allsource-customer
Skill4 starsChanged yesterdayApache-2.0View on GitHub
Prepare AllSource customer work through its verified MCP connector, then hand off to the product for human review and display. Use when the customer asks to prepare a tenant event timeline and show what a replay would affect before i approve anything.
In this repository25 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- allsource-incident-statusSkill
- allsource-partnershipsSkill
- ritual-fullSkill
- ritualSkill
- semantic-isaSkill
- admin-healthSkill
- allsource-data-accessSkill
- allsource-debugSkill
- allsource-incident-statusSkill
- allsource-mcp-setupSkill
- allsource-onboardSkill
- chronos-data-flow-embeddedSkill
- chronos-data-flowSkill
- chronos-durabilitySkill
- chronos-embedded-durabilitySkill
- chronos-releaseSkill
- fly-statusSkill
- mammoth-memorySkill
- ritual-fullSkill
- ritualSkill
- semantic-isaSkill
- seo-aeo-auditSkill
- allsource-prime-memorySkill
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 8
Read workflow for product inputs, domain limits and connector binding requirements.
- Distinctive: line 14
Use authoritative validation/calculation tools and explicit provenance.
≈ “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
AllSource customer workflow
Read workflow for product inputs, domain limits and connector binding requirements. Read human gate contract before any pending write or handoff.
Workflow
- Establish the customer's intended product job and permitted data. Retrieve tenant-authorised event/restart/replay evidence and prepare a read-only investigation view using existing MCP infrastructure.
- Discover the configured product connector and verify its actual tool schemas. This draft package does not supply a live endpoint or install a connector. When unavailable, prepare an unsubmitted factual summary only and state what is missing.
- Use authoritative validation/calculation tools and explicit provenance. Submit only a pending proposal, with consent for required host/server processing, revision checks and idempotency. Never treat model output as agreed data.
- Display the product review resource when supported; otherwise use a verified authenticated product review route where host rules allow it, plus useful text. Source-linked event timeline, query scope, restart proof and replay-plan differences.
- Hand control to the human. The tenant operator reviews the evidence in the product and explicitly authorises any consequential replay or infrastructure action through its separate human gate. Stop before the gated action; do not click approval/signing controls or call privileged product endpoints on their behalf.
- Retrieve the authorised versioned status/result only after the product records the decision. Report exact pending/approved/rejected/failed state; never infer completion from a tool call or chat response.
Limits
No arbitrary queries, cross-tenant payloads, secrets, replay execution, infrastructure change or subscription action from this customer review skill. Existing ingestion SDK functionality is not redefined by this review-surface amendment. The product enforces price, entitlement, identity, human authority and release state. A skill prompt does not enforce security. No arbitrary files, secrets, private portfolio data or unrelated customer records may be read.
Example trigger
“Prepare a tenant event timeline and show what a replay would affect before I approve anything”
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.

