draco-research-promptgen

draco-research-promptgen is a skill for Claude Code, Codex from ciaransaunders/Skills-Public. It costs 0 tokens per session (1,404 once invoked), scanned A, original, MIT.

A prompt-writing skill based on the DRACO research benchmark. It turns broad research requests into instructions with clear goals, limits, and ways to verify the result.

In plain words
What is it for?
Use it to rewrite a research request into a prompt with objective success criteria, a defined scope, time or domain limits, and specified entities or sources. It is for improving research instructions, not for conducting the research itself.
Why use it?
Vague research questions can produce answers that are subjective, too broad, or difficult to check. This skill adds measurable criteria, named sources, and boundaries to make the requested research more focused.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to rewrite a research request into a prompt with objective success criteria, a defined scope, time or domain limits, and specified entities or sources. It is for improving research instructions, not for conducting the research itself.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ciaransaunders/skills-public/draco-research-promptgen
Install

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.

Any agent
npx skills add ciaransaunders/Skills-Public --skill draco-research-promptgen
Clone the repo
git clone --depth 1 https://github.com/ciaransaunders/Skills-Public

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for draco-research-promptgen

README.md
[![agentmods](https://agentmods.dev/badge/skills/ciaransaunders/skills-public/draco-research-promptgen/github.svg)](https://agentmods.dev/skills/ciaransaunders/skills-public/draco-research-promptgen)
Your own site
<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.

agentmods 80×15 button for draco-research-promptgen

Your own site · 80×15
<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>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,404 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 11d ago against content hash 0253ab701b4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

draco-research-promptgen/SKILL.md · 177 lines

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"

Read the full file on GitHub · 177 lines

Files

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.

Changes

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.

  1. 11d ago First seen · 177 lines · 0 tokens per session scan A 0253ab701b4a

Subscribe to this mod's changes

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.