Przejdź do treści
Biblioteka skilli
Zarządzanie i produkt · Analiza

experts

/experts

Zbiera panel ekspertów, by ocenić problem z wielu perspektyw zawodowych, wskazuje zgodności i spory oraz daje rekomendację przewodniczącego z kompromisami.

Repozytorium
skills ↗
Licencja
MIT
Ostatnia zmiana repozytorium
25.10.2026

Ocena i bezpieczeństwo

100/ 100Klasa: dobry
Format25 / 25
Frontmatter z nazwą i opisem, poprawna nazwa, opis do 1024 znaków, nazwa zgodna z folderem.
Odkrywalność25 / 25
Opis mówi, kiedy użyć skilla, ma sensowną długość i jest w 3. osobie.
Treść35 / 35
Co najmniej 150 słów i do 500 linii, nagłówki, listy kroków, przykłady albo kod.
Higiena15 / 15
Bez zaślepek typu TODO, bez ścieżek Windows, z licencją.
Ryzykobrak sygnałów w skanie
Pliki w paczce
43
Skrypty
0
Komentarze HTML
0
Adresy URL w SKILL.md
0
Przestarzałość

Brak sygnałów. Repozytorium zmienione 25.10.2026, bez odwołań do wycofanych modeli i API.

Licencja

MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.

Co robi i kiedy

Zbiera panel ekspertów, by ocenić problem z wielu perspektyw zawodowych, wskazuje zgodności i spory oraz daje rekomendację przewodniczącego z kompromisami.

Oryginalny opis (EN)

Assemble a panel of experts to assess a problem from multiple professional perspectives, surface agreement and disagreement, and deliver a chaired recommendation with clear tradeoffs. Use when the user wants multi-expert judgment, a second opinion, design critique, option comparison, or a recommendation backed by distinct expert viewpoints.

Jak działa

  1. Operating Mode
  2. Resource Map
  3. Panel Modes
  4. Workflow
  5. Expert Standards
  6. Selection Rules
  7. Output Structure
  8. Decision Rules
  9. Red Flags
Sekcje z nagłówków SKILL.md, w oryginale · 293 linii, 1 475 słów
Podgląd SKILL.md
---
name: experts
description: Assemble a panel of experts to assess a problem from multiple professional perspectives, surface agreement and disagreement, and deliver a chaired recommendation with clear tradeoffs. Use when the user wants multi-expert judgment, a second opinion, design critique, option comparison, or a recommendation backed by distinct expert viewpoints.
metadata:
  name: Experts
  description: Assemble a focused panel of experts to assess a problem, surface tradeoffs, and deliver a chaired recommendation.
  author: Flc゛
  created: 2026-03-27T10:42:23Z
---

# Experts

Assemble a focused panel of experts around one problem and produce a chaired recommendation.

This is a cross-domain expert panel skill for complex decisions. It is not limited to one industry or problem class, but every expert seat must still meet the same expert-grade standard.

This skill is for expert judgment first. It is not a generic task router.

## Operating Mode

- Use this skill when the user wants expert advice, a multi-angle assessment, a second opinion, or a recommendation with explicit tradeoffs.
- Treat explicit invocation of `$experts` as permission to assemble a panel of subagents when the environment supports it.
- Prefer domain experts over generic worker roles.
- Require each expert to form an independent view before seeing other experts' conclusions.
- Treat disagreement as useful output, not failure.
- Keep the final answer focused on judgment, rationale, tradeoffs, and boundaries.
- When the environment supports subagents and parallel delegation, prefer true multi-expert execution with independent opinions gathered in parallel where safe.
- When the environment does not support subagents or parallel delegation, simulate the same panel structure in one thread by producing clearly separated expert viewpoints before synthesis.
- Do not collapse the panel into one blended answer just because execution is single-threaded.

## Resource Map

Read [references/roles-index.md](references/roles-index.md) first. Then load only the expert cards that match the problem.

