Run a brutally honest, massively parallel audit, verification, and remediation loop over a codebase, branch, PR, working tree, or recent change window. Use when the user asks for a crazy parallel agent review, wants bugs and what is not world-class, asks what prevents the repo from being world-class OSS, wants fixes prioritized with risks and benefits, or wants findings turned directly into an implementation loop. Prefer this when the user explicitly wants many parallel agents.
How this skill is triggered — by the user, by Claude, or both
Slash command
/parallel-hardening-loop:parallel-hardening-loopopusThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
<SUBAGENT-STOP>
Use this skill for "review hard, then fix hard" work.
It is optimized for requests like:
Anchor the review before launching agents:
working tree: inspect git status --short and git diff --statrecent changes: inspect git log --since='7 days ago' --name-only --statbranch diff: inspect git diff --name-only <base>...HEADPR review: inspect changed files and PR metadata firstPrefer exact files and dates over vague scope. If the user says "past week", treat that as a bounded recent-change review and use concrete git history to define the slice.
Do the immediate blocker work yourself before delegating:
.claude/reports/ for an existing same-day or same-branch deep-audit-YYYY-MM-DD.md. If one exists and the touched files overlap the audited scope, reuse its verified Tier 1-4 findings instead of re-reviewing. This is the canonical input to step 4.The review phase is owned by the deep-audit skill. Do not reinvent its reading + verification waves. Choose one of:
deep-audit end to end. It runs Phase 0 preflight (scripts/preflight.sh → .audit/preflight/findings.json), canary-gated readers, telemetry-injected verifiers, blind judges, and writes .claude/reports/deep-audit-YYYY-MM-DD.md. Use this as the queue.deep-audit with the slice list narrowed to touched files. Keep its discipline: preflight first, canary reader, mandatory Bug Verifier, file:line evidence on every confirmed finding, persistent report file. Do not skip Phase 0 — bounded scopes still benefit from deterministic ground truth.The fix-wave topology in references/agent-topology.md applies to remediation only. Review topology is deep-audit's.
Keep the critical path local. Do not delegate the very next blocking action.
Use the output contract in references/report-format.md. When deep-audit ran, prefer citing its tiered findings and scorecard verbatim — do not paraphrase verified evidence.
Rules:
If the user asks what to do next, produce a priority-ordered plan. When deep-audit produced a .claude/reports/deep-audit-YYYY-MM-DD.md, its Tier 1 → Tier 4 ordering is the queue. Otherwise:
Always include:
If the user wants implementation, switch immediately into the hardening loop in references/remediation-loop.md.
Key rules:
Do not stop at "here are some ideas." The loop is done only when one of these is true:
If the repo is still not world-class after the first pass, say what remains and start the next highest-leverage loop instead of pretending the job is finished.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub griosai/griosai-marketplace --plugin parallel-hardening-loop