loading
loading
Score an agent skill folder for vague triggers, missing evals, and unproven claims before you publish it.
Built for the moment before you publish a skill: it separates a polished README from a runnable one and names the exact missing pieces.
Listed for review
No verified public repo for this skill yet, so this page does not give you an install command. Skills with a verified source install in one command — or fully manual: copy the skill folder into .claude/skills/ and your agent picks it up.
Boostor Quality Score
84/100 · B
Skill Pack Auditor reads a skill folder and grades it against a publish-readiness rubric: it flags missing or malformed frontmatter, an overlong SKILL.md, leftover TODO text, absent behavioral evals, unsourced factual claims, and hidden dependencies on a private machine. The output is a scored audit with findings, a status recommendation, the specific claims it rejected, and the next fixes — so a polished README never gets mistaken for a runnable, sellable skill.
Turn a long reusable prompt into a real skill with frontmatter, triggers, a stop condition, and eval cases.
For the prompt you keep re-pasting: it rewrites it as a triggerable skill and scrubs the private paths most people forget to remove.
Transparent + deterministic: every point above is computed from this skill's real fields plus a prompt-injection safety scan. No black box, no pay-to-rank.