channel-presence
Skill0 starsChanged 3 months agoMITView on GitHub
Maintain the company's third-party GEO surfaces: review-site profiles, marketplace/directory listings, GitHub presence, and AI-ecosystem integration listings. Drafts copy, tracks submissions and escalations, keeps profiles current. A human posts, submits, and merges everything.
In this repository12 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- content-gap-analysisSkill
- content-generationSkill
- content-reworkSkill
- generate-hero-imageSkill
- listings-checkSkill
- retroSkill
- setupSkill
- site-readinessSkill
- target-prompts-discoverySkill
- visibility-measureSkill
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 13
Never posts, submits, merges, or sends anything: Every listing submission, escalation post, and outreach message is drafted here and …
- Distinctive: line 14
Never changes the content plan's scope.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
Channel Presence
The production skill for every channel except self-published content (which belongs to /content-generation and /content-rework). Presence channels share one shape: the deliverable is copy plus state on a surface the company doesn't control, the agent drafts, and a human performs every outward act. The records this skill operates: the listings/ roster and per-surface folders for gatekeeper surfaces (review sites, marketplaces, directories, integration listings, community lists), and content/github/ for the owned GitHub surface. Status tracking of in-flight submissions belongs to /listings-check; this skill produces and maintains the copy.
Boundaries
- Works only in channels the content plan carries (not marked
n/a), and only onapprovedrows (or upkeep of already-liveones). Proposing new rows is/content-gap-analysis's job (or the human's directly); approving them is the human's edit. - Never posts, submits, merges, or sends anything. Every listing submission, escalation post, and outreach message is drafted here and executed by a human. This is a hard constraint: these surfaces punish automation, and trust burned on them takes months to rebuild.
- Never changes the content plan's scope; that is a plan change with its own gate.
What a session does
Work arrives from two directions; handle whichever the session was invoked for:
Approved rows
For each approved row in the listings roster or a channel sub-index, produce what that surface's conventions define:
- Listings (review sites, marketplaces, directories, integration listings): write or update
profile.mdinlistings/<surface>/: the canonical copy, verified like content (facts fromstrategy/company-profile.md, competitor-adjacent claims verified by web search, writing principles applied: factual tone, durable scale claims, no promotional openings). For repo-backed listings, prepare the change as a PR into the owning repo instead. - GitHub: draft the metadata/README changes as PRs into the owning repos; for awesome-lists and registries, draft the inclusion PR or submission content against the listing's roster row, and leave the tracking to
/listings-checkonce the human opens it. - A surface the content plan opened beyond the standard set (community participation, YouTube, and the rest of the playbook): follow the conventions the opening decision defined in that surface's sub-index; the same drafting-only boundary applies.
Advance the row's status as far as agent work can take it (drafted, pr-open); the human takes it the rest of the way and the next session records the result.
Upkeep
Presence decays silently, so every run also sweeps the open channels for:
- Stale profiles: product facts that changed since a profile was last touched (compare against
strategy/company-profile.md); listings whose Last updated predates a pricing or positioning change. - Stuck submissions flagged by
/listings-check: verifying status is that skill's job; when it flags a silent or stuck row, this skill researches and records escalation paths in the listing'sprofile.md(support emails, "pending review" forum threads that staff escalate, named contacts) and drafts the escalation for human approval. Log every attempt with its date; an escalation log is what separates a tracked submission from a stale one. - Follow-ups the human completed: rows the human reports as posted/live get their status, URL, and date recorded.
Recording
Update the touched state tables (the listings roster, channel sub-indexes) in the same run; append the journal entry; refresh memory/state.md if state changed. Escalation attempts and contacts go in the listing's own folder, not the journal, so the next session on that listing starts oriented.
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.

