Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add alivirgo/Major-AI-Skills --skill dont-summarize-without-a-goalgit clone --depth 1 https://github.com/alivirgo/Major-AI-SkillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/alivirgo/major-ai-skills/dont-summarize-without-a-goal)<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/dont-summarize-without-a-goal"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/dont-summarize-without-a-goal/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/dont-summarize-without-a-goal"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/dont-summarize-without-a-goal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00023 | $0.01070 |
| Opus 5.5 | $0.00009 | $0.00428 |
| Sonnet 5.5 | $0.00005 | $0.00214 |
| Haiku 4.5 | $0.00002 | $0.00107 |
Grade A, and why
dont-summarize-without-a-goal scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Don't Summarize Without a Goal (Goal-Directed Extraction) (AI Skill)
Overview
Typing "Summarize this document" is one of the most common - and least effective - prompts in generative AI. Because the model doesn't know why you are reading the document, it defaults to a balanced, generic overview that often omits the exact metrics, dates, or risks you actually care about.
The Goal-Directed Extraction Protocol anchors the AI to a specific persona, decision objective, or lens before reading, ensuring 100% of the output is actionable.
Generic Summaries vs. Goal-Directed Extraction
┌─────────────────────────────────────────────────────────────┐
│ Generic vs. Goal-Directed Flow │
│ │
│ Generic Prompt ("Summarize this 40-page RFP"): │
│ • AI writes 5 paragraphs summarizing company history, │
│ introduction, high-level mission, and team bios. │
│ • 0% of the financial terms or deadlines are highlighted. │
│ │
│ Goal-Directed Prompt ("Extract costs, SLAs, & deadlines"): │
│ • AI outputs a 1-page structured breakdown: │
│ 1. Pricing tiers & setup fees │
│ 2. Hard delivery milestones & penalties │
│ 3. Uptime commitments & SLA credits │
└─────────────────────────────────────────────────────────────┘
Master Goal-Directed Prompt Templates
Pattern 1: The Persona-Driven Lens
Use when analyzing reports for different stakeholders:
Read the attached document: [ATTACH REPORT / PASTE TEXT].
Summarize this document through the lens of a **Chief Financial Officer (CFO)**.
Focus exclusively on:
1. All hard costs, recurring fees, and margin impacts.
2. Capital expenditure (CapEx) vs. Operational expenditure (OpEx) commitments.
3. Financial risk exposure or liability caps.
Ignore background narratives and general marketing descriptions.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · -16 tokens per session 7f64d96e8dcd
- 1mo ago First seen · 107 lines · 39 tokens per session scan A 34bc4ea5c8df
dont-summarize-without-a-goal is a skill published in the GitHub repository alivirgo/Major-AI-Skills (2 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 1,070 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other skills, from other repositories
box-automation
Automate Box cloud storage operations including file upload/download, search, folder management, sharing, collaborations, and metadata queries via Rube MCP (Composio). Always search tools first for...
oracle-confidentiality
Enforce confidentiality across Oracle deliverables — pre-delivery audits, codename enforcement, and content sanitization. Use before any Oracle client handoff, when sanitizing documents, or when checking deliverables for confidential leaks.
atelier-setup
Configure a repository for Atelier's development workflow. Use only when explicitly invoked; inspect existing guidance, issue-tracker and domain-document conventions, preview the proposed configuration, and write only after approval. It does not install Atelier or initialize external tooling.
azure-document-intelligence
Expert knowledge for Azure AI Document Intelligence development including troubleshooting, best practices, decision making, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when using AnalyzeDocument APIs, custom/classification/template models, batch analysis, containers…
azure-content-understanding
Expert knowledge for Azure Content Understanding in Foundry Tools development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, and integrations & coding patterns. Use when designing Content Understanding analyzers, RAG document flows…
managing-artifacts
Artifact storage paths and project-encoded conventions for generated documents, reports, plans, and audits. Loaded by the core rule module. Triggers: 'where should I put this', 'save report', 'output directory'.