More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Shortread: long content cut to what matters

    1

    Turns transcripts, docs and threads into a short TLDR, ranked key points, action items with owners, decisions and open questions.

    Free

    1 useSecurity scanned
    Shortread: long content cut to what matters

    Shortread: long content cut to what matters

    Example session with this skill installed

    Shortread docs/api-specs.md --full

    • Read your context and instructions
    • Compiled the shortread

    I have processed the API specification document. Here is the full summary including all technical sections and supporting context.

    TLDR

    The v2 API transitions from REST to GraphQL to reduce over-fetching, centering on a new unified /query endpoint. Migration completes by Q4, with legacy support maintained for 6 months.

    KEY POINTS

    1. Schema Unification: All microservices will expose their data through a central Apollo Gateway.
    2. Breaking Changes: The /v1/users and /v1/orders endpoints are deprecated effective immediately.
    3. Rate Limiting: New tier-based limits enforced via Redis: 1k req/min for Basic, 10k req/min for Pro.
    4. Auth Update: JWTs now require a kid header for rotating public key validation.
    5. Performance Target: P99 latency must stay under 200ms for the gateway layer.

    ACTION ITEMS
    ☐ @backend-team: Implement Redis rate-limiting middleware by July 15.
    ☐ @dev-docs: Update Postman collections to include GraphQL fragments by July 20.
    ☐ @security: Audit new JWT validation logic.

    NOTABLE QUOTES

    "We cannot support two paradigms indefinitely; the six-month sunset is non-negotiable.": CTO
    "Performance overhead of the gateway is currently 15ms, well within budget.": Lead Architect

    DECISIONS MADE

    • Adopt GraphQL for all new client-facing features.
    • Use Redis for distributed rate limiting instead of local memory.
    • Maintain /v1 endpoints until December 31.

    OPEN QUESTIONS

    • Will the mobile app require a local schema cache?
    • Final pricing tiers for the new API rate limits.

    Next steps

    • Review the Action Items for your specific owner tags.
    • Use Clearcut for the new JWT validation flow if needed.
    • Schedule the security audit mentioned in the action items.

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

    About this skill

    Manual summarization wastes time and often misses the core signal in a sea of filler. This skill compresses long-form content, transcripts, and codebases into structured, high-density briefs without editorial fluff.

    What it does

    • Multi-source compression converts documents, URLs, transcripts, or entire directory structures into structured summaries.
    • Priority ranking organizes key points by objective importance rather than their order of appearance in the source.
    • Actionable extraction lists concrete tasks with owners and drops vague ones like "discuss further".
    • Decision logging captures specific outcomes and open questions to prevent context loss in long threads.
    • Verbatim preservation ensures that dates, percentages, and currency values remain exact to prevent data drift.

    How it works

    1. Target selection by passing a file path, URL, or pasted text to the command.
    2. Mode adjustment using flags like --brief, --full, or --outline to control the depth of information.
    3. Structured parsing where the agent identifies direct quotes, decisions, and action items according to the source content.

    Frameworks & tools

    This tool is language-agnostic and works with Markdown, plain text, and source code. It integrates with existing project contexts by reading README files and manifests to maintain consistent terminology.

    Why this beats prompting it yourself

    Generic prompts often lead to polite filler and "this document discusses" introductions that waste vertical space. This skill enforces strict token discipline and uses specific data extraction rules to ensure every line provides information, not just a description of information.

    Use cases

    • Summarize 60-minute meeting transcripts into owner-assigned action items.
    • Generate high-level overviews of new codebases for rapid onboarding.
    • Distill long technical PRDs into brief TLDRs for executive stakeholders.
    • Extract core decisions and unresolved questions from long Slack or Discord threads.

    Known limitations

    The skill requires the target content to be accessible within the agent's current environment or via provided URL. Length limits are subject to the underlying model's context window.

    Requires environment access to files or URLs. Output quality depends on the clarity of the source text. Ambiguous content will be flagged as unclear rather than interpreted.

    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

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 29 days ago

    • Free with an Agensi account

    Permissions

    Read Files
    Listed29 days ago

    What's inside

    Frequently Asked Questions

    Unlike generic AI prompts that add conversational filler, this skill uses strict token discipline and priority ranking to extract only high-density facts, action items, and data without editorial fluff.

    It is language-agnostic and supports various formats including Markdown, plain text, and source code, and can even parse entire directory structures or URLs.

    The skill includes specific flags like --brief, --full, or --outline, allowing you to control the depth of information based on whether you need an executive TLDR or a detailed technical overview.

    Yes, the skill is designed to read README files and manifests to ensure that all generated summaries use the specific terminology and technical context of your existing project.

    The skill is constrained by the underlying model's context window; however, it is optimized for high-density compression to handle large documents and transcripts efficiently.

    One SKILL.md with the output format, the length modes (--brief, --full, --outline) and the rules. It is free.

    New in Writing & Content