- Home
- Skills
- Agents & Orchestration
- dsh-skill-radar
Dsh Skill Radar
Skill usage radar for DeepSeek Harness: records every skill hit and ranks skills by the last 7 days.
Free
Works with the AI Agents you already use
dsh-skill-radar
Example session with this skill installed
Show me which DeepSeek Harness skills I actually used in the last 7 days, and which ones never fired.
- Read your context and instructions
- Compiled the dsh--radar
Skill usage radar — last 7 days
Most used
- code-review — 42 hits, 9 sessions, triggers: pull-request, diff, review
- test-runner — 31 hits, 7 sessions, triggers: test, pytest, vitest
- doc-writer — 18 hits, 5 sessions, triggers: docs, readme, changelog
Quiet but useful
- release-notes — 4 hits, 2 sessions, trigger: release
- lint-fix — 3 hits, 2 sessions, trigger: lint
Never fired — consider archiving
- old-migration-helper — 0 hits in 7 days
- legacy-deploy — 0 hits in 7 days
Recommendation
Archive old-migration-helper and legacy-deploy until they are needed again. Keep code-review, test-runner and doc-writer front and centre — together they account for most recent skill use.
Connects securely to your tools. The creator never sees your data.
About this skill
Skill usage radar for DeepSeek Harness: records every skill hit with time, session and trigger, ranks skills by the last 7 days, and suggests archiving the ones that never fire.
Source code: https://github.com/dingchenhui0618-arch/dsh-skill-radar — the GitHub version stays free and is the canonical source. This is a non-exclusive listing.
Created by Ding Chenhui (dingchenhui0618@gmail.com). Licensed under the MIT Licence — see LICENSE in the package.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.
Requires DeepSeek Harness version >=0.2.0-rc.2 and <0.3.0. Management actions like archiving rely on a .trash folder.
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 8 days ago
- Free with an Agensi account
- Software
Git