More screenshots
Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
DeepSeek
Muse+22 moreClaude CodeCursorCodex CLIDeepSeekMuse
Dots
Manus
Grok
Grok Bot+18 agentsSprint Planning & Backlog Refiner — Definition of Ready + Capacity Gate
Refines each backlog story against a Definition of Ready, splits oversized work, maps blockers, and issues a COMMIT / COMMIT-WITH-RISK / OVER-COMMITTED verdict against real sprint capacity.
$12
Sprint Planning & Backlog Refiner — Definition of Ready + Capacity Gate
Example session with this skill installed
Product: Inkline (creative proofing for agencies)
Sprint 41 · 2 weeks · capacity 13 pts (historical ~16; Jin OOO 3 days)
Sprint goal: clients comment on proofs; agencies compare versions
Backlog
S1 Pin comments on PDF (5) — AC present
S2 Side-by-side version compare (13) — no AC
S3 Magic-link client access (5) — blocked: Auth tenant not provisioned
S4 “Improve upload performance” — unsized, vague
S5 Resolve/reopen comment threads (3) — AC present
S6 Require client approval before Final (5) — AC present, Figma missing
S7 Download PDF + comments summary (8) — rough idea
S8 Filter comments open/resolved/mine (2) — AC present
Ask: refine DoR, splits, dependencies, capacity-aware commitment. Do not write to Jira.
- Read your context and instructions
- Compiled the sprint planning
Sprint Planning & Backlog Refinement
1. Sprint Summary
| Field | Value |
|---|---|
| Sprint | Sprint 41 (2 weeks) |
| Capacity | 13 points (Jin OOO adjustment; historical full-staff ~16) |
| Stories refined | 8 |
| Ready / Needs-refinement / Split | 3 / 3 / 2 |
| Committed points | 10 of 13 (READY only) |
| Sprint commitment | COMMIT-WITH-RISK |
Why COMMIT-WITH-RISK: 10 ≤ 13 (not over capacity), but version-compare (sprint goal) is not READY without a split, S6 lacks Figma, and reduced capacity leaves little bug buffer.
2. Story Readiness
| ID | Pts | Readiness | Why |
|---|---|---|---|
| S1 Pin comments | 5 | READY | Clear value + testable AC |
| S2 Version compare | 13 | SPLIT | Too large vs capacity / small-enough rule |
| S3 Magic-link access | 5 | NEEDS-REFINEMENT | Auth tenant blocker |
| S4 Upload performance | — | NEEDS-REFINEMENT | Vague, UNSIZED, no metric |
| S5 Resolve threads | 3 | READY | Clear + testable AC |
| S6 Require approval | 5 | NEEDS-REFINEMENT | Missing Figma asset |
| S7 PDF + comments export | 8 | SPLIT | Multi-concern; split recommended |
| S8 Filter comments | 2 | READY | Clear + testable AC |
3. Refined READY stories (commit these)
S1 (5) — pin comments: pin at coordinates; author/time/page visible; pins persist
S5 (3) — resolve/reopen threads with Open filter behavior
S8 (2) — filters for Open / Resolved / Mine
READY total = 10 points
4. Needs refinement (do not commit yet)
| ID | Fix |
|---|---|
| S3 | Provision Auth tenant + AC for expiry |
| S4 | Rewrite with measurable p95 upload target + size |
| S6 | Attach Figma approval modal |
5. Split suggestions
S2 (13) → S2a side-by-side shell · S2b synced navigation · S2c highlights
S7 (8) → S7a download PDF · S7b summary page · S7c merged export
6. Dependency map
- S3 blocked by Auth tenant
inkline-preview - S6 blocked by missing Figma
- S7b/c richer after S1 pins land (soft)
7. Commitment analysis
| Capacity | 13 |
| READY commit | S1+S5+S8 = 10 |
| Headroom | 3 |
| Verdict | COMMIT-WITH-RISK |
Do not pull: whole S2/S7, S3, S4, S6.
If PO forces compare: refine S2a only, then descope S8 (or accept OVER-COMMITTED if 10+5 > 13).
8. Sprint Backlog JSON
Machine-readable stories[], readiness, splits, dependency_map, descope_recommendations,
committed_points: 10, commitment: "COMMIT-WITH-RISK", assumptions labeled
(capacity 13 not invented; split points need team confirm).
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
- Sprint planning fails when vague stories, missing acceptance criteria, and silent blockers get committed as if they were ready.
- Oversized items (13+ points) hide in the sprint and blow the goal.
- Teams need a capacity-honest commit — not a wish list.
What it does
- Scores each story READY, NEEDS-REFINEMENT, or SPLIT against a Definition of Ready.
- Validates or proposes testable acceptance criteria (Given/When/Then where useful).
- Suggests vertical-slice splits for oversized work.
- Maps dependencies (“blocked by”).
- Commits only READY work and returns COMMIT, COMMIT-WITH-RISK, or OVER-COMMITTED with descope recommendations.
Frameworks & tools
- Works with any backlog format (Jira export, Linear list, markdown stories).
- Story-point or capacity-based planning; stack-agnostic product work.
- Outputs markdown + JSON you paste into the tracker — no SaaS integration required.
Why this beats prompting it yourself
- Explicit DoR gate so “Improve performance” cannot slip in as READY.
- Only READY points count toward commitment math.
- Deterministic commit rules (over capacity → OVER-COMMITTED).
- Named descope order when overloaded.
- Anti-fabrication: UNSIZED stays null; assumptions labeled.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Product Management.
• Uses the capacity/velocity you supply — does not invent team speed
• Unsized stories cannot be committed until estimated
• Not multi-phase project critical-path planning
• Does not update Jira/Linear or notify Slack
• Planning aid, not a delivery guarantee
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 20 days ago
Permissions
This skill only reads the backlog and capacity you provide and drafts a refined plan. It does not update issue trackers, invent velocity, or message the team. Grant Read only; leave Shell, Write, Browser, Network, and Env off.