GoogleKnown publishergoogle-gemini/gemini-managed-agents-templates/ai-radio/skills/research/SKILL.mdresearch
Skill99 starsChanged 6 months agoApache-2.0View on GitHub
Gather source material for the radio show from any content source — web, HN, GitHub, papers, or general topics.
189 other projects use a version of this.
Adopted by
Most recently taken up by
- Suge8/friedbuntheir own version, first seen Nov 15, 2026
- Fractera/Agent-Engineering-Infrastructuretheir own version, first seen Nov 15, 2026
- Fractera/Agentic-Engineering-Infrastructuretheir own version, first seen Nov 15, 2026
- iha2/superlitetheir own version, first seen Nov 15, 2026
- SireJeff/k0ntexttheir own version, first seen Nov 15, 2026
- quickchatai/quickreviewtheir own version, first seen Nov 15, 2026
Used with
Projects with it also use daily-arxiv, exp-eval and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
LambenthanSkilldaily-arxiv
每日从 arXiv 拉取新论文，过滤相关性，auto-ingest 高优先级论文，检测 SOTA 更新
Also in 5 projects that use this
- LambenthanSkill
exp-eval
实验判决门：Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges
Also in 5 projects that use this
truongtv22SkillProblem-Solving Techniques
Apply systematic problem-solving techniques for complexity spirals (simplification cascades), innovation blocks (collision-zone thinking), recurring patterns (meta-pattern recognition), assumption constraints (inversion exercise), scale uncertainty (scale game), and dispatch when stuck. Techniques derived from Microsoft Amplifier project patterns adapted for immediate application.
Also in 5 projects that use this
liufeng1976Skillsetup-ts-deep-modules
Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.
Also in 43 projects that use this
skyllwtSkillexp-pilot-eval
Pilot result evaluation — read pilot results, apply success criteria, update idea page (pilot_result, failure_reason if failed), generate PILOT_VERDICT_REPORT. Called by /ideate Phase 5 after /exp-pilot-run.
Also in 4 projects that use this
- skyllwtSkill
exp-pilot-run
Pilot experiment execution — read Pilot Spec YAML, write pilot code, run experiment(Confirm with the user before operation and require the applicant to conduct manual inspection), return results. Called by /ideate Phase 5. Does NOT modify wiki pages or judge pass/fail.
Also in 4 projects that use this
- +5 more from Lambenthan
- +1 more from skyllwt
Other versions189 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 189
- mattpocock/skills★ 325ksame name
- Yeachan-Heo/oh-my-claudecode★ 41ksame name
- Yeachan-Heo/oh-my-claude-sisyphus★ 41ksame name
- QuivrHQ/quivr★ 40ksame name
- The-Vibe-Company/quivr★ 40ksame name
- udecode/plate★ 17ksame name
- openai/plugins★ 7.8ksame name
- ArcReel/ArcReel★ 6.6ksame name
- vinvcn/mattpocock-skills-zh-CN★ 5.8ksame name
- withcoral/coral★ 4.9ksame name
179 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository27 other files it gives its agents.
- ai-radio/AGENTS.mdAGENTS.md
- customer-support/AGENTS.mdAGENTS.md
- data-analyst/AGENTS.mdAGENTS.md
- document-processor/AGENTS.mdAGENTS.md
- news-curator/AGENTS.mdAGENTS.md
- repo-maintainer/AGENTS.mdAGENTS.md
- seo-auditor/AGENTS.mdAGENTS.md
- audio-mixingSkill
- cover-image-generationSkill
- metadata-generationSkill
- music-generationSkill
- script-writingSkill
- tts-generationSkill
- memorySkill
- scannerSkill
- data-explorerSkill
- python-dataSkill
- pdf-parsingSkill
- reconciliationSkill
- slide-creatorSkill
- vendor-verificationSkill
- briefingSkill
- curationSkill
- deliverSkill
- fetch-newsSkill
- github-researcherSkill
- git-workflowSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 5 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 170 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
All research scripts live in skills/research/scripts/ and output to {workspace}/data/research/.
