AutoSci is an AI research platform organized around a wiki, with an agent that supports stages of scientific work such as reading, experimentation, writing, and retaining knowledge across projects. It is for people building or using AI-assisted research workflows, with Claude Code, Codex, and OpenCode adaptations available. The catalogue add-ons extend those agent-specific workflows.
Borrowing it
Nothing to install: this file belongs to skyllwt/AutoSci. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/skyllwt/AutoSci/main/.claude/skills/ideate/SKILL.mdgit clone --depth 1 https://github.com/skyllwt/AutoSciWrote 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/skyllwt/autosci/ideate)<a href="https://agentmods.dev/skills/skyllwt/autosci/ideate"><img src="https://agentmods.dev/badge/skills/skyllwt/autosci/ideate/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/skyllwt/autosci/ideate"><img src="https://agentmods.dev/badge/skills/skyllwt/autosci/ideate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 10 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 3 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 17 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 216 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 218 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 278 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Tool Misuse · line 3 Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
- medium Tool Misuse · line 17 Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
- medium Tool Misuse · line 216 Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
- medium Tool Misuse · line 218 Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
- medium Tool Misuse · line 278 Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
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 | $0.07420 |
| Opus 5.5 | $0.00000 | $0.02968 |
| Sonnet 5.5 | $0.00000 | $0.01484 |
| Haiku 4.5 | $0.00000 | $0.00742 |
Grade A, and why
ideate 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 2mo 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 — 557 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ideate
Generates high-quality research ideas through a 5-phase pipeline, grounded in the wiki knowledge base and external search. Phase 1 scans the research landscape (wiki + WebSearch + S2), Phase 2 runs a dual-model brainstorm (Claude + Review LLM independently), Phase 3 applies first-pass filter + deep validation (feasibility, novelty, review), Phase 4 writes ideas to the wiki (including eliminated ideas, with failure reasons recorded as anti-repetition memory), Phase 5 runs pilot experiments on surviving ideas (idea pages already exist) and updates results.
Inputs
direction(optional): research direction, keywords, or specific problem description. If omitted, automatically selects the most valuable direction from open_questions.md.--max-ideas N(optional, default 3): maximum number of ideas to write to the wiki--skip-validation: skip Phase 3 Step 2 deep validation (skip /novelty and /review; fast mode: first-pass filter only)--skip-pilot: skip Phase 5 pilot experiments (fast mode: Phase 1–4 only)--auto: fully automatic mode, no pause for user confirmation (used when called by /research)
Outputs
wiki/ideas/{slug}.md— one page per idea (status: proposed), covering both top ideas and eliminated ideaswiki/graph/edges.jsonl— new idea → concept/topic relationship edgeswiki/graph/context_brief.md— rebuilt compressed contextwiki/graph/open_questions.md— rebuilt knowledge gap map- IDEA_REPORT (printed to terminal) — pipeline execution summary, ranked results, novelty scores
Wiki Interaction
Reads
wiki/graph/context_brief.md— global contextwiki/graph/open_questions.md— knowledge gaps, drives idea directionwiki/ideas/*.md— existing ideas, especially status=failed ideas and their failure_reason (banlist)wiki/papers/*.md— existing paper methods and resultswiki/concepts/*.md— technical concepts, find cross-domain combination opportunitieswiki/methods/*.md— reusable methods, scope candidate inspirationswiki/topics/*.md— research direction maps, SOTA and open problems (including### Known gapsand### Methodological gaps)wiki/experiments/*.md— existing experiment results, avoid duplication
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.
- 2mo ago First seen · 557 lines · 0 tokens per session scan A 9fb2d36c0048
ideate is a skill published in the GitHub repository skyllwt/AutoSci (1,706 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 7,420 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 2026-08-30.
ideate compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ideateskyllwt/AutoSci | Skill | 1.7k | 1mo ago | MIT | A | 0 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |