ecosystem-brief
Skill97 starsChanged 33 days agoApache-2.0View on GitHub
Produce a decision-ready ecosystem briefing from fresh governed evidence without claiming publication.
In this repository94 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- runxSkill
- adopt-skillSkill
- agencySkill
- answer-from-docsSkill
- attention-reviewSkill
- audit-receiptSkill
- brand-voiceSkill
- business-opsSkill
- chargeSkill
- chief-of-staffSkill
- cold-outreachSkill
- content-pipelineSkill
- contract-drafterSkill
- conversation-replySkill
- conversation-reviewSkill
- crm-cleanupSkill
- cve-auditSkill
- data-storeSkill
- data-subject-requestSkill
- deep-researchSkill
- diagnose-skill-runSkill
- dispute-respondSkill
- extractSkill
- ghostwriteSkill
- github-pr-commentSkill
- github-pr-reviewSkill
- github-syncSkill
- google-analyticsSkill
- google-calendarSkill
- google-search-consoleSkill
- governed-outboundSkill
- helpdeskSkill
- incident-commanderSkill
- issue-intakeSkill
- issue-to-prSkill
- issue-triageSkill
- knowledge-routerSkill
- lead-enrichmentSkill
- lead-qualifySkill
- least-privilegeSkill
- ledgerSkill
- list-hygiene-judgeSkill
- marketplace-invokeSkill
- meeting-followupSkill
- mock-chargeSkill
- mock-paySkill
- mock-refundSkill
- moltbookSkill
- n8n-handoffSkill
- nitrosendSkill
- nws-weather-forecastSkill
- open-meteo-weather-forecastSkill
- operator-inboxSkill
- ops-deskSkill
- organic-growthSkill
- policy-authorSkill
- postmortem-makerSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 27
Use ecosystem-brief for daily or periodic monitoring of a bounded market, technology, project set, or competitive surface.
- Distinctive: line 61
Do not disguise an old event as a new signal because an article was reposted.
- Distinctive: line 63
Do not claim a provider was monitored continuously or a brief was delivered.
≈ “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
Ecosystem Brief
Produce one time-bounded update on what changed, why it matters, and what an operator should do with that information. This is the focused monitoring variant of the research and content chain: a sharp decision brief, not a generic news roundup or an article padded from weak signals.
Lead with the operational implication. Then show the verified change, sources, inference, uncertainty, and recommended posture. Connect a signal to product, trust, distribution, positioning, or catalog work only when the evidence supports that connection.
Composes
<!-- Generated from the native execution closure; run pnpm core-skills:composes:generate. -->ghostwrite#draftresearch#research
When to use it
Use ecosystem-brief for daily or periodic monitoring of a bounded market,
technology, project set, or competitive surface. Use deep-research when the
question is durable and needs a fuller decision memo. Use content-pipeline
when the principal outcome is reader-facing publication rather than operator
awareness.
How the chain works
- Supply governed source packets and an explicit
as_oftime. - A deterministic freshness gate rejects missing provenance, future-dated observations, and sources older than the declared window.
researchverifies citations and separates evidence from inference.ghostwriteturns the ready packet into a concise brief whose claims remain bound to admitted source digests.
The brief remains local. A Slack, email, social, or publication skill must own any outward notification and its approval, idempotency, and provider readback.
Inputs and result
objectiveidentifies the monitoring question or decision.source_packetsprovide governed evidence.as_ofis the explicit evaluation time;max_age_hoursdefines freshness.audience,channel,domain,operator_context, andtarget_entitiesscope relevance without becoming evidence themselves.
The result includes the freshness report, citation-validated research packet,
and evidence-bound brief. It returns needs_more_evidence when no source
survives freshness and provenance checks, and not_worth_publishing when the
change is real but offers no useful posture.
Stop conditions
- Reject stale, future-dated, malformed, or untraceable source packets.
- Do not disguise an old event as a new signal because an article was reposted.
- Carry meaningful uncertainty and conflicting evidence into the brief.
- Do not claim a provider was monitored continuously or a brief was delivered.
- Route external distribution to the owning provider skill with the exact brief and source bindings.
Example
Three fresh official sources show that a framework changed its extension model.
The brief can explain the verified change, infer which integrations may be
affected, and recommend inspect, adopt, or wait. A stale opinion post may inform
background only if admitted under policy; it cannot be presented as the current
event, and a true change with no bearing on the operator can end as
not_worth_publishing.
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.

