agent-skills

Process one GitHub issue end-to-end — read the issue + referenced repo docs/code + existing comments, verify against the landed implementation/intent, and post evidence-backed findings as a comment on the issue. Covers doc-review, doc-audit, system-audit, research, and idea issue types. Use when handling a single issue (issue-sweep calls this per issue).

Sweep open GitHub issues for unprocessed human input and act on each via the issue-review skill — delete-PRs for human-approved deprecated docs, doc-update PRs for approved drifted docs, fix-PRs for approved bugs, analysis+TDD-plan comments for feature/design requests (then implement after confirmation), close issues whose PR merged, comment-only on conditional/security/needs-decision ones. The actionable signal may be a comment OR the issue body. With --autofix-green, also auto-fixes "green" issues that have no human reply yet (unambiguous + verifiable-here + low-risk + non-security) — reproduce→fix→test→PR, never auto-merge. Run manually (/agentloop:issue-sweep) or on a schedule. Designed for a doc-audit + spin-off + feature workflow.

One-command setup/update of an agentloop FLEET on a teammate's machine or cloud — asks a few defaulted questions, then generates/reconciles the two config files (deployment.json + repos.json) and installs the schedule. LOCAL = a crontab marker-block wiring fleet/driver.ts (one row per skill; the driver fans out to every covered repo). CLOUD = one claude routine per (repo×skill) via RemoteTrigger, batch-created from the same catalog. Idempotent — re-run to upgrade. This is the SCHEDULING side that `bootstrap` (repo adoption) deliberately leaves out. Interactive — never runs unattended.

Independent clean-context review of ONE open GitHub pull request — read PR diff + linked issue + verify every claim against live code/tests + run the verification gate (pre-merge) and diagnose its root-cause + detect conflicts with sibling PRs, then emit an evidence-backed merge-readiness verdict (MERGE / COMMENT / SUPERSEDE / BLOCK / CLOSE). Runs verification every time (read-only safe); --post writes one verdict comment. Never auto-merges (that gated step belongs to pr-sweep). Use /agentloop:pr-review <pr#> for a single PR; pr-sweep batches this engine across all open PRs.

Batch-review every open GitHub PR and drive it to a terminal state autonomously — fan out a clean-context pr-review per PR (verify claims against live code, run the verification gate), cluster PRs by shared issue + shared files, DEDUP-CLOSE same-issue duplicates (keep the best one, comment + close the twin), and GATED auto-merge every verified non-breaking PR (docs/tests/fixes AND features) while escalating only security / breaking changes / architecture-direction decisions to a human. Designed to run on a schedule on an independent machine so PRs get reviewed + merged without a human in the loop. Run /agentloop:pr-sweep (review+comment+dedup-close only), /agentloop:pr-sweep --merge (also auto-merge gated PRs), or /agentloop:pr-sweep --dry-run (report only).

Iterative clean-context review of a design/plan document or issue — spawn independent-perspective reviewers each round, score, and synthesize findings without carrying prior-round bias. Use to review an implementation plan, architecture doc, or design proposal before building.

Run a repo's deterministic verification gate (build/lint/types/tests/etc.) and post one measured report to the PR. Use before opening or merging a PR. The engine is repo-agnostic; the check list comes from the repo's own .claude/verify/config.ts.

Automated phase-by-phase implementation with a verification loop — drive a multi-phase build plan one phase at a time, each phase implemented then verified (static + dynamic + adversarial) before advancing. Use to execute a phased implementation plan (tasks.md) autonomously.

Deterministic issue-relationship graph over GitHub native sub-issues + dependencies — compute the ready set / parent-rollup candidates / close-kick targets as pure calculation (scripts, no LLM judgment), write real edges when creating spin-off issues, and mutually exclude terminal actions across parallel agents via claim-comment fencing. Called by issue-sweep (candidate injection), issue-review (edge writing + rollup), and the future agent:ready producer routine.

Git Commit Generator - Generate standardized commit messages following Conventional Commits specification

PR Generator - Generate standardized Pull Request based on branch diff and submit via gh or save as PR.md

One-time setup for a repo adopting the agentloop plugin — scaffold repo-profile, create the controlled GitHub labels, scaffold the verification gate, and preflight the environment. Run this once when onboarding a new repo to the loop-engine skills. Does NOT schedule routines (that's the repo's own infra).

Analyze code changes to find related areas that may also need modification. Supports uncommitted changes, specific commits, commit ranges, and branches. Use before committing or opening a PR to catch missed updates.

Create standardized Pull Requests for blocklet projects. Performs lint checks, unit tests, version updates, and creates PRs following PR templates. Use `/blocklet-pr` or say "help me submit a PR", "create pull request" to trigger.

Creates a new release for a blocklet project by bumping version, building, and bundling. Use when asked to "create a new release", "bump and bundle", or "update blocklet version".

Configure development environment for blocklet-type repositories. Supports parsing GitHub Issue URLs, Blocklet URLs, or problem descriptions to automatically locate repositories, check permissions, clone code, install dependencies, and start development server. Use `/blocklet-dev-setup` or say "help me fix the xxx blocklet issue", "I want to develop xxx blocklet", "I want to modify code related to this URL" to trigger. In short, use this as the starting point when you want to develop a blocklet.

Guide users to choose between blocklet-dev-setup and blocklet-server-dev-setup. Ask what to develop (blocklet or server), handle migration from existing environments, explain convention directories, and showcase advanced usages. Use `/blocklet-getting-started` or say "I want to start blocklet development", "how to setup blocklet dev environment" to trigger.

Clone blocklet-server repository and guide execution of the in-project project-setup skill. Use `/blocklet-server-dev-setup` or say "help me configure blocklet-server environment", "setup blocklet-server" to trigger.

Manage skills from local paths or git repositories - add, update, or remove skill tips in ~/.claude/skills with group-skillname format

Git branch management tool. Detects main iteration branch and branch naming conventions, handles branch creation and switching. Referenced by blocklet-dev-setup, blocklet-pr, and other skills.

Analyze Blocklet Server related URLs, identify their type (daemon/service/blocklet), and locate the corresponding development repository. Supports analysis of IP DNS domains and regular domains.

Evaluate proposals, technical decisions, and product directions against Robert's thinking patterns, ArcBlock's AFS/AINE architecture, and engineering philosophy. Use when reviewing proposals, evaluating technologies, or self-reviewing designs.

Load ArcBlock company context (products, technical architecture, strategy) on demand. Use `/arcblock-context` to see available topics, or `/arcblock-context <topic>` to load specific context.

AI 采访式内容创作系统。不是人写，也不是 AI 自动写，而是 AI 分析后采访人再按人的风格写。通过问答不断沉淀用户画像（观点、写作风格、思考逻辑），持续迭代演进。支持博客、社交媒体、观点文章等场景。

Converts static web or Next.js projects into ArcBlock blocklets using provided DID. Analyzes project structure, generates configuration files, and validates setup. Requires blocklet DID as parameter.

Use when creating, modifying, or debugging Claude Code plugins. Triggers on .claude-plugin/, plugin.json, marketplace.json, commands/, agents/, skills/, hooks/ directories. Provides schemas, templates, validation workflows, and troubleshooting.