ValentinNikolaev/agent-skills / agent-plugins/skills/council
council
VerifiedRun independent advisor passes and anonymized peer review for a consequential choice. Use when the user requests a council, debate, or stress test; prefer specialist reviews otherwise.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 7.0 KB |
| agents/openai.yaml | config | 218 B |
| references/advisors-and-prompts.md | markdown | 4.4 KB |
| references/example.md | markdown | 2.5 KB |
references/example.md
View on GitHub# Example Council session
Use this fictional example to understand structure, not as evidence for another decision.
## User frame
A small software company must choose between:
- releasing a self-service plan now;
- running three paid concierge pilots first.
Supplied facts: the prototype works, five prospects completed interviews, two offered to pay for a pilot, onboarding still requires six founder hours per customer, and no retention data exists. The company has eight weeks of runway for this experiment.
## Quick advisor excerpts
**Contrarian:** Two verbal pilot offers do not validate self-service demand. Six founder hours per account also hides the real onboarding cost. Require signed pilot commitments and record every manual step before funding a broader launch.
**First-Principles Thinker:** The immediate decision is not self-service versus concierge. It is which path produces reliable retention and willingness-to-pay evidence within eight weeks. Concierge pilots provide that evidence sooner if they use the intended price and product workflow.
**Executor:** Run three paid pilots with a fixed onboarding checklist, time tracking, one success metric, and a renewal decision in week six. Automate only steps repeated across all three.
## Anonymized review
The responses converge on paid pilots because the supplied evidence supports learning, not scale. That convergence is not proof that the pilots will retain. All three underweight acquisition repeatability; the experiment should record where each buyer came from and how long conversion took.
## Calibrated synthesis
### Where the Council Converges
Use paid pilots before a broad self-service release. The shared reasoning rests on the supplied onboarding burden and missing retention data, not on advisor vote count.
### Where the Council Disagrees
The Contrarian treats the two offers as weak until signed. The Executor treats them as enough to start a tightly bounded experiment. Both views depend on whether the prospects accept the intended price and success criteria.
### Blind Spots and Evidence Gaps
Acquisition repeatability and post-pilot retention remain unknown.
### Recommendation
Run three paid concierge pilots before investing in self-service onboarding.
### First Action
Send a one-page paid-pilot offer with price, outcome, timeline, and week-six renewal decision to the two interested prospects.
### What Would Change the Verdict
A credible set of self-service customers already completing onboarding without founder help would support launching the plan sooner.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |