duplicate-request-merging
Skill0 starsChanged 17 days agoMITView on GitHub
Find feature requests, ideas, or tickets that describe the same underlying need in different words, merge them into one clean request, and keep every requester and piece of evidence attached. Use when someone shares a backlog, ideas board, Productboard or Canny export, or request spreadsheet and asks to dedupe, consolidate, clean up, or find duplicates, or wants an accurate count of how many customers asked for something.
In this repository33 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- beta-program-managerSkill
- cross-team-dependency-mapSkill
- customer-advisory-board-prepSkill
- data-request-routerSkill
- decision-logSkill
- deprecation-planSkill
- experiment-logSkill
- feature-flag-trackingSkill
- feedback-taggingSkill
- information-debt-auditSkill
- internal-enablement-briefSkill
- kpi-health-checkSkill
- launch-readiness-checklistSkill
- meeting-to-action-converterSkill
- new-pm-onboarding-packSkill
- pricing-packaging-change-logSkill
- process-documentationSkill
- product-metrics-definitionsSkill
- product-ops-contextSkill
- quarterly-planning-prepSkill
- raci-builderSkill
- release-notes-draftingSkill
- request-intake-triageSkill
- retro-facilitationSkill
- ritual-calendarSkill
- roadmap-hygieneSkill
- sprint-review-summarySkill
- support-escalation-patternsSkill
- tool-stack-auditSkill
- vendor-evaluation-scorecardSkill
- voice-of-customer-digestSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Distinctive: line 18
Read every request and write the need behind it in plain words.
- Distinctive: line 24
Don't merge when:
- Distinctive: line 29
When unsure, list the pair as "possible duplicate" for a person to decide rather than merging.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Duplicate request merging
The same need gets filed five ways: "CSV export," "download my data," "get reports into Excel," "export button," "send data to finance." Counted separately, each looks minor. Merged, it's one of the top asks. Merging done carelessly, though, hides real differences.
Before you start
If .agents/product-ops-context.md exists (or .claude/product-ops-context.md), read it first. Use the team, owners, tools, meetings, and metric definitions it already has, and only ask for what's missing or specific to this task. If it doesn't exist, go ahead with what you're given, and suggest running product-ops-context once so the next skill doesn't have to ask.
Step 1: Group by underlying need
Read every request and write the need behind it in plain words. Group requests whose needs match, even if the proposed solutions differ.
Merge when requests share the same:
- Job: what the customer is trying to get done
- Outcome: what "solved" looks like for them
Don't merge when:
- The same words mean different things ("permissions" for admins vs. for end users)
- One request is a narrow subset of another and needs separate tracking
- They need the same feature but for clearly different reasons that would change how it's built
When unsure, list the pair as "possible duplicate" for a person to decide rather than merging.
Step 2: Write the merged request
For each group:
### [Merged title: the need, in plain words]
- **Need:** [one or two sentences]
- **Variations asked for:** [the different solutions people proposed]
- **Requesters:** [N] — [names or accounts]
- **Segments:** [plan, size, industry, as available]
- **Evidence:** [revenue at stake, quotes, deal or renewal links, as given]
- **Merged from:** [IDs or titles of original requests]
- **Keep as primary:** [ID of the original to keep, usually the oldest or most detailed]Count requesters as unique accounts or people, not original requests. One account filing three times is one requester. Compute counts with real arithmetic.
Step 3: Output
# Request dedupe — [Source] — [Date]
**Summary:** [N] requests reviewed → [N] unique needs · [N] merged groups · [N] possible duplicates
## Merged groups (largest first)
[Entries from Step 2]
## Possible duplicates (need a decision)
| Request A | Request B | Why they might match | Why they might not |
## Unique requests
[Short list]Recommend merges; don't delete or merge records in any tool yourself. Never drop a requester or piece of evidence during a merge.
Related skills
- request-intake-triage — sort new asks first
- feedback-tagging — tag the merged requests consistently
- roadmap-hygiene — connect merged requests to roadmap items
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

