inspiro-best-practices
Skill1 starsChanged 9 months agoMITView on GitHub
Bash-first best practices for production Inspiro usage with zero SDK dependency. Use when you need stable, scriptable API workflows for search, extract, crawl, and research using curl and INSPIRO_API_KEY.
- Reads credentials
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Only API key authentication is supported.
- Distinctive: line 20
Use the provided Bash scripts from this repository:
- Very specific: line 73
Keep INSPIRO_API_KEY in environment or ~/.claude/settings.json.
- Very specific: line 74
Use small max_results/limit first, then scale up.
- Distinctive: line 75
Always validate JSON request bodies before batch execution.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Inspiro Best Practices (Bash Only)
This skill is Bash-first and requires no Python/JavaScript SDK.
Authentication
Only API key authentication is supported.
export INSPIRO_API_KEY="your_inspiro_api_key"Recommended Execution Pattern
Use the provided Bash scripts from this repository:
skills/inspiro/search/scripts/search.shskills/inspiro/extract/scripts/extract.shskills/inspiro/crawl/scripts/crawl.shskills/inspiro/research/scripts/research.sh
These scripts validate inputs and call Inspiro REST endpoints directly.
Direct API Calls (curl)
Search
curl --request POST \
--url https://api.inspiro.top/search \
--header "Authorization: Bearer $INSPIRO_API_KEY" \
--header 'Content-Type: application/json' \
--data '{"query":"latest ai trends","max_results":5}'Extract
curl --request POST \
--url https://api.inspiro.top/extract \
--header "Authorization: Bearer $INSPIRO_API_KEY" \
--header 'Content-Type: application/json' \
--data '{"urls":["https://example.com"]}'Crawl
curl --request POST \
--url https://api.inspiro.top/crawl \
--header "Authorization: Bearer $INSPIRO_API_KEY" \
--header 'Content-Type: application/json' \
--data '{"url":"https://docs.example.com","max_depth":1,"limit":20}'Research
curl --request POST \
--url https://api.inspiro.top/research \
--header "Authorization: Bearer $INSPIRO_API_KEY" \
--header 'Content-Type: application/json' \
--data '{"input":"AI agent framework comparison","model":"mini"}'Operational Tips
- Keep
INSPIRO_API_KEYin environment or~/.claude/settings.json; never hardcode in scripts. - Use small
max_results/limitfirst, then scale up. - Always validate JSON request bodies before batch execution.
- For reproducible automation, prefer repository scripts over ad-hoc one-liners.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

