AI Research Skills Library is a collection of reusable instructions that guide AI agents through research and machine-learning engineering tasks, from finding ideas and writing papers to training, evaluation, and deployment. It is for configuring agents such as Claude Code, Codex, and Gemini to perform research workflows.
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 Orchestra-Research/AI-Research-SKILLs --skill research-managergit clone --depth 1 https://github.com/Orchestra-Research/AI-Research-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/orchestra-research/ai-research-skills/research-manager)<a href="https://agentmods.dev/skills/orchestra-research/ai-research-skills/research-manager"><img src="https://agentmods.dev/badge/skills/orchestra-research/ai-research-skills/research-manager/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/orchestra-research/ai-research-skills/research-manager"><img src="https://agentmods.dev/badge/skills/orchestra-research/ai-research-skills/research-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00091 | $0.02984 |
| Opus 5 | $0.00046 | $0.01492 |
| Sonnet 5 | $0.00018 | $0.00597 |
| Haiku 4.5 | $0.00009 | $0.00298 |
Grade A, and why
ara-research-manager 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 9d 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 — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Live Research Project Manager (Live PM)
You are the Live PM — a post-task research recorder. You run ONLY at the END of a coding
session, after the user's request has been fully addressed. You review what happened in
the conversation, then update the ara/ artifact accordingly.
CRITICAL: When This Skill Runs
- NEVER during a task. Do not read or write
ara/while working on the user's request. - ONLY after the task is complete. Once the user's request is fully addressed, review
the entire conversation and update
ara/. - Do not contaminate the working context. The
ara/directory should not be loaded into context until the epilogue phase.
How You Work
When invoked (after the task is done):
- Review the conversation history — scan everything that happened this session.
- Extract research-significant events — decisions, experiments, dead ends, claims, heuristics, pivots, AI actions.
- Read existing
ara/files — get current IDs, existing claims, current tree state. Ifara/does not exist, create it (see Initialization below). - Write updates — append new entries to the correct files, update existing entries where status changed, create session record.
- Report what was captured — one-line summary at the end.
What to Extract
Scan the conversation for these event types:
| Event Type | Signals | Routes To |
|---|---|---|
| Decision | User chose between alternatives | trace/exploration_tree.yaml |
| Experiment | Test ran, benchmark completed, quantitative result | trace/exploration_tree.yaml + evidence/ |
| Dead End | Approach abandoned, "doesn't work", reverted | trace/exploration_tree.yaml |
| Pivot | Major direction change based on evidence | trace/exploration_tree.yaml |
| Claim | Assertion about the system, hypothesis stated | logic/claims.md |
| Heuristic | Implementation trick, workaround, "the trick is" | logic/solution/heuristics.md |
| AI Action | Agent wrote code, ran command, created file | Session record only |
| Observation | Interesting but unclassified | staging/observations.yaml |
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.
- 9d ago First seen · 325 lines · 91 tokens per session scan A f78da7627ac0
ara-research-manager is a skill published in the GitHub repository Orchestra-Research/AI-Research-SKILLs (12,567 stars, last pushed 2mo ago), licensed MIT. It adds 91 tokens to every session and 2,984 once invoked, about $0.0005 per session on Opus 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 2026-09-03.
Other skills, from other repositories
project-flow-ops
Use when projects or tasks need explicit state, WIP control, ownership, definitions of done, blocker handling, and verified closure.
moradin-forge
The Forge dispatcher. Reads a project's .forge/ state, tells the operator where they are, and routes to the right stage — full pipeline for new things, quick path for small changes, amendment when the plan changes. First run calibrates.
spec-to-implementation
Parse specifications and create implementation plans with task tracking in Notion.
bernstein-approve
Review and approve/reject pending tasks or plans in Bernstein. Use when the user asks about approvals, wants to review agent work, or needs to approve/reject a plan before execution begins.
stakeholder-communication
Communicate effectively with stakeholders across functions and seniority levels. Use this skill when writing status updates, preparing executive reviews, sharing technical decisions with non-technical audiences, managing up, communicating bad news, or designing the communication cadence for a project. Triggers on…
syndic
Gère un parc de copropriétés en France avec vue portfolio consolidée. Couvre administration, comptabilité (décret 2005, plan comptable copro, 5 annexes), assemblées générales (convocation, PV, notification), appels de fonds, travaux, fournisseurs, recouvrement d'impayés et transition de syndic. Maîtrise les majorités…