promptfoo-evals
promptfoo
Write, refine, run, and QA non-redteam promptfoo eval suites after the target or provider already works: prompts, vars, test cases, assertions, model-graded rubrics, tra…
24.7KGitHub
OPENAGENTSKILL / DIRECTORY
AI Agent Skills
Find a skill for your next task. Explore tools for Codex, Claude Code, Cursor and more.
Results · “health-endpoint”
17–22 / 22
More filters
Candidates in this shortlist, not the full registry. GitHub stars belong to repositories, not individual skills.
Results: 22
open-code-review-delegate
alibaba
Delegation mode for open-code-review (OCR). Instead of OCR calling an LLM endpoint, this skill instructs the host agent to perform the code review itself, using OCR only…
22.1KGitHub
seo-audit
AgriciDaniel
Full website SEO audit with parallel subagent delegation. Crawls up to 500 pages, detects business type, delegates to up to 15 specialists (8 always + 7 conditional), ge…
16KGitHub
think
AgriciDaniel
Apply the Fable-derived 10-stage OBSERVE, OBSERVE, LISTEN, THINK, CONNECT, CONNECT, FEEL, ACCEPT, CREATE, GROW loop to consequential or ambiguous reasoning and decisions…
14.5KGitHub
wiki-lint
AgriciDaniel
Run a deterministic, read-only health check on an Obsidian wiki. Use for lint, vault health check, audit wiki health, find orphans, find dead links, frontmatter audit, p…
14.5KGitHub
Financial Statement Analyzer
Geeksfino
Perform a forensic company financial-statement review across earnings quality, health, fraud risk, and operating efficiency.
271GitHub