Dsh Skill Radar

    1

    Skill usage radar for DeepSeek Harness: records every skill hit and ranks skills by the last 7 days.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    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

    1. code-review — 42 hits, 9 sessions, triggers: pull-request, diff, review
    2. test-runner — 31 hits, 7 sessions, triggers: test, pytest, vitest
    3. 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.

    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. 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. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    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 forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 8 days ago

    • Free with an Agensi account

    Requires

    Git

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Network Access
    Environment Variables
    Listed8 days ago

    What's inside

    Frequently Asked Questions

    dsh skill radar automates usage monitoring by tracking every invocation, allowing you to identify which DeepSeek Harness skills are providing value and which are cluttering your workspace.

    This skill is specifically engineered for DeepSeek Harness versions 0.2.0-rc.2 through 0.3.0; it is not compatible with older versions or other agent frameworks.

    Setup is simple: install the plugin via the 'dsh plugin' command and restart your environment to access the analytics dashboard within your active sessions.

    The 'Archive' feature moves zero-hit skills into a designated '.trash' folder, keeping your workspace clean while allowing you to restore them later if needed.

    You receive the full dsh skill radar plugin, including the usage tracking engine, the 7-day activity dashboard, and the integrated lifecycle management tools.

    New in Agents & Orchestration