Common expert cards:

- [references/role-chair.md](references/role-chair.md)
- [references/role-architect.md](references/role-architect.md)
- [references/role-frontend-expert.md](references/role-frontend-expert.md)
- [references/role-backend-expert.md](references/role-backend-expert.md)
- [references/role-product-expert.md](references/role-product-expert.md)
- [references/role-security-expert.md](references/role-security-expert.md)
- [references/role-privacy-expert.md](references/role-privacy-expert.md)
- [references/role-performance-expert.md](references/role-performance-expert.md)
- [references/role-data-expert.md](references/role-data-expert.md)
- [references/role-devops-expert.md](references/role-devops-expert.md)
- [references/role-platform-expert.md](references/role-platform-expert.md)
- [references/role-mobile-expert.md](references/role-mobile-expert.md)
- [references/role-search-expert.md](references/role-search-expert.md)
- [references/role-payments-expert.md](references/role-payments-expert.md)
- [references/role-compliance-expert.md](references/role-compliance-expert.md)
- [references/role-ml-expert.md](references/role-ml-expert.md)
- [references/role-itinerary-expert.md](references/role-itinerary-expert.md)
- [references/role-budget-travel-expert.md](references/role-budget-travel-expert.md)
- [references/role-travel-risk-expert.md](references/role-travel-risk-expert.md)
- [references/role-family-travel-expert.md](references/role-family-travel-expert.md)
- [references/role-local-transport-expert.md](references/role-local-transport-expert.md)
- [references/role-experience-curator.md](references/role-experience-curator.md)
- [references/role-destination-culture-expert.md](references/role-destination-culture-expert.md)
- [references/role-information-discovery-expert.md](references/role-information-discovery-expert.md)
- [references/role-source-verification-expert.md](references/role-source-verification-expert.md)
- [references/role-recency-expert.md](references/role-recency-expert.md)
- [references/role-coverage-analyst.md](references/role-coverage-analyst.md)
- [references/role-signal-vs-noise-analyst.md](references/role-signal-vs-noise-analyst.md)
- [references/role-qa-expert.md](references/role-qa-expert.md)
- [references/example-platform-modernization-panel.md](references/example-platform-modernization-panel.md)
- [references/example-analytics-dashboard-panel.md](references/example-analytics-dashboard-panel.md)
- [references/example-subscription-billing-panel.md](references/example-subscription-billing-panel.md)
- [references/example-ai-assistant-panel.md](references/example-ai-assistant-panel.md)
- [references/example-task-local-identity-panel.md](references/example-task-local-identity-panel.md)
- [references/example-family-japan-panel.md](references/example-family-japan-panel.md)
- [references/example-istanbul-culture-panel.md](references/example-istanbul-culture-panel.md)
- [references/example-ai-release-watch-panel.md](references/example-ai-release-watch-panel.md)
- [references/example-acquisition-rumor-panel.md](references/example-acquisition-rumor-panel.md)
- [references/task-local-expert-template.md](references/task-local-expert-template.md)

Read the example only when you need a high-quality reference for what a professional panel output should look like.

## Panel Modes

Choose one mode before assembling the panel:

- `advisory`: provide expert judgment and recommendation only
- `decision-support`: provide recommendation plus a concrete next-step plan
- `deep-dive`: investigate a complex problem with more evidence gathering before recommendation

Use `advisory` by default unless the user asks for execution planning or deeper analysis.

## Workflow

Follow this sequence unless the user asks for a narrower deliverable.

### 1. Frame the question

Extract and restate:

- the exact question to be assessed
- the desired decision or output
- known constraints, assumptions, and approvals
- relevant code, documents, systems, or artifacts
- time sensitivity
- the panel mode

Reduce vague requests into a precise assessment question before assembling the panel.

### 2. Select the panel

Choose a small panel with one `chair` and two to six experts.

Pick experts that match the real decision surface. Prefer distinct viewpoints over panel size.

Use the role cards in [references/roles-index.md](references/roles-index.md) when they fit. If no card fits cleanly, synthesize a task-local expert with a clearly named professional lens and explicit remit.

### 2a. Synthesize a task-local expert when needed

Create a task-local expert only when the registry does not cover a real decision lens.

A task-local expert must:

- represent a genuine expert discipline, not an ad hoc job title
- have a narrow and defensible professional lens
- be likely to disagree with at least one other expert for substantive reasons
- add decision value that cannot be cleanly absorbed by an existing card

Do not create fake-specialized seats such as:

- feature-name experts
- implementation-step experts
- generic smart-reviewer variants
- duplicate experts that only rephrase another card

When you create a task-local expert, read [references/task-local-expert-template.md](references/task-local-expert-template.md) and define:

- expert name
- professional lens
- decision surface
- required evidence
- core evaluation criteria
- critical unknowns
- reject conditions
- explicit non-goals and boundary with nearby experts

Task-local experts are valid only for the current panel unless the user explicitly asks to persist them into the library.

