Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →gmickel/flow-next-spec-completion-review
Spec completion review - verifies all spec tasks implement the spec requirements.
Passed 10 of 15 test cases with the skill, and 4 of 15 without it.
and 4 more in the full report
8 fixed6 passed either way8 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
In a single execution run for fn-77 where no `--review` flag was provided, how many times should `flowctl review-backend` be called during initialization and backend routing?
| Checked | Without skill | With skill |
|---|---|---|
| Executes flowctl review-backend exactly once during Phase 0. | Missed | Passed |
The instructions your model reads when the skill loads.
Workflow is backend-split. Read workflow-common.md for Phase 0 (backend detection + philosophy), then read ONLY the file matching your active backend:
BACKEND=codex → workflow-codex.mdBACKEND=copilot → workflow-copilot.mdBACKEND=cursor → workflow-cursor.mdBACKEND=host → workflow-host.mdBACKEND=rp → workflow-rp.mdDo not load the others — only the active backend's file is needed.
Verify that the combined implementation of all tasks in a spec satisfies the spec requirements. This is NOT a code quality review (that's impl-review's job) — this confirms spec compliance only.
Role: Spec Completion Review Coordinator (NOT the reviewer)
Backends (branch on the Phase 0 RP_ELIGIBLE probe):
RP_ELIGIBLE=1: RepoPrompt (rp), Codex CLI (codex), GitHub Copilot CLI (copilot), Cursor CLI (cursor), or host-native (host)RP_ELIGIBLE=0: Codex CLI (codex), GitHub Copilot CLI (copilot), Cursor CLI (cursor), or host-native (host) — rp is macOS-only; never list it in guidance you surface (--review=rp stays accepted)The executable Phase 0 lives in workflow-common.md §"Phase 0: Backend Detection" — Read it and execute it ONCE, before any other bash in this skill. It defines $FLOWCTL (bundled — NOT installed globally; which flowctl fails, expected), probes RP_ELIGIBLE, resolves $BACKEND via the single flowctl review-backend call, and handles the ASK / none cases. Never invoke flowctl review-backend a second time in the same run.
Exception: a --review=<backend> argument (see Backend Selection below) wins — when present, set BACKEND from the flag and skip Phase 0's review-backend call + ASK handling (still run its $FLOWCTL / RP_ELIGIBLE setup lines).
When RP_ELIGIBLE=0 (not macOS, no supported RepoPrompt CLI), never steer the user toward rp: every backend summary, recommendation, or override hint you surface presents only the runnable configured backends codex, copilot, cursor, host (plus none). Suppression is not a ban: an explicit --review=rp, FLOW_REVIEW_BACKEND=rp, or review.backend=rp still resolves to rp and errors at runtime via require_rp_cli().
Priority (first match wins):
--review=rp|codex|copilot|cursor|host|none argumentFLOW_REVIEW_BACKEND env var — bare backend (rp, codex, copilot, cursor, host, none) OR spec form (codex:gpt-5.4:xhigh, copilot:claude-opus-4.5, cursor:gpt-5.5-high); host is bare-only (host:<model> is rejected).flow/config.json → review.backend (same bare / spec forms)Check $ARGUMENTS for:
--review=rp or --review rp → use rp--review=codex or --review codex → use codextest cases passed, vs 4 / 15 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.