Loading...
Loading...
Found 337 Skills
Review a Ralph plan and bd graph for defects via a subagent.
Generate candidate fixes for verified security findings. Consumes TRIAGE.json (preferred), VULN-FINDINGS.json, or a vuln-pipeline results directory. Pipeline input is delegated to the execution-verified `vuln-pipeline patch` ladder; static-analysis input gets a per-finding patch subagent + independent reviewer and is written as inert diffs for human review. Writes PATCHES/bug_NN/{patch.diff,patch_result.json}, PATCHES.md, and PATCHES.json. Use when asked to "fix the findings", "patch these vulns", "generate fixes", or "close the loop on triage".
Claude Code extensibility: agents, skills, output styles. Capabilities: create/update/delete agents and skills, YAML frontmatter, system prompts, tool/model selection, resumable agents, CLI-defined agents. Actions: create, edit, delete, optimize, test extensions. Keywords: agent, skill, output-style, SKILL.md, subagent, Task tool, progressive disclosure. Use when: creating agents/skills, editing extensions, configuring tool access, choosing models, testing activation.
Monitor background processes from Claude Code using sentinel files, heartbeat liveness, and subagent polling. Best practices and anti-patterns for autonomous loops that need to kick off work, detect completion/failure/hang/timeout, and resume the main context without wasting tokens. TRIGGERS - monitor background process, sentinel file, heartbeat monitoring, process supervision, agentic loop monitor, background task health, detect hung process, poll for completion, watchdog pattern, process liveness, monitor long-running task, agent poll loop, circuit breaker pattern.
Plan a non-trivial code change end-to-end — size triage (XS–XL), slicing strategy, optional parallel subagent dispatch, per-slice Implement → Test → Verify → Commit discipline. Use for any multi-file change, refactor across files, executing a planned task from any planning source, cross-cutting modification (analytics sweep / i18n / library migration), or when about to write more than ~100 lines. 也用于增量实现 / 切片落地 / 推进已规划任务 / 跨切面改动。Skip only for trivial XS edits and pure documentation / configuration changes.
Batch-translate content files using Gemini CLI as a subagent, with Claude orchestrating quality and validation
A curated collection of 136+ specialized Codex subagents for development tasks across 10 categories
End-to-end orchestration for non-trivial software feature development. Use this skill whenever the user asks to implement a PR-sized feature, break down a plan, have subagents review a plan, run a plan-review-development-acceptance loop, coordinate multiple review perspectives, produce an acceptance report, or generate an HTML PR summary. Prefer this skill for multi-step code changes even if the user only says "build this feature" and the task is not a tiny one-file edit.
Invoke a Rubber Duck Reviewer subagent to independently critique plans and implementations before proceeding. Use when the agent is about to implement a non-trivial plan (multi-file changes, architectural decisions, security-sensitive logic, database schema changes), after completing a self-contained unit of work (module, endpoint, feature), when stuck or facing repeated failures (same test fails 2+ times, unexpected results), or when the agent wants independent validation of assumptions and design decisions. Triggers on any non-trivial implementation task where independent critique would catch blind spots before they become costly mistakes.
This skill should be used when the user wants to bulk-build ArcKit artefacts in parallel rather than running individual /arckit:* commands one at a time. Load whenever the task sounds like 'kick off a build', 'build everything', 'generate all artefacts', 'run all the commands', 'rebuild this project from scratch', 'resume the build', 'pick up where we left off', 'refresh the artefacts', 'run the recipe', 'build the whole project end-to-end', or 'parallel build', or mentions `--plan`, `--resume`, `--target`, `--refresh`, `--recipe`, or `.arckit/state.json`. The skill orchestrates parallel /arckit:* generation using subagent isolation: reads project state, computes the artefact dependency DAG, dispatches one subagent per target per wave (each subagent invokes a /arckit:* skill in its own context), validates outputs, commits the wave, and persists progress to .arckit/state.json for resumability.
Delegate menial, well-scoped coding tasks to a cheap Qwen-backed subagent via the `claude-9arm` command instead of burning Claude tokens/quota. Use when the work is mechanical and low-risk — bulk renames, formatting, boilerplate, find-replace, grep-style search & summarization, reading/condensing logs or files, test/docstring/comment scaffolding, or running builds/linters/tests and reporting pass-fail. Also use when the user says "use qwen", "delegate this", "send it to 9arm/qwen", or "do this cheaply". Do NOT use for architecture, design, debugging judgment, security-sensitive edits, or anything needing this conversation's context.
Static source-code vulnerability scan. Reads a target directory (and THREAT_MODEL.md if present), spawns parallel review subagents per focus area, and writes VULN-FINDINGS.json + .md for /triage to consume. Read-only — no building, running, or network. For execution-verified crashes, use vuln-pipeline instead. Use when asked to "scan for vulns", "review this code for security issues", "find bugs in <dir>", or as the step between /threat-model and /triage.