugin, runlistings_searchon 1-3 nouns from what it does, thentags_get tag=<job tag from a good hit> store=<store> limit=20. - Done when each name maps to one ref.
- Pull. Done when each ref has ranks, metrics, featuring, changes and tools, or a stated gap for each.
- Report. One row per plugin, then who is gaining inside this set, judged by whether their order relative to each other changed, not raw position; beside each move list any dated change in the same window, worded as timing, not cause. Then what each changed, or "nothing changed" plainly when that's the result. With the user's plugin in the set, close on one or two next steps tied to a listed change, naming
optimize-listingfor copy oraudit-discoverabilityfor tools. Done when every claim has a date and a basis. If.agents/plugin-stack.mdexists, addwatch-competitors: <today>, top move: <move>under Runs without asking, in your own words.
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
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.