Source profileQuality 75/100Review permissions

mediause/agent-skills/chatgpt/SKILL.md

chatgpt

Standardized ChatGPT skill for MediaUse. Includes Windows install, key onboarding, strict context/auth flow, full ChatGPT dynamic command map, and safety/rate controls.

Source repository stars
9
Declared platforms
0
Static risk flags
2
Last source update
2026-07-28
Source checked
2026-07-28
DecisionCompatibilityInstallWorkflowPermissionsEvidenceSource

Decision brief

What it does—and where it fits

Use this skill to run structured ChatGPT workflows in MediaUse, including conversation control, prompt/response retrieval, and image generation with safe execution pacing.

Best for

    Not for

    • Tasks that require unconfirmed production actions or broad system permissions.
    • Environments where the pinned source and install steps cannot be inspected.

    Compatibility matrix

    Platform support, with evidence labels

    PlatformStatusEvidenceWhat to check
    CodexNot declaredNo explicit evidencePortability before use
    Claude CodeNot declaredNo explicit evidencePortability before use
    CursorNot declaredNo explicit evidencePortability before use
    Gemini CLINot declaredNo explicit evidencePortability before use
    Open the compatibility checker

    Installation

    Inspect first. Install second.

    The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.

    Source-detected install commandSource
    npx skills add https://github.com/mediause/agent-skills --skill "chatgpt"
    Safe inspection promptEditorial

    Inspect the Agent Skill "chatgpt" from https://github.com/mediause/agent-skills/blob/766e5075b28b3acd541436a7e3b3e21cdc38da01/chatgpt/SKILL.md at commit 766e5075b28b3acd541436a7e3b3e21cdc38da01. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.

    Workflow

    What the source asks the agent to do

    1. 01

      3.1 Discover and plugin setup

      Review the “3.1 Discover and plugin setup” section in the pinned source before continuing.

      Review and apply the “3.1 Discover and plugin setup” source section.
    2. 02

      6. Workflow Examples

      Review the “6. Workflow Examples” section in the pinned source before continuing.

      Review and apply the “6. Workflow Examples” source section.
    3. 03

      6.1 Ask and read workflow

      Review the “6.1 Ask and read workflow” section in the pinned source before continuing.

      Review and apply the “6.1 Ask and read workflow” source section.
    4. 04

      6.2 Conversation history and detail workflow

      Review the “6.2 Conversation history and detail workflow” section in the pinned source before continuing.

      Review and apply the “6.2 Conversation history and detail workflow” source section.
    5. 05

      6.3 New conversation and image generation workflow

      Review the “6.3 New conversation and image generation workflow” section in the pinned source before continuing.

      Review and apply the “6.3 New conversation and image generation workflow” source section.

    Permission review

    Static risk signals and limitations

    Runs scripts

    medium · line 20

    The documentation asks the agent to run terminal commands or scripts.

    Before every run, execute the install script once to auto-install or auto-upgrade to the latest MediaUse CLI.

    Network access

    medium · line 25

    The documentation includes network, browsing, or remote request actions.

    powershell -C "iwr https://release.mediause.dev/install.ps1 -UseBasicParsing | iex"

    Runs scripts

    medium · line 63

    The documentation asks the agent to run terminal commands or scripts.

    First step on every run: execute install script once to auto-install/auto-upgrade the latest MediaUse CLI.

    Network access

    medium · line 265

    The documentation includes network, browsing, or remote request actions.

    powershell -C "iwr https://release.mediause.dev/install.ps1 -UseBasicParsing | iex"

    Evidence record

    Why each signal appears

    EvidenceSourceComputedTestedEditorial
    SignalValueEvidence typeMeaning
    Quality score75/100ComputedDocumentation, specificity, maintenance, and trust rules
    Repository stars9SourceRepository attention, not individual Skill quality
    Compatibility0 platformsSourceDeclared in the catalog source record
    Usage guideautomated source guideEditorialGenerated or reviewed according to the visible evidence level

    Pinned source

    Provenance and original SKILL.md

    Repository
    mediause/agent-skills
    Skill path
    chatgpt/SKILL.md
    Commit
    766e5075b28b3acd541436a7e3b3e21cdc38da01
    License
    Not declared
    Collected
    2026-07-28
    Default branch
    master
    View the original SKILL.md

    MediaUse ChatGPT Skill

    Use this skill to run structured ChatGPT workflows in MediaUse, including conversation control, prompt/response retrieval, and image generation with safe execution pacing.

