x-api
Read and post to X/Twitter via API. Check mentions, post tweets, search. Uses OAuth 2.0 user context with token refresh.
81
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Evaluation results
99%
60%Mentions Triage Tool for @joelclaw
Scam filtering & mentions API usage
requests-oauthlib library
0%
100%
uv run invocation
0%
100%
secrets lease for consumer key
0%
100%
secrets lease for all four credentials
0%
100%
secrets revoke --all
0%
100%
Correct user ID in URL
0%
100%
Correct mentions endpoint
100%
100%
tweet.fields parameter
100%
100%
Scam/shitcoin filtering logic
81%
93%
Two-section report
100%
100%
OAuth1Session constructor params
0%
100%
Without context: $0.3341 · 1m 26s · 17 turns · 23 in / 4,854 out tokens
With context: $0.4207 · 1m 33s · 23 turns · 28 in / 4,831 out tokens
100%
36%Weekly Update Automation for @joelclaw
Tweet approval workflow before posting
Draft saved separately
100%
100%
No auto-posting in main flow
100%
100%
Separate post script exists
100%
100%
requests-oauthlib in post script
50%
100%
uv run invocation
0%
100%
secrets lease in post script
0%
100%
All four secret names used
0%
100%
secrets revoke --all
0%
100%
Correct POST endpoint
100%
100%
No financial advice in draft
100%
100%
Workflow documentation
100%
100%
Without context: $0.2302 · 1m 3s · 15 turns · 21 in / 3,469 out tokens
With context: $0.3625 · 1m 10s · 21 turns · 24 in / 4,147 out tokens
100%
70%Community Buzz Tracker for @joelclaw
Authenticated search API with secrets management
requests-oauthlib import
0%
100%
uv run invocation
0%
100%
secrets lease x_consumer_key
0%
100%
secrets lease x_consumer_secret
0%
100%
secrets lease x_access_token
0%
100%
secrets lease x_access_token_secret
0%
100%
OAuth1Session keyword args
0%
100%
Correct search endpoint
100%
100%
tweet.fields in search params
100%
100%
secrets revoke --all
0%
100%
Results saved to JSON file
100%
100%
Without context: $0.2061 · 43s · 13 turns · 15 in / 2,719 out tokens
With context: $0.4953 · 1m 37s · 28 turns · 284 in / 5,631 out tokens
- Evaluated
- Agent
- Claude Code
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.