prioritize-backlog
/prioritize-backlog
Ranguje pomysły i pozycje backlogu według oceny wartości i pewności w skali 0-100, gdy trzeba ustalić, co budować dalej.
- Autor
- sparkline-ventures ↗
- Repozytorium
- product-eval ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 29.06.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 2
- Skrypty
- 0
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 29.06.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
Co robi i kiedy
Ranguje pomysły i pozycje backlogu według oceny wartości i pewności w skali 0-100, gdy trzeba ustalić, co budować dalej.
Wyzwalacze z opisu
Oryginalny opis (EN)
Rank opportunities or backlog items by evidence-backed Value and Confidence bands, storing exact 0-100 scores for audit. Use when the user says "prioritize my backlog", "rank these", "what should we build next", "score these opportunities", or hands over a list of problems/features to sequence. This is the Rank opportunities outcome, distinct from updating a roadmap's Now/Next/Later. Falls back to proxies when data is thin and flags lower confidence.
Jak działa
- Workflow
- Output
Podgląd SKILL.md
--- name: prioritize-backlog description: Rank opportunities or backlog items by evidence-backed Value and Confidence bands, storing exact 0-100 scores for audit. Use when the user says "prioritize my backlog", "rank these", "what should we build next", "score these opportunities", or hands over a list of problems/features to sequence. This is the Rank opportunities outcome, distinct from updating a roadmap's Now/Next/Later. Falls back to proxies when data is thin and flags lower confidence. --- # Prioritize Backlog Score and rank a set of problems or opportunities so the user knows what to build next and why. Produce a defensible ranking with explicit reasoning, not a gut order. In chat, show bands and recommendations first; store exact numbers in scope files. ## Workflow ### 1. Gather the items and their context Take the list to rank (from the user, from problem-framed themes, or from `.product-eval/<scope>/`). Read `.product-eval/<scope>/context.md` for the north-star metric and personas, and `.product-eval/<scope>/sources.md` for the confidence ceiling. If business context is missing, ask only the few questions needed to score (north star, primary personas) and proceed. **Preflight (data contract).** When ranking themes already written to `.product-eval/<scope>/`, validate `themes.md` against the conformance preflight in `DATA-CONTRACT.md` (Validation) first (members resolve to real evidence, `total_weight` matches the members, `confidence_band` is consistent with `confidence`). On a failure, stop and report the file, field, and violation rather than scoring malformed input. ### 2. Score Value per item Using `references/scoring-framework.md`, score four dimensions (each 0-25, summed). Store the exact 0-100 `value` and `value_band`; show the band in chat. - **Persona weight**: buyer vs admin vs end-user vs edge case. - **Funnel location**: retention/activation rank highest; advocacy lowest. - **Frequency**: how often the affected users hit this. - **Competitive pressure**: from "customers leaving" down to "no pressure". When first-party data is missing, use the proxies in the reference (complaints as a drop-off proxy, sales objections as a conversion proxy, competitor investment as a gap proxy) and mark those scores as lower confidence. ### 3. Score Confidence per item, report as a band Confidence reflects how well-supported the item is by evidence: count of independent evidence items, diversity of source types, their strength (1-5), recency, and how much is first-party. Store the exact 0-100 `confidence` for audit and calibration, but present `confidence_band` in chat (Low / Moderate / High). Respect the ceiling from `.product-eval/<scope>/sources.md`. Signal strength is an input to Confidence, not a separate verdict. ### 4. Apply the recommendation matrix Map each item's (Value, Confidence) to a recommendation using the matrix in the reference: *Decide now / Run a research sprint / Do not commit yet / Deprioritize.* High value + low confidence means "research more", not "drop", keep these visible. ### 5. Rank and present Order by recommendation tier first, then Value band within tier. Present a scannable ranked table: item, Value band, Confidence band, recommendation, one-line rationale. Call out the few items worth acting on now and the few to deprioritize. Put exact point scores only in an audit note or the scope file. ### 6. Record and offer next step Write `.product-eval/<scope>/scores.md` with exact scores, bands, and reasoning, and log the ranking in `.product-eval/<scope>/decisions-log.md`, using the score and decisions-log schemas in the data contract (`DATA-CONTRACT.md`). Offer to decide on the top item or pressure-test the resulting shortlist. Honor user score overrides, but require a one-sentence reason and log it. ## Output A ranked table with bands, recommendations, and a short "act on these / hold these" summary. Keep exact math and internal paths out of the chat unless asked. End with `Next move:` and recommend deciding on the top item, pressure-testing the shortlist, rendering a scorecard, or writing the report the user asked for.
Pliki w paczce (2)
- SKILL.md 4 KB
- references/scoring-framework.md 5 KB
Wersje
W bazie nie ma innych skilli o nazwie prioritize-backlog.
Migawka bazy z 13.11.2026 · wersja paczki b5f66c5ae587 (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
- 100score-backlog
Ocenia i szereguje pozycje backlogu metodami RICE, ICE lub własną ważoną punktacją przy priorytetyzacji backlogu i funkcji. - 100helm-plan
Układa roadmapę produktu, priorytetyzuje backlog i ustala kolejność funkcji, na przykład metodą RICE, gdy trzeba zdecydować, co budować dalej. - 100helm-plan
Buduje roadmapę produktu, priorytetyzuje backlog i szereguje pomysły na funkcje, na przykład punktacją RICE, by wskazać, co budować dalej. - 90Backlog Management
Prowadzi backlog projektu w pliku BACKLOG.md: dodaje pozycje, aktualizuje je, sprawdza i ustala priorytety. - 100prioritization
Pomaga uszeregować backlog funkcji lub listę pomysłów metodami RICE, MoSCoW i drzewa możliwości, by zdecydować, co budować najpierw. - 100roadmap
Prowadzi prywatny backlog ROADMAP.md: zapisuje i szereguje pomysły na funkcje i ustalenia o konkurencji, oznaczając gotowe pozycje.