piflow-gate

piflow-gate is a Plan & work review gates skill for AI agents, published by blueif16 in the PiFlow repository on GitHub. Skillspace rates piflow-gate D (59/100) and it passed the safety scan; the rating is based on static analysis only.

Pi Flow · GATE — the base agent that judges whether ONE fixer's candidate edit actually fixed its issue, and decides its fate: STAGE it for a human to adopt, or REJECT it back to a fresh fixer. The third agent of the optimize loop and the last: triage NAMES the defect, the fixer SOLVES it, the GATE judges the fix — the issue file is the boundary object through all three, and the loop always runs them in that order. The CLI spawns this agent over the PROVED candidate via `piflowctl optimize verify --node <id>` (the standalone gate-only re-check — there is NO `optimize gate` verb), or INLINE during `piflowctl optimize fix --node <id>` on the full-tier soft path, equipped with this skill. LOAD / FOLLOW when: you ARE the gate/verify turn over a fixer's candidate; you must decide ACCEPT-and-stage vs REJECT-and-drop-back; you must audit a fix for reward-hacking / a band-aid / teaching-to-the-test; or a human asks "did the fix actually work", "is this a real fix or a hack", "why was the…

Grade
D
Quality
59 / 100
Safety
Passed
GitHub stars
101

Unproven: rated by static analysis only, not yet compared head-to-head.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

Our review

Architecture
84 / 100
Maturity
Basic: a single SKILL.md
Security scan
No issues found
License
MIT
Adoption
Adopted by 1 other repositories, in 0 collections

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.