Audit existing skills with Tessl scoring, metadata and trigger-coverage checks, repo conventions, and skill-authoring best practices. Use when creating or revising a skill, triaging weak self-activation, or comparing a skill against source-repo guidance such as `AGENTS.md`, `CLAUDE.md`, or repo rules, plus external skill guidance. Do not use to verify general application code or to rewrite unrelated docs.
97
98%
Does it follow best practices?
Impact
97%
1.05xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
A platform team has been maintaining a growing library of agent skills. One of their oldest skills — onboarding-assistant — was written before the team adopted any formal quality standards. It recently started showing poor activation rates: users keep forgetting to invoke it, and when they do, the agent sometimes goes off-script. The team lead has asked you to do a thorough audit of the skill and produce a written report that the team can use to decide which issues to fix first.
The skill lives in the skills/onboarding-assistant/ folder of the repo provided below. The repo also contains a AGENTS.md with team conventions. Your job is to audit the skill using the Tessl CLI, evaluate it against standard skill-authoring criteria, and write up what you find.
Produce a file called audit-report.md in the working directory. The report must cover:
Also produce a file called audit-log.sh containing the exact shell commands you ran during the audit (Tessl invocations, any file reads, etc.), in execution order.
The following files are provided as inputs. Extract them before beginning.
This skill helps. When someone joins the company, use this to help them.
Help the user with onboarding. You can:
Be helpful and friendly. Make sure they feel welcome. Try your best to assist with whatever they need.
If there are documents, read them. If there are scripts, run them. Good luck!
=============== FILE: AGENTS.md ===============
name and description