DevWorth: Developer Career & Work Audit

    1

    Make your engineering work easier to explain with evidence.

    $19

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    DevWorth: Developer Career & Work Audit

    Example session with this skill installed

    Use the bundled tools on a synthetic three-commit Git repository with two authors. Filter to demo@example.invalid. Summarize only measured activity and explain what cannot be concluded. Do not research salaries or upload repository evidence.

    • Read your context and instructions
    • Compiled the devworth

    Synthetic Git evidence demo

    Actually executed the bundled Git collector, commit analyzer and timeline generator against a fictional Git repository. The fixture had three commits from two authors; filtering selected Demo Developer only.

    Measured resultValue
    Selected commits2
    Active commit dates2
    Lines added / deleted2 / 0
    Python file-change records2
    January 2026 commits1
    February 2026 commits1
    Weekend commit share0.5
    After-hours commit share0.5
    Network requests0

    Verified that the other author's commit was excluded and an unmatched author filter returned zero commits. The actual JSON outputs are included as examples/synthetic-summary.json and examples/synthetic-timeline.json.

    Interpretation limits: the two timestamp patterns carry LOW confidence and do not measure work hours. This tiny fixture does not establish engineering level, production ownership, compensation fairness or salary. A real audit must inspect representative diffs, validate ownership and outcomes, record missing non-Git work, and use dated regional sources before discussing compensation.

    Next step: run the same local collection on an authorized repository and have the agent produce the Evidence Ledger using the five included guides. examples/sample-audit.md separately illustrates a fictional report format; its career conclusions are not claimed as test results.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Make your engineering work easier to explain with evidence. DevWorth guides a coding agent through Git history, representative diffs, project complexity and responsibility to prepare a structured developer career report.

    Choose a full audit, workload review, promotion evidence, portfolio selection, sourced compensation discussion, freelance pricing or a direct career reality check. The workflow separates facts, inferences and speculation, attaches confidence to an Evidence Ledger, and distinguishes technical skill from responsibility.

    Included: one SKILL.md entry point; five guides for methodology, scoring, compensation, fairness and report structure; three local scripts for Git collection, commit summaries and monthly timelines; an illustrative fictional audit; actual synthetic demo outputs; MIT license.

    The scripts collect and summarize evidence locally. They do not determine seniority or pay automatically. Commit counts are not a skill score, timestamps are not hours worked, and file-path domain labels require human review. A useful career report also needs representative code and context about ownership and outcomes. Compensation ranges must use current, dated sources for the user's region; no salary dataset is bundled.

    Keep private code, author details and employment information local unless you explicitly authorize sharing. No guaranteed raise, hiring outcome, legal advice, hosted service or support subscription is included. The development repository is private; the delivered source package retains its included MIT license.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Research & Analysis.

    Git counts and file-path hints require interpretation; timestamps do not measure hours worked. Full audits need representative diffs, ownership and non-Git work context. No salary dataset, guaranteed raise or hiring result is included. Compensation requires current dated sources for the buyer’s region.

    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 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

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 7 days ago

    Software
    GitPython 3.10+Bash

    Git evidence stays local by default. Browser/network access is optional for current regional salary sources. Bash is available through Git for Windows or WSL.

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Network Access
    Browser

    Read buyer-authorized local Git history and source files; run the bundled Bash/Python tools; write local evidence files and reports. Git evidence can contain emails, paths and confidential work. Do not upload it by default. Network/browser use is optional for current public compensation sources and requires the buyer’s context; no telemetry, tokens or external service is required by the scripts.

    Listed7 days ago

    What's inside

    Frequently Asked Questions

    Use a buyer-authorized local Git repository. Exported logs can support a narrower review, but interpreting architecture and code complexity needs representative source and diffs. No production server or cloud credentials are required.

    DevWorth supplies a repeatable evidence-collection workflow, five audit guides and a report template. Claims should cite evidence with confidence labels. A coding agent can still make mistakes, so review its interpretation and missing context.

    The scripts summarize selected commits, file changes and monthly activity. An agent then reviews code and responsibility evidence to draft a report and Evidence Ledger. Git counts alone do not establish level, hours, ownership or fairness.

    One SKILL.md entry point, five audit guides, three local Git/Bash/Python tools, a fictional report example, actual synthetic demo outputs, README and MIT license. No salary dataset, hosted service or support subscription is included.

    No. Commit timestamps are low-confidence activity signals, not a timesheet, and cannot establish billable hours or total work time.

    Yes. Modes include a full audit, workload review, promotion evidence, portfolio selection, sourced compensation discussion, freelance pricing and a direct career reality check. Outputs require review and do not guarantee a raise or promotion.

    New in Research & Analysis