### 3. Gather independent opinions

Ask each expert to assess the problem independently.

Each opinion should cover:

- core judgment
- evidence basis and what is inferred versus directly observed
- confidence level and the main reason for that confidence level
- reasoning and assumptions
- preferred option
- main risks
- critical unknowns that could change the recommendation
- decision thresholds that would cause the expert to change position
- what the expert would reject and why

Do not let experts anchor on each other too early.

If experts are running in parallel, gather these opinions independently before cross-examination.

If experts are running in a single thread, still keep the outputs structurally independent:

- write each expert section separately
- do not let later experts silently inherit prior conclusions
- preserve disagreement even when the same agent is simulating multiple seats

### 4. Run cross-examination

After independent opinions exist, ask experts to challenge each other.

Focus on:

- hidden assumptions
- underestimated costs
- ignored failure modes
- disagreement about priorities
- conditions under which another expert would be right

Keep this phase evidence-driven and concise.

### 5. Deliver the chaired recommendation

The `chair` synthesizes the panel into a decision-ready output.

Return:

- the question
- the final panel
- each expert's core view
- the evidence and confidence profile behind each view
- agreement points
- disagreement points
- the recommended path
- tradeoffs and risks
- boundaries where the recommendation does or does not hold

When the user asks to proceed, include a short next-step plan after the recommendation. Do not turn the report into a full execution playbook unless explicitly requested.

## Expert Standards

Apply these rules to every expert:

- Act as the most senior expert for the assigned perspective.
- Stay rigorous, concrete, and scope-bound.
- Prefer defensible reasoning over confident tone.
- Distinguish observed facts from inference and speculation.
- State confidence level and what would increase or decrease it.
- Make assumptions explicit.
- Name the key unknowns that prevent a stronger recommendation.
- State reject conditions, not just preferred outcomes.
- Push back on weak framing, false binaries, and unsupported claims.
- Optimize for helping the user make a better decision, not for winning an argument.

## Selection Rules

- Prefer the smallest panel that can expose meaningful tradeoffs.
- Prefer domain experts to generic reviewers.
- Add a role expert only when a domain lens is not enough.
- Avoid duplicate experts with the same perspective.
- Expand the panel only when the decision has genuine cross-functional risk.
- If one expert would dominate because the question is narrow, use fewer experts and state that clearly.

## Output Structure

Use this structure when returning a panel result:

```markdown
# Expert Panel Report

## Question
- <the decision or problem being assessed>

## Decision Criteria
- <which evaluation axes matter most in this panel>
- <which constraints are primary versus secondary>

## Panel
- chair: <why this chair is appropriate>
- <expert>: <perspective and remit>

## Expert Opinions
- <expert>: <core judgment, rationale, major risks>
- evidence: <what is known, what is inferred>
- evidence quality: <direct evidence | indirect evidence | expert inference>
- confidence: <high | medium | low> and why
- critical unknowns: <what could still change the answer>
- reject conditions: <what would make this expert reject a path>

## Agreement
- <shared conclusions>

## Disagreement
- <meaningful differences in view or priorities>

## Recommendation
- recommended path: <best option>
- why: <main justification>

## Tradeoffs
- <what is gained and what is given up>

## Minority View
- <which dissenting view did not win>
- <under what conditions that view becomes stronger>

## Confidence and Unknowns
- <where the panel is confident>
- <where the panel is still reasoning under uncertainty>

## Immediate Implications
- <what should be decided, validated, or sequenced next if this recommendation is accepted>
- <what signal should trigger re-evaluation of the panel's conclusion>

## Boundaries
- holds when: <conditions where this advice fits>
- avoid when: <conditions where this advice should not be followed>
```

## Decision Rules

- Prefer explicit tradeoffs over vague best practices.
- Prefer recommendations that match the user's real constraints, not an idealized environment.
- State uncertainty when the evidence is incomplete.
- Keep minority concerns when they materially affect risk.
- Separate recommendation quality from implementation difficulty.
- If the panel lacks a necessary perspective, say so and adjust the panel before concluding.