    Scope

    Use this skill when the task targets ChatGPT operations such as:

    • Account: health check
    • Chat: status, new conversation, send/ask prompts, read/history/detail
    • Image: generate images from prompts

    1. Install MediaUse CLI (Windows Only)

    Use the official install script for Windows:

    Run:

    powershell -C "iwr https://release.mediause.dev/install.ps1 -UseBasicParsing | iex"

    Then verify :

    mediause --version

    Current support status:

    • Windows: supported
    • Linux: not supported yet
    • macOS: not supported yet

    Recommended skill install path:

    • .mediause/skills/chatgpt/SKILL.md

    2. Get and Configure MediaUse Key

    2.1 Apply for key

    1. Open https://mediause.dev/
    2. Sign in to your account.
    3. Open Project.
    4. Create or copy your API key.

    2.2 Configure key in CLI

    mediause manage key <your_key> --json

    3. Core Flow (Mandatory Order)

    Always follow this order:

    First step on every run: execute install script once to auto-install/auto-upgrade the latest MediaUse CLI.

    1. Discover site and commands.
    2. Bind account context with use account.
    3. Check status with auth health.
    4. Execute dynamic site actions.
    5. Verify with trace/task.

    3.1 Discover and plugin setup

    mediause plugin list --json
mediause plugin add chatgpt --json
mediause chatgpt -h
mediause chatgpt chat -h

    3.2 Bind context before any read/write

    use account must be executed successfully before any fetch or interaction action.

    use account argument format:

    • <platform:account_id>
    • account_id should be selected from mediause auth list --json.

    By default, use account keeps the browser hidden. Use --show when manual observation or takeover is needed.

    mediause auth list --json
mediause use account chatgpt:<account_id> --policy balanced --json

    3.3 Auth health precondition

    auth health is valid only after successful use account.

    mediause auth health --json

    If auth health indicates not logged in/expired:

    mediause auth login chatgpt --json
mediause use account chatgpt:<account_id> --policy balanced --json
mediause auth health --json

    If page shows unusual traffic, captcha, or risk confirmation:

    mediause use account chatgpt:<account_id> --policy balanced --show --json

    Risk reduction note:

    • In challenged sessions, --show usually reduces repeated interception risk.

    Complete verification manually, then rerun the action.

    3.4 Guest mode (optional)

    Manifest default account id is guest. Guest mode can be used only for read/chat actions when the runtime supports unauthenticated chatgpt:guest context (that is, mediause use account chatgpt:guest --json succeeds):

    mediause use account chatgpt:guest --json

    Guest mode rules:

    • Read/chat operations only (chat.status, chat.new, chat.send, chat.ask, chat.read, chat.history, chat.detail).
    • image.generate may require logged-in account depending on current runtime and page state.
    • If action is blocked in guest mode, switch to logged-in account context.

    4. ChatGPT Dynamic Command Map (v1)

    Source schema:

    • plugin: plugin.chatgpt
    • manifest: crates/platforms/plugins/chatgpt/manifest.yaml

    4.1 account.*

    • mediause chatgpt account health --json

    4.2 chat.*

    • mediause chatgpt chat status --json
    • mediause chatgpt chat new --json
    • mediause chatgpt chat send --prompt <text> [--new <bool>] --json
    • mediause chatgpt chat ask --prompt <text> [--timeout <seconds>] [--new <bool>] --json
    • mediause chatgpt chat read [--markdown <bool>] --json
    • mediause chatgpt chat history [--limit <n>] --json
    • mediause chatgpt chat detail --id <conversation_id> [--markdown <bool>] --json

    4.3 image.*

    • mediause chatgpt image generate --prompt <text> [--timeout <seconds>] --json

    5. Operational Constraints (Mandatory)

    Apply these constraints for all actions to reduce account risk and keep behavior stable.

    5.1 Human-like pacing

    • Never execute high-frequency prompt bursts continuously.
    • Add randomized delay between repeated prompt/image requests.
    • Add longer cooldown after long-running ask/generate operations.

    5.2 Frequency limits and minimum spacing

    • Hard stop if operation rate is abnormally high.
    • Stop immediately on repeated anti-bot challenge, login re-validation, or risk prompt.

    Quick policy matrix:

    • chat.ask / chat.send: <= 30 per hour, >= 5s spacing
    • image.generate: <= 10 per hour, >= 30s spacing
    • chat.read / chat.history / chat.detail / chat.status: <= 60 per minute, >= 1s spacing

    If a limit is hit:

    1. Pause at least 10 minutes.
    2. Resume with read/status actions first.
    3. Re-check session health before interaction actions.

    5.3 Safety policy

    • Do not bypass platform protections.
    • Do not attempt credential scraping or session hijacking.
    • Respect platform terms and local regulations.

