A repository-local process for importing selected third-party skills into a CSL Agent Kit codebase while recording where each skill came from. It preserves source details such as the repository, path, version reference, commit, licence, and upstream status.
Analyze one Git project or component and write one systematic, source-backed current-state report under docs/analysis/. Use for durable project maps, component maps, responsibility and functional-module models, core working flows, or architecture understanding needed for continued development. Exclude quick…
Use when the user wants to release a project. This skill only routes to the matching release SOP, checks readiness, and gathers confirmation items; it does not perform ecosystem-specific publishing itself.
A Chinese-language skill for searching Zhihu, a Chinese question-and-answer community, and the wider web, plus reading the current user's Zhihu content.
Maintain this repository's project-local Task Target alignment evaluations. Use in CSL Agent Kit for level and Safety cases, fresh-context model runs, scoring, and protocol comparisons.
Analyze one Git project, directory, or file against one current implementation question and write one durable, source-backed report under docs/analysis/. Use for /analyze-project, need-bounded deep source analysis, a current behavior chain, or repository-specific prediction checks. Develop and learn are focus aliases…
Run a fail-closed, uncapped Reviewer–Editor loop for code, PRDs, RFCs, design documents, and other deliverables. Use only when the user explicitly requests adversarial review, a two-agent Reviewer–Editor loop, or independent Reviewer approval. Exclude ordinary one-pass review, self-review, routine file operations, and…
Re-explains and re-verifies prior assistant messages with evidence-backed explanations, confidence levels, and ASCII diagrams. Use when the user asks to clarify, justify, get on the same page, or understand the reasoning behind a previous answer.
Use when the user wants to render Mermaid diagrams as SVG, generate polished diagram visuals, create flowcharts, sequence diagrams, state diagrams, class diagrams, ER diagrams, or XY charts. Use for diagram visualization, theming, or presentation-quality diagram output.
Explores user intent and design options before implementing a new feature, component, or behavioral change. Use when the user wants to design before coding, requirements are unclear, or mentions brainstorming, ideation, or exploring approaches.
Diagnose and fix failing tests, CI failures, red builds, pipeline failures, crashes, exceptions, stack traces, timeouts, flaky behavior, regressions, or bug reports. Use when the user reports a failure, asks to fix a bug, asks why tests fail, or asks to make CI pass.
Runs an uncapped Coordinator-mediated Synthesizer–Challenger loop that develops a comprehensive answer through full-batch internal discussion, asking users only for key choices. Use only when the user explicitly requests iterative adversarial or multi-perspective synthesis of a question, topic, idea, decision, or…
Route an ambiguous coding task to indexed Git repositories using human-maintained business responsibilities, page snapshots, and focused CodeGraph lookup. Use when a task does not name one unambiguous repository, may span repositories, or the user asks to list, query, add, update, or validate locally indexed projects.
Build a lightweight map and project glossary before exploring an unknown repository or unfamiliar module. Use for quick orientation, entry-point discovery, broad code exploration, feature work in a new codebase, or shared vocabulary for key concepts, types, responsibilities, and call relationships. Do not use for a…
Provides brief or detailed, source-backed in-chat understanding of any target. Use for TL;DRs, quick overviews, exploration, in-depth explanations, or detailed reports. Do not use for background or durable-file research, reviews, audits, recommendations, tutorials, plans, implementation, or repository mapping.
Use when the user wants app-icon artwork, a transparent 1024×1024 PNG, Chrome extension icons, or platform icon materials. Offers 10 styles, generates a green-screen source, waits for approval, removes it with Node.js sharp, and validates outputs. Exclude general images, vector-system edits, and…
Parses a Figma URL and generates a structured text description of the UI layer architecture. Use when the user provides a Figma URL and asks to parse, analyze, describe, or extract design information.
Manages Zhihu iOS component dependencies and builds via venom-cli. Use when the user mentions Zhihu iOS development, venom-cli, component dependency management, or asks to build/check/make/switch/integrate components in a Zhihu project.
Create first-time Zhihu Yunxiao One MRs; list open MRs or QA; batch-approve requests; and manage the macOS approval daemon and dashboard. Use for Yunxiao MR creation, listing, QA, approval, or daemon management. Exclude metadata edits, code review, join/restore, and GitHub or GitLab PRs.
Create, inspect, update, enable, disable, delete, and audit persistent Agent Hooks rules that inject prompts or run scripts at supported hook timings. Use for cross-session user directives, reusable changed-file or command matching, runtime guards, hook-like automation, or trigger inventory and management for Codex…
Manage persistent Agent Rules. Use when the user wants to add, edit, list, or remove an unconditional rule, change a bundled default rule, or inspect how built-in, user, and project rules are injected. Use Agent Hooks for conditional or scripted automation instead.
Use when the user wants to list, create, inspect, or follow SOPs, procedures, playbooks, runbooks, workflow rules, or process documents. Also use when the user mentions "SOP", "procedure", "playbook", "runbook", "process doc", or "per our SOP".
10 4d agoA67 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: