Agent Skill Radar
Use when the user wants to scan GitHub for AI agent skills, MCP servers, prompt systems, context engineering tools, or agent-native CLI opportunities; generate daily opportunity reports; choose a two-week open-source project; or turn GitHub trend research into build briefs, fake-door probes, and launch content.
Install
$ agentstack add skill-soarsky1991-skill-radar-skill-radar ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-soarsky1991-skill-radar-skill-radar) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Agent Skill Radar
Use this skill to find project opportunities from GitHub evidence instead of brainstorming from scratch.
Workflow
- Run the radar CLI.
- Read the top-scoring repos and issue samples.
- Pick one opportunity with a narrow companion-tool shape.
- Generate a build brief, fake-door probe, README angle, and launch post.
- Save the report under
reports/and keep the data underdata/.
Commands
Run the default daily scan:
agent-skill-radar runCollect a custom scan:
agent-skill-radar collect \
--query "agent memory coding assistant stars:>100 created:>=2025-01-01" \
--limit-per-query 12 \
--issue-limit 6 \
--out data/custom.jsonRender a report:
agent-skill-radar report --input data/custom.json --out reports/custom.mdInterpretation Rules
- Treat
build-nowas a proof-of-concept signal, not permission to build a large product. - Prefer a companion tool, plugin, skill pack, template, benchmark, or CLI wrapper over a fork.
- Avoid topics where the only signal is stars. Look for issue comments, reactions, recurring workarounds, and ecosystem gaps.
- For giant repositories, build around the ecosystem edge: docs, config, migration, compatibility, monitoring, security, or publishing workflows.
- If the same gap appears across 3 or more repos, promote it to a standalone project idea.
Output Template
For each shortlisted idea, write:
Project:
Target user:
Observed demand:
Repo evidence:
Why upstream will not solve it:
Smallest useful artifact:
Distribution wedge:
Two-week scope:
Fake-door question:Probe Template
Use a neutral validation comment. Do not pitch too early.
I have seen this come up in a few agent-tooling repos. My current workaround is .
I am considering a small standalone that does without requiring upstream changes.
Before building it: would this solve your case, or is the real blocker different?Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: soarsky1991
- Source: soarsky1991/skill-radar
- License: MIT
- Homepage: https://github.com/soarsky1991/skill-radar/blob/main/reports/latest.md
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.