Status basis: pypi_downloads_30d momentum fell to 0 per 3d from 36595005 (<= 40% of the prior window)
- Cooling pypi_downloads_30d momentum fell to 0 per 3d from 36595005 (<= 40% of the prior window)
- Cooling pypi_downloads_30d momentum fell to 0 per 3d from 36595005 (<= 40% of the prior window)
- Cooling pypi_downloads_30d momentum fell to 0 per 3d from 36595005 (<= 40% of the prior window)
- Accelerating pypi_downloads_30d gained 36595005 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Reactivated pypi_downloads_30d did not move for 7d, then gained 36595005 in the last 3d
- Cooling pypi_downloads_30d momentum fell to 0 per 3d from 36595005 (<= 40% of the prior window)
- Accelerating pypi_downloads_30d gained 36595005 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Reactivated pypi_downloads_30d did not move for 7d, then gained 36595005 in the last 3d
- Accelerating pypi_downloads_30d gained 36595005 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Reactivated pypi_downloads_30d did not move for 7d, then gained 36595005 in the last 3d
- Accelerating pypi_downloads_30d gained 36595005 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Reactivated pypi_downloads_30d did not move for 7d, then gained 36595005 in the last 3d
- first observed Kanon started keeping permanent history for this agent
| Machine-callable | — | unknown | — |
| Open source | 1 | verified | 1 quote(s) |
| Self-hostable | — | unknown | — |
| Bring your own key | — | unknown | — |
| Autonomy level | 2 | inferred | 2 quote(s) |
| Pricing model | — | unknown | — |
| Integrations | — | unknown | — |
“Unknown” means we have not verified it — it is not a “no”. Hard filters never treat unknown as false.
By integrating human-in-the-loop control into AI research workflows, it improves reliability and trust in AI-assisted development.
Evidence quotesverbatim, from the product’s own materials
“public GitHub repository (README fetched)”— structural
“cp agents/web-search-agent.md ~/.claude/agents/”— readme
“supporting two-phase research: outline generation”— readme
“A structured research workflow skill for Claude Code, OpenCode, and Codex”— readme
FAQ
What is Deep-Research-skills?
Deep-Research-skills enhances AI programming assistants with structured, human-in-the-loop research capabilities, ensuring accuracy and control during complex problem-solving.
What does Deep-Research-skills do?
Conduct deep, systematic research on technical problems within AI coding tools while maintaining human oversight on critical steps.
Why does Deep-Research-skills matter?
By integrating human-in-the-loop control into AI research workflows, it improves reliability and trust in AI-assisted development.
Is Deep-Research-skills open source?
Yes — Deep-Research-skills is open source.
How popular is Deep-Research-skills?
As tracked by KanonAgent: 2.4k upvotes (first indexed 2026-07-24).
What are the best Deep-Research-skills alternatives?
Similar AI agents tracked by KanonAgent: Stealth Venture, taste-skill, archify, open-design, deer-flow, ruflo.