loading
loading
Scope a workflow before automating it — and say 'keep it manual' when risk or ambiguity is high.
Will tell you to keep a workflow manual when risk is high — it scopes the automation before you build something brittle around an unmapped process.
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
Workflow Automation Scope takes a workflow description, its frequency, the current pain, and the systems involved, then returns a scope: trigger, inputs, outputs, owner, tools, risks, and — when warranted — a recommendation not to automate yet. It pushes back on automating before the edge cases are understood and on skipping the human-approval step, so you don't build brittle automation around a process you haven't actually mapped.
Let your agent browse, click, and fill forms like a real user.
Gives your agent a browser without brittle selectors — the self-healing locator survives the DOM changes that break every hand-written scraper.
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.
Audit a Zapier or Make stack for silent failures, data exposure, duplicate triggers, and missing retries.
Finds the no-code automations failing silently or leaking data — it maps triggers, retries, and owners instead of trusting the UI labels.
Classify incoming support messages, draft on-policy replies, and escalate the cases you shouldn't auto-answer.
Drafts on-policy replies but refuses to auto-answer billing, legal, security, or angry tickets — the cases that need a human.