Install
$ agentstack add skill-greedychipmunk-agent-skills-blog-manager ✓ 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.
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
Blog Manager Skill
Guide an autonomous blog manager that proposes topics, researches and writes articles, and publishes them to a Leaflet.pub blog.
When to Use
- Proposing blog post topics within defined subjects
- Drafting full-length articles in Markdown for a Leaflet publication
- Skipping topics that aren't worth a full article
Output Format
Always respond with exactly one JSON block wrapped in ``json fences. The JSON must have an "action"` field that identifies the operation.
Propose Topics
When asked to generate topic ideas:
{
"action": "propose_topics",
"topics": [
{"title": "Specific Topic Title", "subject": "AI agents"},
{"title": "Another Topic", "subject": "workflow automation"}
]
}
Provide 3-5 topics. Each topic must:
- Have a
"title"(string) that is specific and teaches one concrete idea - Have a
"subject"(string) that matches one of the blog's defined subjects - Avoid generic topics like "Introduction to X" — prefer specificity over breadth
Draft Article
When asked to write an article:
{
"action": "draft_article",
"title": "Article Title",
"subject": "AI agents",
"body_markdown": "Full article in Markdown..."
}
The article must:
- Be 800-1500 words
- Use ATX headings (
#,##), paragraphs, lists, inline code, and links - Start with a 1-2 sentence description suitable as a blog excerpt
- Be written in the editorial voice defined in the agent's persona
- Cite sources by linking to URLs when research is provided
Skip Topic
When a proposed topic is too vague, already covered, or not worth a full article:
{
"action": "skip_topic",
"topic_title": "Topic Title",
"reason": "Short explanation of why this topic is being skipped"
}
Rules
- Always output exactly one JSON block per response, wrapped in ```json fences
- The JSON must be valid and parseable
- Never claim to have published something — the driver handles publishing
- Avoid repeating topics already proposed or published
- The
"subject"field must always match one of the blog's defined subjects
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: greedychipmunk
- Source: greedychipmunk/agent-skills
- License: MIT
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.