- Home
- Skills
- Product Management
- Lanewright Backlog Check: readiness check and human sign-off
Works with the AI Agents you already use
Lanewright Backlog Check: readiness check and human sign-off
Check a sprint backlog before any agent starts: format, IDs, size, testable criteria, regions and SRS coverage. Writes a READY / NOT READY report and a sign-off block only a human fills.
Free
Lanewright Backlog Check: readiness check and human sign-off
Example session with this skill installed
Check the sprint 1 backlog before we start.
- Read your context and instructions
- Compiled the lanewright backlog check
Real output of the bundled script on the Superapps sprint 1 backlog (the example in the Lanewright Sprint Planner listing). The agent then adds its own judgment checks and writes docs/sprints/backlog-check-01.md with an empty sign-off block for a human.
INFO | docs/sprints/sprint-01-backlog.md | - | sha256 | 5ee9061c03416899e962f0de6a7501781fbf380688c6dc743eca69a2c749cbf3
INFO | docs/sprints/sprint-01-backlog.md | - | format | Lanewright
WARN | docs/sprints/sprint-01-backlog.md | BE-1-S01-03 | broad-citation | cites 4 requirement IDs (over 3): split the item
INFO | docs/sprints/sprint-01-backlog.md | - | total-sp | 28 SP in 8 items
INFO | docs/requirements/srs.md | - | coverage | not cited by any item: F-05, F-06, F-07, F-08, F-09, F-10, F-11, F-12, F-13, F-14, F-15, F-16, F-17, F-18
INFO | docs/requirements/srs.md | - | coverage | weakly covered, cited only by items with more than 3 requirement IDs: F-01, F-02, F-03, F-04
VERDICT | docs/sprints/sprint-01-backlog.md | 0 error(s), 1 warning(s) | READY WITH WARNINGS
SUMMARY | 1 file(s) | 0 error(s), 1 warning(s), 5 info | READY WITH WARNINGS
Verdict READY WITH WARNINGS: one item cites four requirements and should be split. The SHA-256 line is the fingerprint Lanewright and scrum-kit compare before the sprint starts.
Connects securely to your tools. The creator never sees your data.
About this skill
Lanewright Backlog Check is the gate in front of a sprint. It reads your sprint backlog files (Lanewright or scrum-kit format, from the Sprint Planner or written by hand) and runs a bundled Python script, then reviews what a script cannot judge.
The script checks: the table format; leftover template placeholders; ID format, duplicates and sprint number; empty cells; story points from 1 to 10; with .claude/kit.json, that every region or module exists; short or vague acceptance criteria ("works properly" with no number); and, with the SRS, which requirements have no item.
The agent then judges whether each acceptance criterion is independently testable, whether an item fits one owner in one week, whether the dependency order makes sense, and whether the owner fits the region.
Output: docs/sprints/backlog-check-{nn}.md with a verdict (READY, READY WITH WARNINGS or NOT READY), a findings table with suggested fixes, total story points, a SHA-256 fingerprint of every backlog file, and a sign-off block (approved by, role, date, overrides, and which proposed "not applicable" Definition of Done items you approve). The agent never fills the approval itself: only after you answer yes and give your name and role, and every override of an error is recorded. It never edits a backlog without asking.
It does not replace Lanewright or scrum-kit. It sits in front of them: approve the backlog, then run the sprint. Lanewright (1.0.1 and later) and scrum-kit read this report as their readiness gate: they compare the fingerprint with the backlog, so a backlog changed after your sign-off is caught, and they accept a "not applicable" DoD item only when you approved it here.
These four skills prepare the work. To run the sprints, use Lanewright (paid): https://www.agensi.io/r/HUZAIRSAPUTRA?to=/skills/lanewright-sprint-workflow-for-ai-coding-agent-teams or the free scrum-kit Claude Code plugin: https://github.com/huzairsaputra/scrum-kit. They work without either.
Why four skills, not one: https://github.com/huzairsaputra/lanewright-planning#why-four-skills-not-one
The four free skills on Agensi: Intake https://www.agensi.io/r/HUZAIRSAPUTRA?to=/skills/lanewright-intake-raw-project-input-to-cited-facts, SRS https://www.agensi.io/r/HUZAIRSAPUTRA?to=/skills/lanewright-srs-cited-requirements-in-word-and-markdown, Sprint Planner https://www.agensi.io/r/HUZAIRSAPUTRA?to=/skills/lanewright-sprint-planner-srs-to-weekly-plan-and-backlogs, Backlog Check https://www.agensi.io/r/HUZAIRSAPUTRA?to=/skills/lanewright-backlog-check-readiness-check-and-human-sign-off
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.
The script's vague-word list covers English and Indonesian only; judgment checks depend on the agent; it checks the file, not whether the work is actually well understood by the team.
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
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 4 days ago
- Free with an Agensi account
- Software
Python 3.8+
Permissions
File Scopes