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 ciaransaunders/Skills-Public --skill draco-research-promptgengit clone --depth 1 https://github.com/ciaransaunders/Skills-PublicWrote 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/ciaransaunders/skills-public/draco-research-promptgen)<a href="https://agentmods.dev/skills/ciaransaunders/skills-public/draco-research-promptgen"><img src="https://agentmods.dev/badge/skills/ciaransaunders/skills-public/draco-research-promptgen/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/ciaransaunders/skills-public/draco-research-promptgen"><img src="https://agentmods.dev/badge/skills/ciaransaunders/skills-public/draco-research-promptgen.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 | $0.00000 | $0.01404 |
| Opus 5 | $0.00000 | $0.00702 |
| Sonnet 5 | $0.00000 | $0.00281 |
| Haiku 4.5 | $0.00000 | $0.00140 |
Grade A, and why
draco-research-promptgen 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 11d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DRACO Research Prompt Generator
Transform vague research requests into prompts that maximise deep research agent performance, based on the DRACO benchmark methodology.
Core Principle: The Three Pillars
Every generated prompt MUST satisfy all three criteria simultaneously:
1. OBJECTIVITY
Clear, measurable success criteria where multiple experts would converge on what constitutes a correct answer.
Indicators of objectivity:
- Specific metrics, dates, or verifiable facts
- Named authoritative sources
- Documented information vs. opinions
- Deterministic outcomes
Red flags (make subjective):
- "Best", "should", "compelling", "interesting"
- Speculative future predictions
- Undefined quality judgments
2. BOUNDED/CONSTRAINED
Natural limits preventing endless expansion. Clear point where a complete answer has been given.
Good constraints:
- Specific number limits with objective ranking metrics ("top 5 by AUM", "3 most-cited papers")
- Time constraints ("2022–2025", "since Q3 2024")
- Geographic/domain limits ("in the EU", "for e-commerce")
- Named entities (not "top approaches" but "LoRA, full fine-tuning, and instruction tuning")
Pseudo-constraints to AVOID:
- Ungrounded "Top N" without objective metric ("top 5 challenges" — subjective)
- "Cite at least N sources" (different experts choose different sources)
- "Multiple studies" without naming which ones
3. CHALLENGING
Difficulty from complexity or synthesis, NOT from volume or tedium.
Good challenge sources:
- Synthesis across multiple named sources
- Multi-step reasoning or analysis
- Finding specific hard-to-locate information
- Domain expertise requirements
Bad (tedious, not challenging):
- Listing many items without analysis
- Kitchen-sink queries with 8+ deliverables
- Simple factual recall
The Six Augmentation Dimensions
Apply systematically to transform vague queries:
CONTEXT Dimensions
| Dimension | Action | Example |
|---|---|---|
| Persona | Add professional role context | "As a buy-side analyst conducting due diligence..." |
| Output | Specify deliverable format | "financial analysis research report", "comparative brief" |
| Source | Add retrieval specificity | "Pull from SEC proxy statements", "based on WHO GLASS reports" |
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 177 lines · 0 tokens per session scan A 0253ab701b4a
draco-research-promptgen is a skill published in the GitHub repository ciaransaunders/Skills-Public (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,404 tokens. 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 2026-08-31.
Other skills, from other repositories
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
prompt-master
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…
bedrock
AWS Bedrock foundation models for generative AI. Use when invoking foundation models, building AI applications, creating embeddings, configuring model access, or implementing RAG patterns.
few-shot-example-gen
Few-shot example generation and optimization for improved LLM performance.
chain-of-thought-prompts
Chain-of-thought and step-by-step reasoning prompts for complex problem solving.
llm-classifier
LLM-based zero-shot and few-shot classification for flexible intent detection.