Skills-compatible agents / Research
Last 30 Days
Researches recent discussion and evidence across configured web and community sources, then synthesizes attributed findings.
66,836 repository stars · checked 2026-11-06. Count applies to mvanhorn/last30days-skill, not this individual skill.
Guide by IDAKIM Digital. Source review: . Original explanation based on the linked publisher sources.
What it does
Last 30 Days is a research skill backed by an engine and multiple source integrations. The reviewed version has separate routes for fresh topic research, comparisons, discovery and existing research. Available sources depend on setup and host capabilities; the name does not mean every result is automatically accurate or every platform is available.
When to use it
- Find recent developer experiences with a tool.
- Compare current community discussion around competing products.
- Investigate a recent topic while keeping links and evidence boundaries.
Step-by-step workflow
- Identify the topic, time window and whether the request needs new research or a follow-up.
- Check source availability and complete only the necessary setup.
- Plan searches and collect evidence through the documented engine and host search path.
- Distinguish original observations, repeated claims and incomplete source coverage.
- Produce a sourced synthesis and disclose missing sources, dates and limitations.
Example request
Use last30days to research recent developer experiences with local coding agents. Compare setup friction, reported reliability and hardware constraints. Link the original sources, distinguish anecdotes from measurements and identify which platforms were unavailable. Do not read browser cookies or use paid integrations without explicit authorization.
Worked example
Several highly upvoted comments can reveal a recurring complaint, but they do not measure its prevalence across all users. Keep the original dates and links, describe the discussion as reported experience and use official documentation to verify product capabilities.
What you get
A recent, attributed research brief or comparison with transparent source coverage.
How to evaluate the result
- Confirm the requested artifact or behavior is actually delivered, with evidence appropriate to this workflow.
- Repeat the example on your own inputs and check the stated limits; repository popularity is not an execution test.
- Verify important facts, permissions and failure paths before adopting the result.
What you need
The complete skill, its engine/runtime references, network access and source-specific credentials or host integrations when applicable.
Setup and activation
Follow the publisher README for your specific client and preserve the complete selected skill folder, including companion references and scripts. Claude Code, Codex and other hosts may use different plugin or Agent Skills installation paths. This guide does not establish that every host has the same tools. Security-scan the exact version before installation; this website installs or executes nothing.
Limits and considerations
Some sources require credentials, paid services or browser access. The current source includes consent rules for browser-cookie reads. Missing access must remain a disclosed gap; popularity signals and market odds are not proof of factual accuracy.
Related workflows
- Use a task-specific validation workflow to check the final result.
- Review companion scripts and references before adding this skill to an agent.
License and reuse
MIT at repository level; inspect per-file terms and separately licensed assets before reuse.
Further reading
Read the original source
Publisher: mvanhorn/last30days-skill
Source reviewed: 2026-11-06
Source reviewed; not installed, executed or security-scanned for this directory. These example requests were written by IDAKIM Digital. Upstream content can change.