    5.4 Output and error handling

    • Prefer --json output for machine workflows.
    • Require structured error handling with stable fields/code when available.
    • On blocked/rate-limit/risk prompt, stop and return actionable next steps.

    6. Workflow Examples

    6.1 Ask and read workflow

    mediause use account chatgpt:<account_id> --json
mediause auth health --json
mediause chatgpt chat ask --prompt "Summarize latest Rust async patterns" --timeout 90 --json
mediause chatgpt chat read --markdown true --json
mediause trace last --json

    6.2 Conversation history and detail workflow

    mediause use account chatgpt:<account_id> --json
mediause auth health --json
mediause chatgpt chat history --limit 20 --json
mediause chatgpt chat detail --id <conversation_id> --markdown true --json
mediause trace last --json

    6.3 New conversation and image generation workflow

    mediause use account chatgpt:<account_id> --json
mediause auth health --json
mediause chatgpt chat new --json
mediause chatgpt image generate --prompt "minimal poster design, geometric, red black white" --timeout 120 --json
mediause trace last --json

    7. Execution Checklist

    Before run:

    Before every run, execute the install script once.

    1. CLI installed via https://release.mediause.dev/install.ps1 on Windows.
    2. PATH updated and mediause --version works.
    3. API key configured and verified.
    4. Account context bound via mediause use account chatgpt:<account_id> --json.
    5. If guest mode is used, verify the target action is actually supported in guest context.
    6. If manual verification may be needed, be ready to rerun use account with --show.
    7. Pacing policy is enabled.

    During run:

    1. Respect delays and minimum spacing.
    2. Stop on anti-bot/risk prompts.
    3. If unusual traffic appears, rerun mediause use account chatgpt:<account_id> --show --json and complete verification manually.
    4. Avoid repetitive burst loops.

    After run:

    1. Save logs and outcomes.
    2. Record any risk warning and cooldown events.
    3. Keep activity under conservative limits.

    8. Quick Command Reference

    # always run once before each workflow (auto-upgrade latest)
powershell -C "iwr https://release.mediause.dev/install.ps1 -UseBasicParsing | iex"
mediause --version

# discover
mediause plugin list --json
mediause plugin add chatgpt --json
mediause chatgpt -h
mediause chatgpt chat -h

# context + status
mediause auth list --json
mediause use account chatgpt:<account_id> --json
mediause use account chatgpt:<account_id> --show --json
mediause auth health --json

# chat actions
mediause chatgpt account health --json
mediause chatgpt chat status --json
mediause chatgpt chat new --json
mediause chatgpt chat send --prompt "Draft a release note" --json
mediause chatgpt chat ask --prompt "Explain CAP theorem in simple terms" --timeout 90 --json
mediause chatgpt chat read --markdown true --json
mediause chatgpt chat history --limit 10 --json
mediause chatgpt chat detail --id <conversation_id> --markdown true --json

# image action
mediause chatgpt image generate --prompt "isometric dashboard illustration" --timeout 120 --json

# trace
mediause trace last --json

    Skill Metadata Maintainer: @mediause-demo Last-Updated: 2026-05-21 Version: v1

    Alternatives

    Compare before choosing

    Computed 997

    event4u-app/agent-config

    design-review

    Use when the user says "review the design", "check the UI", or wants a comprehensive UI/UX review. Uses a 7-phase methodology covering interaction, responsiveness, accessibility, and more.

    2026-07-280 platforms
    Computed 9831,966

    K-Dense-AI/scientific-agent-skills

    dask

    Distributed computing for larger-than-RAM pandas/NumPy workflows. Use when you need to scale existing pandas/NumPy code beyond memory or across clusters. Best for parallel file processing, distributed ML, integration with existing pandas code. For out-of-core analytics on single machine use vaex; for in-memory speed use polars.

    2026-07-280 platforms
    Computed 9831,966

    K-Dense-AI/scientific-agent-skills

    medchem

    Medicinal chemistry filters for compound triage. Apply drug-likeness rules (Lipinski, Veber, CNS), structural alert catalogs (PAINS, NIBR, ChEMBL), complexity metrics, and the medchem query language for library filtering.

    2026-07-280 platforms
    Computed 9831,966

    K-Dense-AI/scientific-agent-skills

    neurokit2

    Use NeuroKit2 to build or audit reproducible research workflows for physiological time-series preprocessing, event/interval analysis, multimodal alignment, variability, and complexity. Trigger when code imports neurokit2 or needs its current APIs, schemas, and method-aware validation—not for diagnosis or device validation.

    2026-07-280 platforms