Loading source
Pulling the file list, source metadata, and syntax-aware rendering for this listing.
Source from repo
A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems.
Files
Skill
Size
Entrypoint
Format
Open file
Syntax-highlighted preview of this file as included in the skill package.
researcher/discovery/manual-seed.jsonl
1{"url":"https://www.anthropic.com/engineering/building-effective-agents","title":"Building Effective Agents","author_or_org":"Anthropic","source_type":"engineering_blog","candidate_reason":"Direct guidance from Anthropic on agent design patterns, tool use, and workflow vs autonomous agents."}2{"url":"https://www.anthropic.com/research/swe-bench-sonnet","title":"Claude on SWE-bench: agent design lessons","author_or_org":"Anthropic","source_type":"engineering_blog","candidate_reason":"Production agent design lessons against a public benchmark."}3{"url":"https://www.anthropic.com/research/tracing-thoughts-language-model","title":"Tracing the thoughts of a large language model","author_or_org":"Anthropic","source_type":"paper","candidate_reason":"Mechanistic insight into reasoning that affects context engineering and tool design."}4{"url":"https://openai.com/index/introducing-deep-research/","title":"Introducing deep research","author_or_org":"OpenAI","source_type":"engineering_blog","candidate_reason":"Production autonomous research agent design with explicit tool use, long horizons, and citation requirements."}5{"url":"https://openai.com/research/practices-for-governing-agentic-ai-systems","title":"Practices for governing agentic AI systems","author_or_org":"OpenAI","source_type":"paper","candidate_reason":"Governance and harness practices that align with harness-engineering."}6{"url":"https://research.google/blog/google-research-2024","title":"Google Research engineering posts","author_or_org":"Google Research","source_type":"engineering_blog","candidate_reason":"Engineering retrospectives on agent and evaluation systems."}7{"url":"https://www.cursor.com/blog/composer","title":"Cursor Composer","author_or_org":"Cursor","source_type":"engineering_blog","candidate_reason":"Production coding agent design patterns and harness."}8{"url":"https://vercel.com/blog/we-removed-80-percent-of-our-agents-tools","title":"We removed 80% of our agent's tools","author_or_org":"Vercel","source_type":"engineering_blog","candidate_reason":"Already cited in project-development; refresh with the latest evidence and any follow-ups."}9{"url":"https://www.primeintellect.ai/auto-nanogpt","title":"Auto-NanoGPT","author_or_org":"Prime Intellect","source_type":"engineering_blog","candidate_reason":"Seed source for durable-research-thread mechanism; refresh and check for follow-up evidence."}10{"url":"https://github.com/karpathy/autoresearch/blob/master/program.md","title":"Karpathy autoresearch program","author_or_org":"Andrej Karpathy","source_type":"code","candidate_reason":"Seed source for locked-editable-surfaces mechanism; track upstream changes."}11{"url":"https://www.cohere.com/research","title":"Cohere research blog","author_or_org":"Cohere","source_type":"engineering_blog","candidate_reason":"Retrieval, RAG, and evaluation research relevant to multiple skills."}12{"url":"https://www.deepmind.com/research/alphaevolve","title":"AlphaEvolve","author_or_org":"Google DeepMind","source_type":"paper","candidate_reason":"Autonomous experimentation system pattern relevant to harness-engineering."}13