Menu
Skeleton skill for eval fixture — replace with the real skill content
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Encapsulates the DECISIONS: tagging protocol for architectural decision documentation in task outputs
Tag tests with AC references so /df:verify L3 can confirm every spec AC is exercised by at least one test
Produces structured JSON intelligence for a remote GitHub repo — fetches metadata and file tree via gh api, reads key files via WebFetch. No local clone. Use when evaluating an unfamiliar repo before planning integration work.
Fetches live web content using headless Chromium via Playwright. Use when you need to read documentation, articles, or any public URL that requires JavaScript rendering. Falls back to WebFetch for simple HTML pages.
Verifies UI acceptance criteria by launching a headless browser, extracting the accessibility tree, and evaluating structured assertions deterministically. Use when a spec has browser-based ACs that need automated verification after implementation.
Discovers requirement gaps during ideation. Use when user describes features, planning specs, or requirements seem incomplete. Asks clarifying questions about scope, constraints, edge cases, success criteria.
| name | example-skill |
| description | Skeleton skill for eval fixture — replace with the real skill content |
| allowed-tools | ["Read","Edit","Bash","Write"] |
This is the skill file that the eval loop will mutate each iteration. Replace this entire file with the real skill you want to evaluate.
!cat specs/doing-*.md 2>/dev/null || echo 'NOT_FOUND'
!cat .deepflow/decisions.md 2>/dev/null || echo 'NOT_FOUND'
Apply the changes described in the active spec, one task at a time.
output/{task-id}/result.jsonstatus: "complete" fieldspecs/ or .deepflow/