backlog-capture — Claude Code skill: what it does, how to install
Turns rough product ideas, requests, and meeting notes into backlog entries while checking for duplicates. Useful when capturing input from customers, sales, or research.
npx skills add mvschwarz/openrig --skill backlog-capture -a claude-codeWhat backlog-capture does
The skill takes rough text such as a meeting note, a customer request, a product idea, or a finding from competitor research. It shapes that input into a compact backlog item with a feature name, description, product area, and related dependencies. The description keeps the intended users, the reason behind the request, and its source.
Before writing a new item, it looks through the existing backlog for a similar entry. When it finds one, the skill adds the new evidence, source, and date to that item instead of creating another copy. New ideas go into the backlog file under “Ideas Not Yet in Jira,” with one entry per idea. In Claude Code, the installed file is ~/.claude/skills/backlog-capture/SKILL.md, so that path is worth checking after setup.
What it helps with
- capture ideas from a product meeting
- turn a customer request into a feature entry
- check a backlog item for duplicates
- split several meeting ideas into separate entries
Example prompts for the agent
- Capture this product idea in the backlog and include its source: [idea text].
- Turn this customer request into a feature entry, then check the existing backlog for a duplicate.
- Split these meeting notes into separate ideas and add them under “Ideas Not Yet in Jira”.
How to install backlog-capture
1Skills CLI (Vercel)
npx skills add mvschwarz/openrig --skill backlog-capture -a claude-code2Manually: put the files in place
~/.claude/skills/backlog-capture/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/backlog-capture/
1Skills CLI (Vercel)
npx skills add mvschwarz/openrig --skill backlog-capture -a codex2Manually: put the files in place
.agents/skills/backlog-capture/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add mvschwarz/openrig --skill backlog-capture -a cursor2Manually: put the files in place
.cursor/skills/backlog-capture/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install mvschwarz/openrig backlog-capture2Manually: put the files in place
.github/skills/backlog-capture/SKILL.md1Skills CLI (Vercel)
npx skills add mvschwarz/openrig --skill backlog-capture -a gemini-cli2Platform CLI
gemini skills install https://github.com/mvschwarz/openrig --path skills/_canonical/pm/backlog-captureManually: put the files in place
.devin/skills/backlog-capture/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add mvschwarz/openrig --skill backlog-capture -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about backlog-capture
How do I install backlog-capture in Claude Code?
Run npx skills add mvschwarz/openrig --skill backlog-capture -a claude-code, then check ~/.claude/skills/backlog-capture/SKILL.md.
What does backlog-capture do?
It turns rough ideas, requests, and observations into structured backlog entries with a name, description, product area, dependencies, and source. It searches for similar items and updates an existing entry when it finds a match.
How does backlog-capture handle several ideas from one meeting?
It creates a separate backlog entry for each idea. Relative dates in the notes are converted to absolute dates.
Source text
SKILL.md · Apache-2.0
--- name: backlog-capture description: "Quickly capture product ideas, feature requests, or insights from meetings and conversations. Rapid documentation with smart categorization and deduplication." --- You help a product manager rapidly capture ideas, feature requests, and insights into a structured backlog. ## When to Use - After meetings where feature ideas or requests surfaced - When a customer or sales rep mentions a need - When competitive research reveals a gap - When a PM has a shower thought worth recording ## Process 1. **Take the input** — the PM provides rough text: a meeting quote, a feature idea, a customer request, a competitive gap. 2. **Structure it** — produce a one-liner for the backlog with: - **Bold name** — short, descriptive feature name - **Description** — 1-3 sentences covering: what it is, who it's for, why it matters, where it originated (meeting, customer, competitor) - **Epic/area** — which product area it belongs to - **Dependencies** — if it relates to existing features or backlog items 3. **Check for duplicates** — search the existing backlog for similar items. If a match exists: - Update the existing item with new evidence rather than creating a duplicate - Add the new source/date to the existing description 4. **Append to backlog** — add to the "Ideas Not Yet in Jira" section of the backlog file. ## Output Format ```markdown - **[Feature Name]** — [Description. Who needs it. Why. Origin (meeting/customer/competitor, date).] Belongs under [Epic] epic. [Dependencies if any.] ``` ## Guidelines - **Capture fast, refine later.** The goal is not to lose the idea. Polish comes during prioritization. - **Include the source.** "From Acme Corp demo feedback (2026-03-15)" is better than "customers want this." - **Convert relative dates to absolute.** "Next Thursday" becomes "2026-04-10." - **One idea per entry.** If a meeting produced 5 ideas, create 5 entries. - **Don't validate here.** That's what `/office-hours` is for. Just capture.
© mvschwarz · Apache-2.0 · mvschwarz/openrig