research-channel
Skill14 starsChanged 3 months agoMITView on GitHub
Research and choose a marketing channel using owned performance, current public evidence, platform mechanics, audience habitat, native format, proof requirements, operator capacity, benchmarks, and freshness. Use when channel choice needs evidence rather than generic best practices.
In this repository22 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- brief-creativeSkill
- brief-product-uiSkill
- conquistadorSkill
- create-brandSkill
- create-paid-campaignSkill
- create-shortformSkill
- debate-agentsSkill
- improve-conversionSkill
- knowledge-reviewSkill
- map-user-flowSkill
- measure-growthSkill
- model-growth-funnelSkill
- optimize-searchSkill
- plan-campaignSkill
- polish-vietnameseSkill
- research-positioningSkill
- write-copySkill
- write-longformSkill
- write-outreachSkill
- write-socialSkill
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 29
Use freshness appropriate to the claim.
- Distinctive: line 61
Do not publish, contact communities, access private analytics, or change live channel settings without explicit approval.
≈ “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.
Files
Research a channel decision
Choose where and how to operate from evidence, fit, and capacity—not popularity.
Define the decision
Name the product, audience, outcome, candidate channels, time horizon, operator capacity, and what would change the choice. A channel audit without a decision becomes a fact dump.
Keep evidence types separate
Collect and label:
- owned/account performance with source, window, sample, and comparable format;
- operator-supplied experience and constraints;
- current primary platform documentation and policy;
- current observed examples or manual sampling;
- third-party benchmarks with population and comparability;
- inference and unknowns.
Use freshness appropriate to the claim. Reverify volatile formats, ranking signals, policy, pricing, and platform features at execution time. Owned results can guide account-specific choices without overriding brand, safety, or channel-fit floors.
Compare fit
For each channel assess:
- audience habitat and intent;
- native format and value delivered in-channel;
- proof available;
- distribution/access advantage;
- feedback speed;
- production and participation capacity;
- destination readiness;
- safety, policy, and reputation risk;
- primary outcome and realistic diagnostics.
Include a veto: when the product should not use the channel.
Deliver
Return:
- decision and evidence boundary;
- owned-evidence readout;
- public evidence with source/freshness notes;
- focused channel comparison;
- recommended channel, role, format, and first test;
- channels to defer and why;
- next evidence and revisit date.
Do not publish, contact communities, access private analytics, or change live channel settings without explicit approval.
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.

