Install
$ agentstack add skill-sawyer-middeleer-dot-claude-analyzing-source ✓ 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
Analyzing a Source
Analyze a single source in depth and create a comprehensive summary suitable for research synthesis.
Process
Step 1: Retrieve
- Given a URL: fetch it directly with WebFetch; verify the content is accessible and relevant
- Given a topic: WebSearch for the best source, prioritizing authoritative and detailed ones; fetch the most relevant result
- Inaccessible or thin: try alternative sources; note access issues in the summary rather than fabricating around them
Step 2: Deep Analysis
Focus on:
- Core concepts, definitions, frameworks the source presents
- Main arguments, claims, findings — what is it asserting?
- Evidence, data, examples — what supports the claims?
- Methodology — how was the work conducted?
- Limitations, caveats, counterarguments — where are the boundaries?
- Connections to the research focus provided
- Quality and credibility — how reliable is this source, and why?
- Unique insights — what does this source offer that others won't?
Step 3: Write the Summary
Use the template at ${CLAUDE_PLUGIN_ROOT}/skills/analyzing-source/templates/article-summary.md.
Be concise yet thorough — extremely information-dense, leveraging specific data:
- Include direct quotes and concrete examples, not just paraphrase
- Provide analytical judgment about significance, not just description
- Connect explicitly to the research focus
- Make the summary self-contained — readable without the original
Step 4: Save
- Filename: a descriptive slug (
kubernetes-scaling-patterns.md,pricing-research-meta-analysis.md) - Location:
{working_directory}/summaries/{filename}.md - All template sections filled
Step 5: Report
- What source was analyzed
- Where the summary was saved
- 2–3 sentences on the most important insights
Guidelines
- Thorough, not brief — this is deep research, not scanning; capture nuance
- Specific evidence — quotes, data points, named examples
- Critical — note limitations, assess quality, surface assumptions
- Focused — comprehensive within the research focus, not encyclopedic beyond it
- Always save the file — the coordinator depends on it existing
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Sawyer-Middeleer
- Source: Sawyer-Middeleer/dot-claude
- 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.