Ensemble SOLID review — fans the ruleset across overlapping focused workers over the same code, then reduces by corroboration.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Fixed paths (relative to this arm directory, the claude -p working directory):
../ruleset/solid-rules.json*.py under ../corpus/cases/./findings/workers/ (absolute path when calling the planner/workers)./findings/findings.mdplan_ensemble.py and reduce.py from the ensemble-rule-review skill. From this
arm directory they are at ../../../plugins/plugin-creator/skills/ensemble-rule-review/scripts/;
the runner may pass an absolute path instead — use whichever it provides.Plan (deterministic). Run the planner over the shared ruleset, with ./findings/workers/ (as an
ABSOLUTE path) as the report dir:
uv run <scripts>/plan_ensemble.py ../ruleset/solid-rules.json \
--report-dir "$(pwd)/findings/workers" --window 2 --json
Use the worker assignment and recommended keep-threshold from the planner's output.
Map (parallel). Spawn the principles-reviewer agent once per worker in the plan. Give
each its groups + per-group rules as YOUR RULE SLICE, the identical targets (all files under
../corpus/cases/), and its planner outfile. Run all workers in one parallel batch. Workers
write location as corpus/cases/<file>:<line>.
Reduce (deterministic). Merge by corroboration on (group, location) and write the ranked result
to ./findings/findings.md:
uv run <scripts>/reduce.py "$(pwd)/findings/workers" --glob 'worker-*.md' \
--keep-threshold 2 > ./findings/findings.md
The reduced, ranked findings in ./findings/findings.md are the arm's output — the scorer parses
them against ../corpus/gold.json.
Each principles-reviewer worker emits the fixed candidate schema.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Add automated documentation updater to any Claude skill. Creates a Python sync script that downloads upstream docs, processes markdown for AI consumption, and maintains local cache with configurable refresh. Collects template variables, then delegates implementation through 5-phase workflow. Use when adding auto-updating reference documentation to plugins or skills.
中文简介正在准备中。当前显示原文说明。
SAM-style feature initiation workflow — discovery through codebase analysis, architecture spec, task decomposition, validation, and context manifest. Use when a user asks to add a feature, plan a feature, or convert an idea into an executable SAM plan.
中文简介正在准备中。当前显示原文说明。
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
中文简介正在准备中。当前显示原文说明。
Browser automation for AI agents using the agent-browser CLI and Playwright. Use when navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, logging into sites, or automating any browser task. Triggers on "open a website", "fill out a form", "click a button", "scrape data", "test this web app", "automate browser actions", or any programmatic web interaction request.
中文简介正在准备中。当前显示原文说明。
Runs the description-drift experiment — spawns all Claude Code agents simultaneously to collect self-reported capabilities, then compares them against static frontmatter descriptions to reveal how reliable orchestrator routing based on descriptions actually is. Use when measuring description drift across the agent fleet, re-running the capability collection experiment, analyzing a specific agent's self-reported capabilities, or auditing whether frontmatter descriptions accurately reflect agent behavior.
中文简介正在准备中。当前显示原文说明。
Create or adapt Claude Code agent definitions. Use when creating an agent, changing subagent configuration, selecting agent scope, or designing a specialized delegation role.
中文简介正在准备中。当前显示原文说明。