- Distinctive: line 34
When picking stories, SKIP anything related to politics, race, religion, international conflicts, historical controversies, gender/culture …
- Distinctive: line 98
If the user provides a topic without a specific source:
- Distinctive: line 99
Use Google Search to find recent articles, blog posts, and discussions
- Very specific: line 101
Write the research markdown directly to {workspace}/data/research/
- Distinctive: line 107
All research must be saved here regardless of source — the script-writing step reads from this directory.
- Distinctive: line 111
When reviewing the research output, identify:
“Common” is measured: kept by at least 6 in 10 of the 170 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Research
Gather source material for the radio show based on the user's prompt. The research strategy is agent-driven — you decide how to gather content based on what the user asks for.
Scripts
All research scripts live in skills/research/scripts/ and output to {workspace}/data/research/. They use only Python stdlib — no dependencies.
| Script | Command | Source |
fetch_hn.py | python3 skills/research/scripts/fetch_hn.py --workspace ./workspace --top 6 | Hacker News |
fetch_github.py | python3 skills/research/scripts/fetch_github.py --repo owner/repo --workspace ./workspace | GitHub repos |
fetch_url.py | python3 skills/research/scripts/fetch_url.py --url https://... --workspace ./workspace | Any URL |
Script Details
fetch_hn.py — Hacker News (two-phase)
Phase 1: Scan — grab top 10 story titles, scores, and comment counts (fast, no deep-diving):
python3 skills/research/scripts/fetch_hn.py --workspace ./workspace --mode scan --top 10Output: {workspace}/data/research/hn-scan.md — a list of stories with IDs.
You read this file, pick the 2-3 most interesting stories for radio, then run phase 2.
When picking stories, SKIP anything related to politics, race, religion, international conflicts, historical controversies, gender/culture wars, or immigration. Stick to tech, programming, AI/ML, open source, science, startups, and developer culture.
Phase 2: Deep-dive — fetch full comment threads for the stories you picked:
python3 skills/research/scripts/fetch_hn.py --workspace ./workspace --mode deep-dive --stories 43210987,43209876Output: {workspace}/data/research/hacker-news.md — full stories with top comments.
| Argument | Default | Description |
--workspace | workspace | Root workspace directory |
--mode | (required) | scan or deep-dive |
--top | 10 | Number of stories to scan (scan mode only) |
--stories | (required for deep-dive) | Comma-separated story IDs |
fetch_github.py — GitHub Repository
python3 skills/research/scripts/fetch_github.py --repo googleapis/python-genai --workspace ./workspaceAccepts owner/repo or a full GitHub URL (https://github.com/owner/repo).
| Argument | Default | Description |
--repo | (required) | GitHub repo (owner/repo or full URL) |
--workspace | workspace | Root workspace directory |
--releases | 5 | Number of releases to fetch |
--issues | 8 | Number of top issues to fetch |
What it does:
- Fetches repo metadata (stars, description, language).
- Fetches and decodes the README.
- Fetches recent releases with changelogs.
- Fetches top issues by comment count, including top comments.
- Outputs →
{workspace}/data/research/github.md
Uses the GitHub REST API directly — no auth needed for public repos.
fetch_url.py — Any URL
python3 skills/research/scripts/fetch_url.py --url https://example.com/blog-post --workspace ./workspace| Argument | Default | Description |
--url | (required) | URL to fetch content from |
--workspace | workspace | Root workspace directory |
--max-chars | 8000 | Max chars to extract |
What it does:
- Fetches the HTML page.
- Strips scripts, styles, nav, footer.
- Converts HTML to markdown-like text.
- Extracts title and meta description.
- Outputs →
{workspace}/data/research/url_<safe_name>.md
Works for blog posts, documentation pages, arXiv abstracts, news articles, etc.
General Topic (no script — agent-driven)
If the user provides a topic without a specific source:
- Use Google Search to find recent articles, blog posts, and discussions
- Gather multiple perspectives and opposing viewpoints
- Write the research markdown directly to
{workspace}/data/research/
Output
- Directory:
{workspace}/data/research/ - Format: One or more markdown files with structured content
- All research must be saved here regardless of source — the script-writing step reads from this directory.
What to look for
When reviewing the research output, identify:
- Consensus: What do most people agree on?
- Debates: What are the key disagreements?
- Contrarian takes: Any notable dissenting opinions?
- Expert insights: Comments or quotes from people with domain expertise.
- Emotional stories: Anything that would make compelling radio.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.