Tested, plain-markdown skills for Claude Code, Codex, Cursor and any agent that reads a SKILL.md. Each one does a concrete job, like screening a resume, checking a site before launch or finding the page that should rank, and shows its evidence.
Checks a site you own before you ship it, without pretending a status code is a finding. A 200 on /.env that matches the app shell is catch-all routing, a blanket 403 is an unanswered question, and a check that never ran becomes INCONCLUSIVE — never a pass.
Shown working, 24 Oct 2026, on skills.caffeinity.com. Probed 19 sensitive paths; nothing exposed and every security header in place: PASS. See the run
Crawls a site you own and returns deterministic, evidence-backed technical SEO findings, with blocked or unrun checks reported INCONCLUSIVE rather than a pass.
Shown working, 24 Oct 2026, on skills.caffeinity.com. Found one broken internal link across 24 pages; the re-crawl after the fix came back clean. See the run
Audits and fine-tunes a skill that already exists: the description that never fires, overlap with installed siblings, stale names and counts, handoff contracts that do not hand off. Ships check_skill.py, a deterministic validator over frontmatter, folder and heading agreement, description length and reference paths that do not exist. Not for creating one from scratch; that is draft-skill.
Shown working, 24 Oct 2026, on the 42 skills in this catalogue. Caught one skill that strict installers could not load; fixed in that skill and in tune-skill. See the run
Shown running · 23 and 24 October 2026
Tested on real targets, this site first.
Each tab is a real run: what the skill found, and what changed because of it. Nothing here is a mock-up; where a fix is still waiting on a decision, the tab says so.
seo-crawl · skills.caffeinity.com
One broken link, found by the crawler
pages 24 of 24 fetched
checks 5 complete
findings 1 error · 12 info
Cloudflare rewrote a sample address on the red-team page into a link that 404s. The address is now excluded from obfuscation and the 12 long titles and descriptions were shortened.
Before → after
before
23 Oct · error broken-internal-link
/cdn-cgi/l/email-protection → 404
after
24 Oct · new build, 25 pages fetched
errors 0
warnings 25 canonical → skills.caffeinity.com
(expected on the preview host)
tune-skill's own fallback parser had let the error through without PyYAML; it now fails it too.
Before → after
before
FAIL crash-test invalid YAML
unquoted ": " in description
after
crash-test description in a YAML block
check_skill.py: 0 fail
fixed in crash-test and tune-skill
tune-skill · regress.py × 44 skills
The family checked against itself
skills checked 44
regressions 0
improvements 23
new skills 3
regress.py runs the validator on every skill, then the checks one file cannot show: handoffs to skills that do not exist, and two skills claiming the same trigger. The nightly health job runs it; W10 fixes what it finds.
One plugin carries every skill on this site plus eleven agents, one per workflow. Or take a single skill into any agent that reads a SKILL.md.
Claude Code
Every skill, plus the eleven agents: skill-builder, release-gatekeeper, seo-lead and the rest.
Codex
The same plugin from the Codex marketplace in the repo; then install caffeinity from the Plugins directory. caffeinity-routing picks the brew.
Any agent
Cursor, Qoder, Gemini CLI and others: one skill at a time with the skills installer. Swap wordsmith for any skill; every skill page has its exact command.