How to use this directory
What the parts of a profile mean, how to find the right skill, and what to do when something looks wrong.
Finding a skill
Browse All Skills for the full catalogue, or narrow it by category (development, data, writing, design, ops, productivity, finance) or by publisher. The search box on the list page matches titles, taglines and summaries.
Every page exists in English and Chinese; the language toggle in the header keeps you on the same skill rather than sending you back to the homepage.
Reading a profile
A profile leads with what the skill does and who published it, then the scored review, then the practical detail: use cases, installation, day-to-day usage, comparisons with similar skills, strengths and limitations, and a short FAQ.
The badges near the title are factual, not editorial. “Official” means the source repository belongs to the named organisation, established from public provenance. The star count and licence come from the source repository. “Updated” is the repository's last commit, not the date we wrote the review.
Making sense of the score
The FSRS score out of 100 combines weighted dimensions — Trust & safety carries the most weight at 25, then Reliability at 20, then Adaptability at 15, and so on. Each dimension on the page shows its own sentences of reasoning, so you can disagree with a specific judgement rather than the whole number.
Alongside the score, the profile states its evidence level: high means key paths were checked and reproduced with independent corroboration; low means the review rests mainly on static reading of the author's own material. A low evidence level is a signal to do your own testing, not necessarily a bad skill.
Some skills are marked Not recommended regardless of their arithmetic total, because a red-line issue could not be reasonably resolved. The methodology page lists what those red lines are.
Before you install anything
A skill is code that runs inside an agent with real access to your machine. Whatever the score says, check the source repository yourself, look at what permissions the skill asks for, start in a scratch directory or a test account, and keep a way to undo it.
Never paste real credentials into an example configuration you have not read, here or anywhere else.
A skill is missing, or a profile is wrong
Candidates are discovered from GitHub by rule, so a very new or very obscure repository may simply not have been picked up yet, and a profile may lag behind a repository that changed last week.
To suggest a skill, report an error, or ask for your own repository to be corrected or delisted, write to [email protected] with the URL. Maintainer requests about their own repository are honoured.
Anything else
The methodology page documents the full scoring standard. The privacy page explains exactly what the site collects. For anything not covered, [email protected] reaches a person.