- Home
- Skills
- Code Quality & Review
- feedback no duplicate docs
feedback no duplicate docs
Enforce a single source of truth by preventing duplicate tracking, TODO, and checklist documents in your repository.
Free
Works with the AI Agents you already use
feedback no duplicate docs
Example session with this skill installed
Create a list of verification steps for the upcoming production deployment to track our progress.
- Read your context and instructions
- Compiled the feedback no duplicate
I have checked the repository for existing tracking documents and found tasks/CHECKLIST.md. Instead of creating a new file, I have added the deployment verification steps as a new section in the existing checklist to maintain a single source of truth.
Updated tasks/CHECKLIST.md
# Project Checklist
## Existing Tasks
- [x] Configure CI/CD pipeline
- [x] Set up staging environment
## Deployment Verification (New)
- [ ] Verify SSL certificate expiry on production
- [ ] Run smoke tests against the load balancer endpoint
- [ ] Check Prometheus alerts for 5xx spikes
- [ ] Validate database migration version in RDS
- [ ] Confirm CDN cache invalidation completion
Next steps
- Review the new Deployment Verification section in
tasks/CHECKLIST.md. - Let me know if you prefer these steps to be in a dated version instead (e.g.,
REGRESSION_2026_06_20.md). - I can add links to this section from your
README.mdfor quicker access.
Connects securely to your tools. The creator never sees your data.
About this skill
Repo bloat and document drift happen when agents create new files for tasks that already have a home. Parallel tracking documents lead to outdated information, lost context, and a fragmented source of truth. This skill forces a "search-before-write" workflow to ensure checklists, TODOs, and roadmaps stay consolidated.
What it does
- Prevents duplication by identifying existing tracking files before a new one is initialized.
- Consolidates tracking by preferring
Editoperations on existing.mdfiles over creating new ones. - Automates discovery using targeted glob patterns for common document types like checklists, bug logs, and roadmaps.
- Self-corrects misses by providing a recovery flow to migrate content and delete redundant files if a duplicate was already created.
How it works
- Search phase triggered before any
.mdwrite in the repo root,tasks/, ordocs/directories. - Analysis phase to determine if the new content is orthogonal or belongs in an existing candidate file.
- Consolidation phase where the agent extends the existing document section or asks the user for the authoritative file.
- Cleanup phase to delete duplicates and update cross-references if a miss occurs.
Frameworks & tools
Works with any repository structure using Markdown for documentation. Optimized for agents with filesystem access tools like Glob, Edit, and Write.
Why this beats prompting it yourself
Generic prompts often fail to check the full directory tree before generating output, leading to TODO_v2.md or REGRESSION_NEW.md clutter. This skill encodes specific search heuristics and a "Single Source of Truth" logic that enforces repository hygiene automatically.
Use cases
- Adding deploy verification steps to an existing project checklist.
- Appending new bugs to a central
BUG.mdinstead of creating a new task file. - Updating an existing sprint roadmap with deferred items.
Known limitations
Does not apply to genuinely unique artifacts with a different audience or angle. Requires the agent to have filesystem search capabilities.
How to use
Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scanned
Verified clean today
- Free to download with an account