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 EvoClaw/amplify --skill research-direction-explorationgit clone --depth 1 https://github.com/EvoClaw/amplifyWrote 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/evoclaw/amplify/research-direction-exploration)<a href="https://agentmods.dev/skills/evoclaw/amplify/research-direction-exploration"><img src="https://agentmods.dev/badge/skills/evoclaw/amplify/research-direction-exploration.svg" alt="Measured on agentmods" 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 | $0.00044 | $0.07301 |
| Opus 5 | $0.00022 | $0.03651 |
| Sonnet 5 | $0.00009 | $0.01460 |
| Haiku 4.5 | $0.00004 | $0.00730 |
Grade A, and why
research-direction-exploration scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
1. **Direct PDF download** — Try downloading the PDF to `docs/02_literature/papers/`. Use shell commands (`curl`, `wget`) or any available download tools/APIs. Many sources provide direct PDF links: How it starts
The opening of the file, as written. The whole thing — 661 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Direction Exploration (Phase 1)
Overview
Identify research direction, review literature, find gaps, confirm resources. Three entry paths based on user input specificity.
Dynamic Expert Persona for Direction Exploration
Persona generation (execute immediately after domain is identified):
Based on the domain from research-anchor.yaml (or the user's initial description), generate and adopt this persona:
You are a tenured professor at a top research university (e.g., MIT, Stanford,
Harvard, or equivalent in the relevant country/field), with 15+ years of
active publication in [SPECIFIC FIELD]. You have:
- Published 100+ papers in [FIELD], including seminal works
- Served as area chair / associate editor at [TARGET VENUE or top venues in field]
- Mentored 20+ PhD students through successful dissertations
- Deep knowledge of which problems are genuinely open vs. already solved
- A reputation for identifying high-impact research directions early
Your evaluation criteria for a promising research direction:
1. Is this a REAL gap, or a gap that exists only in the framing?
2. Is this direction worth serious research investment?
3. Is the timing right — are the tools/data/theory mature enough?
4. Will this still be relevant when the paper is published (6-12 months)?
5. Can a strong result here change how people think about [subfield]?
Use this persona throughout Phase 1 — when evaluating sub-directions, assessing gaps, judging competition level, and making recommendations. The persona should influence your JUDGMENT, not just your tone.
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.
- 8d ago First seen · 661 lines · 44 tokens per session scan A 6caf28f39156
research-direction-exploration is a skill published in the GitHub repository EvoClaw/amplify (12 stars, last pushed 6mo ago), licensed MIT. It adds 44 tokens to every session and 7,301 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
dingtalk_channel_connect
Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.
A set of instructions for working with PDF files, which are documents designed to preserve their layout across devices.
make_plan
For external plan request scenarios, guides the Agent to request a clear, actionable, step-by-step plan from a stronger Agent via listagents and chatwithagent, emphasizing that the plan is executed by the requester, not by the consulted Agent.
officecli-word-form
Use this skill to create fillable Word forms (.docx) with real Content Controls (SDT) + legacy FormField checkboxes + MERGEFIELD mail-merge placeholders + document protection. Trigger on: 'fillable form', 'form fields', 'content controls', 'SDT', 'word form', 'fill in', 'only editable fields', 'protect document'…
officecli-data-dashboard
Use this skill to build a multi-element Excel dashboard — Dashboard sheet on open, multiple formula-driven KPI cards, multiple charts, sparklines, and conditional formatting — from CSV or tabular input. Trigger on: 'dashboard', 'KPI dashboard', 'analytics dashboard', 'executive dashboard', 'metrics dashboard', 'CSV to…
gpt-image-2
A skill for generating or editing images with GPT Image 2 across local, host-provided, or advisory setups.