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 product team has three skills that have been underperforming. Users keep triggering the wrong skill, or no skill at all. The team's hypothesis is that the skill names and descriptions are too vague and that the boundary between overlapping skills is never stated, causing the model to half-trigger all three whenever any related request comes in.
Additionally, the team recently added a fourth skill, data-pipeline, and wants to know whether its description is written in a style consistent with the others. They also noticed that a pull request last week added some application code review guidance directly to the data-pipeline skill, which they suspect is out of place.
Your task is to audit all four skills for discovery and boundary clarity, identify which ones are most at risk of poor activation, and write a report with concrete rewrite suggestions for the names and descriptions. Also flag any content that belongs in a different skill or a different tool entirely.
Produce:
audit-report.md — one section per skill, each including: the Tessl command run, the score, a discovery assessment, a boundary assessment, the current description's weaknesses, and a proposed replacement descriptionaudit-log.sh — shell commands run in execution orderrewrite-suggestions.md — the four proposed replacement name + description fields in frontmatter format, ready to copy-pasteThe following files are provided as inputs. Extract them before beginning.
Use this skill to send notifications. It can send emails, Slack messages, and webhooks.
This skill handles alerts. Use it when something goes wrong and you need to alert someone. It can also send routine notifications if needed.
Routes outbound communications to the right channel. Works with email, Slack, PagerDuty, and webhooks.
Use this skill for data pipeline tasks. It orchestrates ETL jobs, monitors pipeline health, and triggers backfills.
When reviewing any Python application code in the repo: