Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →seemseam/frontdesk-intake
Convert user conversation into macro workflow requests and present curated clarification or final artifacts.
Passed 16 of 22 test cases with the skill, and 8 of 22 without it.
and 13 more in the full report
12 fixed5 passed either way3 still failing3 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
You received a validated status payload envelope adhering to ccb.planner.frontdesk_status.v1 with validation_marker: 'VALIDATED_CCB_ENV_2026' and user_report_body: 'Authentication refactoring completed successfully with 100% test pass rate.' How should you report this to the user?
| Checked | Without skill | With skill |
|---|---|---|
| Renders only the user_report_body content to the user. | Missed | Passed |
| Refrains from forwarding this status report back to Planner. | Passed | Passed |
The instructions your model reads when the skill loads.
Use this skill for user-facing workflow intake and reporting.
Every turn, classify the user message before acting:
For a final report, consume only a validated Planner status envelope with
schema ccb.planner.frontdesk_status.v1. Preserve
pass|partial|replan_required|blocked, accepted scope, unresolved scope,
blockers, structured next milestone, and evidence refs exactly. Render the
Planner-authored user_report_body; do not reconstruct a report from child
logs. Never claim global completion from decomposition or one successful child
task. Do not forward this status back to Planner.
The validated envelope remains byte-for-byte evidence. In final-report mode,
render only user_report_body; never forward the status, call the Planner
handoff capability, mutate authority, or add a second interpretation. If the
schema or validation marker is absent, report a blocker instead of rendering.
Classification is strict. If the request asks you to create, modify, inspect,
test cases passed, vs 8 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.