team-feedback
Skill0 starsChanged 18 days agoMITView on GitHub
Format feedback for the Solum platform team — new rules (eligibility, insurance, copay), bug reports, and feature requests — using the WHEN/THEN/Example framework with Trading Partner IDs. Use this skill when the user wants to send feedback to the team or eng, report a platform bug, request a rule change, write a feature request, or convert raw clinic feedback into implementable rules. Triggers: "feedback for the team", "write this up for eng", "report this to the team", "new rule for the platform", "feature request", "convert this into a rule", "regla para la plataforma", or when the user pastes raw clinic feedback about eligibility, insurance, or copay behavior that needs to go to engineering.
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 28
NOT for: strategy discussions, prose emails, customer-facing messages
- Distinctive: line 98
Add new mappings here as they come up.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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
Team Feedback — WHEN/THEN/Example Framework
Overview
Feedback to the platform team must be implementable without a single clarifying question: explicit condition + explicit behavior + evidence.
Core principle: write the condition as the error you SEE, never the cause you assume. "If MCO fails" forces eng to investigate what an MCO is; "el check automático da failed" does not.
When to Use
- New platform rules (eligibility, insurance, copay behavior)
- Bug reports
- Feature requests
- NOT for: strategy discussions, prose emails, customer-facing messages
The Output Contract
The message consists of, in order:
- One template block per rule (below)
- Optionally, ONE line starting with
Nota:flagging a concern for eng to consider
Nothing else. No intro paragraphs, no root-cause analysis, no recommendations to "investigate first" — the rule as observed is the deliverable; a concern is one Nota: line.
WHEN (condición):
Insurance = [Trading Partner ID] ([nombre])
Y [el error/estado que se ve en la plataforma]
THEN (comportamiento):
[acción concreta]
Ejemplo (evidencia):
[clínica], paciente/check [ID]Rules
- Insurance = Trading Partner ID, always. The TPID is the same across all clinics; display names are not. Name goes in parentheses for readability only. If the TPID is unknown, ask the user — never guess or substitute the name.
- Condition = observed error/state, exactly as seen in the platform UI (e.g., "el check automático da failed", "la insurance tiene más de un copay").
- THEN = one concrete action the platform should take (retry with X, choose Y, allow Z).
- Evidence required: clinic + patient ID or check ID. If missing, ask for it.
- Feature requests state the behavior, never a question or timeline ask: "Cuando los usuarios crean un Prior Auth, permitir agregar modifiers a los CPT codes."
- Language: match the user's draft language (team usually writes Spanish); keep
WHEN/THENkeywords as-is. - Output as plain copy-paste-ready text — no markdown formatting in the message itself.
Example: Before → After
Raw feedback:
"if MCO fails, run with straight Medicaid. [Clinic A]: 00000000-0000-0000-0000-000000000001"
Formatted:
WHEN (condición):
Insurance = 68049 (Peach State Health Plan)
Y el check automático da failed
THEN (comportamiento):
Reintentar el check con Insurance = QBZJV
Ejemplo (evidencia):
[Clinic A], paciente 00000000-0000-0000-0000-000000000001Example: Non-Insurance Rule (Copays)
WHEN (condición):
La insurance tiene más de un copay
THEN (comportamiento):
Elegir el copay cuyo mensaje contenga "freestanding"
Ejemplo (evidencia):
[Clinic B], check 00000000-0000-0000-0000-000000000002Known Trading Partner IDs
| Payer | TPID | Notes |
| Peach State Health Plan (GA Medicaid MCO) | 68049 | On failed check → retry with QBZJV |
| Georgia straight Medicaid | QBZJV | Fallback payer for 68049 |
Add new mappings here as they come up.
Common Mistakes
| Mistake | Fix |
| Insurance referenced by name only | Always TPID; name in parentheses |
| Condition written as assumed cause ("if MCO fails") | Condition = visible error ("el check da failed") |
| Root-cause essay or pushback instead of the rule | Template block + at most one Nota: line |
| Feature request as a question or timeline ask | State the behavior: "Cuando [acción], [comportamiento]" |
| No evidence | Clinic + patient/check ID, always |
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- andeya/team-skills★ 4same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository31 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- chief-of-staffSkill
- codex-reviewSkill
- conference-prepSkill
- doc-conversion-qaSkill
- eligibility-checkSkill
- fact-checkSkill
- google-adsSkill
- icp-researchSkill
- linkedin-carousel-builderSkill
- mac-performance-triageSkill
- meeting-followupSkill
- meeting-prepSkill
- mobile-auditSkill
- one-pager-builderSkill
- ops-metricsSkill
- pmf-pulseSkill
- post-conference-fupSkill
- post-conference-insightsSkill
- postmortemSkill
- prior-auth-review-skillSkill
- product-insightsSkill
- seoSkill
- site-reviewSkill
- solum-health-brandSkill
- task-triageSkill
- uscis-petition-reviewSkill
- weekly-retroSkill
- weekly-reviewSkill
- win-lossSkill
- x-healthcare-postsSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

