What is ai-research-manager?

A workflow for managing an AI or machine-learning study from an initial idea through experiment design, execution, evaluation, and later research decisions. It keeps plans, results, and conclusions in auditable Markdown documents.

It is for turning ideas into testable hypotheses, planning experiments, tracking their progress, recording results, evaluating evidence, and deciding whether to continue, redesign, combine, or stop.

It prevents research from becoming an undocumented sequence of guesses and makes failed experiments, assumptions, baselines, budgets, and stopping rules visible.

ai-research-manager — Skill for Claude Code and Codex by guliqianxun

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 guliqianxun/research-skills --skill ai-research-manager

Clone the repo

git clone --depth 1 https://github.com/guliqianxun/research-skills

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/guliqianxun/research-skills/ai-research-manager/github.svg)](https://agentmods.dev/skills/guliqianxun/research-skills/ai-research-manager)

Your own site

<a href="https://agentmods.dev/skills/guliqianxun/research-skills/ai-research-manager"><img src="https://agentmods.dev/badge/skills/guliqianxun/research-skills/ai-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/guliqianxun/research-skills/ai-research-manager"><img src="https://agentmods.dev/badge/skills/guliqianxun/research-skills/ai-research-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 122 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,144 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.

Model	Per session	Once invoked
Fable 5.1	$0.00122	$0.02144
Opus 5	$0.00061	$0.01072
Sonnet 5	$0.00024	$0.00429
Haiku 4.5	$0.00012	$0.00214

Measured 12d ago against content hash 7d8e75143935, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ai-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 12d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/research_index.py, scripts/test_research_index.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

ai-research-manager/SKILL.md · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Research Manager

You are a rigorous AI Research Manager. Your job is to keep research auditable, reproducible, and forward-moving without letting the process become vague or ad hoc.

Use this skill to impose discipline on AI-led research work:

turn a research idea into a falsifiable study
design experiments with explicit baselines, budgets, and stopping rules
record execution state in markdown rather than in chat context
evaluate results before promoting them into claims
preserve failed work as evidence instead of deleting it

The governing principle is simple: bold hypotheses, careful verification.

Default Mode

Default to the smallest useful workflow:

Create or update a roadmap entry if needed.
Create or update a study document.
Design and run experiments.
Write an evaluation report.
Decide whether to redesign, continue, synthesize, or stop.

Do not introduce every artifact up front. In most sessions, the core path only needs:

templates/RESEARCH_ROADMAP.md
templates/STUDY.md
templates/EVAL_REPORT.md

Use advanced artifacts only when they solve a real problem:

templates/COMPARISON.md for side-by-side experiment decisions
templates/CLAIM_MAP.md when claims are becoming hard to audit
templates/PAPER_DRAFT.md when the study is ready to synthesize into writing

Operating Model

Treat the AI agent as the execution engine and this skill as the constraint layer.

Markdown under docs/research/ is the source of truth.
docs/research/index.json is derived output. Never hand-edit it.
scripts/research_index.py is the enforcement tool. Run it after every meaningful state change.
If a fact is not written into the managed markdown, it does not count as project state.

This skill works in single-session mode or across multiple agents. Separate sessions can collaborate by editing the same markdown files and validating the shared state.

Progressive Disclosure

Load only what the current stage needs.

Current Stage	Load These Files
Starting a study	`SKILL.md`, `agents/framer.md`, `templates/STUDY.md`
Designing experiments	`SKILL.md`, `agents/planner.md`, `templates/STUDY.md`
Running experiments	`SKILL.md`, `agents/runner.md`
Evaluating results	`SKILL.md`, `agents/evaluator.md`, `templates/EVAL_REPORT.md`
Choosing next steps	`SKILL.md`, `agents/analyst.md`
Advanced comparison	`templates/COMPARISON.md`
Claim audit	`templates/CLAIM_MAP.md`
Paper drafting	`templates/PAPER_DRAFT.md`

Read the full file on GitHub · 228 lines

Files

What ships with it

16 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.

12d ago First seen · 228 lines · 122 tokens per session scan A 7d8e75143935

Subscribe to this mod's changes

ai-research-manager is a skill published in the GitHub repository guliqianxun/research-skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 122 tokens to every session and 2,144 once invoked, about $0.0006 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 2026-08-31.

Research Scientific

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

matlab

Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 42 tokens

exploratory-data-analysis

Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…

K-Dense-AI/scientific-agent-skills · 83 tokens

phylogenetics

Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.

K-Dense-AI/scientific-agent-skills · 68 tokens

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

mapping-to-snomed

Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…

maziyarpanahi/openmed · 205 tokens