## Red Flags

Stop and reassess if:

- the question is still too vague to judge
- the panel contains overlapping experts with no distinct lens
- experts are repeating the same argument in different words
- the recommendation hides unresolved disagreement
- evidence is too thin for a credible conclusion
- the user is asking for implementation but the panel has only produced advice
Pliki w paczce (43)
  • README.md 2 KB
  • SKILL.md 13 KB
  • agents/openai.yaml 1 KB
  • references/example-acquisition-rumor-panel.md 13 KB
  • references/example-ai-assistant-panel.md 19 KB
  • references/example-ai-release-watch-panel.md 13 KB
  • references/example-analytics-dashboard-panel.md 15 KB
  • references/example-family-japan-panel.md 15 KB
  • references/example-istanbul-culture-panel.md 13 KB
  • references/example-platform-modernization-panel.md 14 KB
  • references/example-subscription-billing-panel.md 17 KB
  • references/example-task-local-identity-panel.md 15 KB
  • references/role-architect.md 1 KB
  • references/role-backend-expert.md 2 KB
  • references/role-budget-travel-expert.md 2 KB
  • references/role-chair.md 2 KB
  • references/role-compliance-expert.md 2 KB
  • references/role-coverage-analyst.md 2 KB
  • references/role-data-expert.md 2 KB
  • references/role-destination-culture-expert.md 3 KB
  • references/role-devops-expert.md 2 KB
  • references/role-experience-curator.md 2 KB
  • references/role-family-travel-expert.md 3 KB
  • references/role-frontend-expert.md 2 KB
  • references/role-information-discovery-expert.md 3 KB
  • references/role-itinerary-expert.md 2 KB
  • references/role-local-transport-expert.md 3 KB
  • references/role-ml-expert.md 2 KB
  • references/role-mobile-expert.md 2 KB
  • references/role-payments-expert.md 2 KB
  • references/role-performance-expert.md 1 KB
  • references/role-platform-expert.md 2 KB
  • references/role-privacy-expert.md 2 KB
  • references/role-product-expert.md 2 KB
  • references/role-qa-expert.md 2 KB
  • references/role-recency-expert.md 2 KB
  • references/role-search-expert.md 2 KB
  • references/role-security-expert.md 2 KB
  • references/role-signal-vs-noise-analyst.md 2 KB
  • references/role-source-verification-expert.md 3 KB
  • references/role-travel-risk-expert.md 2 KB
  • references/roles-index.md 14 KB
  • references/task-local-expert-template.md 4 KB

Wersje

RepozytoriumWynikLicencja
Ta strona · flc1125/skills100MIT
remotion-dev/remotion100MIT
jamescai-md/motionframe-edit100MIT
2389-research/review-squad100MIT

Migawka bazy z 13.11.2026 · wersja paczki 9491968c6048 (skrót SHA-256 całej paczki)

Pobrania w ostatnich 30 dniach: 0 · ranking

Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.

Podobne skille

  • 100convening-experts
    Zwołuje panele ekspertów do rozwiązywania problemów, z wieloma perspektywami, metodami MECE, DMAIC, RAPID i Six Sigma, analizą przyczyn źródłowych i decyzjami strategicznymi.
  • 100gvm-experts
    Ocenia, ponownie ocenia i zarządza ekspertami w rejestrze GVM, w tym ich autorytetem i dodawaniem nowych.
  • 100customer-panel-of-experts
    Buduje panel prawdziwych person nabywców z głębokiego skanu dozwolonych narzędzi i zleca im debatę nad decyzją, taką jak premiera, podwyżka cen, nowy produkt lub zmiana pozycjonowania, z rekomendacją.
  • 95expert-panel
    Ocenia treści i strategie panelem dobranych ekspertów, poprawia je w kolejnych rundach, aż wynik osiągnie 90 punktów.
  • 100k-war-room
    Zwołuje moderowany pokój wojenny z panelem ekspertów, którzy spierają się na czacie, głosują i piszą protokół z decyzjami, ryzykami i planem działania.
  • 81persona-panel
    Uruchamia równoległy przegląd treści przez wiele person, na przykład ekspertów albo recenzentów zgodności, i scala werdykty.

Uwagi i zgłoszenia

Wiadomość trafi do Bartosza Sokolińskiego. Adres e-mail jest potrzebny tylko do odpowiedzi. Szczegóły w polityce prywatności.