meta-codereview-current-diff
This meta-skill runs three independent code reviewers (safety, test coverage, and style) in parallel against uncommitted changes, then produces a single arbitrated verdict of BLOCK, BLOCK_WITH_OVERRIDE, or PASS_WITH_NOTES. Use it before committing when you need multi-perspective review feedback instead of iterating through a single reviewer loop, particularly for projects with strict safety and testing standards.
git clone --depth 1 https://github.com/opensquilla/opensquilla /tmp/meta-codereview-current-diff && cp -r /tmp/meta-codereview-current-diff/src/opensquilla/skills/exp/meta-codereview-current-diff ~/.claude/skills/meta-codereview-current-diffSKILL.md
# Codereview of Current Diff (Meta-Skill)
A **combinator-style** meta-skill that runs three independent
reviewers in parallel over the currently-uncommitted diff, then
arbitrates a single verdict with a strict priority rule.
This is the same combinator + arbitrate pattern as
`meta-security-review-bundle`, applied to a code-review domain. The
three reviewers each carry a tight, project-specific rubric — safety
focuses on injection / credentials / G1.6 contract; tests focuses on
the "new public surface ⇒ corresponding test" expectation; style
flags only a fixed list of antipatterns so it doesn't drift into
free-form opinions.
## Trigger surface
Fire by saying `multi-reviewer diff`, `codereview my diff`, or one of the
localized triggers listed in the frontmatter. The diff is read from the working
tree (`git diff --cached HEAD`, falling back to `git diff HEAD` if nothing is
staged).
## Fallback
If `read_diff` returns `NO_DIFF`, the downstream reviewers should
reply with their respective clean verdicts ("CLEAR" / "PASS" /
"CLEAN") and arbitrate emits `PASS_WITH_NOTES: clean`. If a reviewer
LLM step fails, the orchestrator's partial outputs are visible in
`step_outputs`; operator should manually re-run the failed reviewer.Submit audio or video for multilingual dubbing, poll status, and download dubbed audio. Use when the user asks for dubbing, 多语言配音, 视频翻译配音, 译制片, or wants a source clip dubbed into another language.
Generate a structured short-video shooting script from a topic. Emits a strict, machine-parseable shot list (3 shots by default) with image prompt + video prompt + voiceover + on-screen text per shot. Trigger when the user asks for a video script, 分镜, 短视频文案, AI视频, 短剧脚本, or wants visual prompts ready for image/video generation.
Use when the user asks to schedule recurring tasks, one-off reminders, timers, or cron-style jobs through the OpenSquilla cron tool.
Multi-round research with explicit methodology, evidence tracking, and citation-tagged synthesis. Trigger on 'deep dive', 'research report', 'literature review', 'investigate X across sources', 'multi-round investigation'. Distinct from the `summarize` skill, which is a single-pass condensation; this skill maintains a state file across iterations, tracks coverage, and produces a long-form report with per-claim citations. Three execution stages: plan (scope into sub-questions), iterate (record evidence per round), compile (synthesize report). The skill itself does not fetch the web — it tells the host agent which fetches to perform via OpenSquilla's existing web tools, and records what comes back.
Read, edit, or create Microsoft Word `.docx` files. Trigger this skill whenever the user mentions a Word document, .docx file, contract, report, brief, memo, or asks to extract text, modify an existing doc, generate one from a brief, or audit tracked changes. Three execution paths: text-and-structure extraction, in-place edit-by-run (preserves styles), and create-from-scratch with python-docx. Falls back to OOXML unzip-and-patch for layout work python-docx cannot reach.
Capture the current git diff (staged, working-tree, or staged file list) as text. Direct shell call for workflows that need repository diffs without an LLM agent loop.
GitHub operations via `gh` CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: complex web UI interactions requiring manual browser flows (use browser tooling when available), bulk operations across many repos (script with gh api), or when gh auth is not configured.
Query the per-turn DecisionEntry log for skill co-occurrence patterns, meta-skill usage stats, and the router fixture corpus. Returns a JSON summary suitable for downstream LLM consumption. Used by meta-skill-creator's harvest step but also useful standalone for 'which skills did I use most this week?'