frappe-standard-script-report-view
Expert guidance for writing the .js controller for a Frappe Standard Script Report. Use when defining report filters, implementing formatter callbacks, adding…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-01 00:15
Writing & research
14,525 results
to-prd
Turn the current conversation into a PRD and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.
stop-slop-zh-tw
Remove predictable AI writing patterns, translationese, and Chinese mainland terms from Traditional Chinese (Taiwan) articles, and check Taiwan Chinese punctuation and spacing between Chinese and English. Use when the user explicitly asks to remove AI flavor, correct Taiwan usage, review or rewrite Chinese articles, or check Chinese typography; suitable for technical blogs, community posts, and documents. Do not trigger just because a task includes Chinese; pure translation, summarization, fact-checking, code modification, or imitating a personal voice do not fall under this…
deep-read
Deep-read non-technical material and output a complete research article. Four-stage pipeline: Capture → Read → Synthesize → Compose. Material types: papers (arxiv, journals), book chapters, news reports, long-form articles, interview transcripts, industry reports, policy documents. One skill completes it end to end, without relying on external...
survey
Domain landscape mapping — starting from a domain name or research direction, produce a structured domain map (research programs → core controversies → evolutionary threads → open problems → entry recommendations). Three-stage pipeline: reconnaissance → mapping → writing. Use when the user wants to understand the full picture of a domain, quickly enter a new research direction, find a survey-style domain map, or asks "what is the current state of domain X".
loom
Route ambiguous or multi-step Loom requests and create Material Lists. Use when the user provides mixed source material and needs help starting, when the…
loom-research
Capture, read, and synthesize source material into a Synthesis Pack. Use when the user asks to research a topic, deep-dive into a concept, analyze or process…
loom-write
Write drafts and articles from research, create Topic Notes, and finalize publication output. Use when the user asks to write an article, draft from a…
fact-check
Audit a published article or blog post for factual accuracy by extracting verifiable claims, researching each against current sources, and generating a…
cite-before-answer
Verify all claims are backed by evidence before producing a final answer. Use when completing research tasks, writing cited answers, or ensuring factual…
research-protocol
Gather facts from the web using evidence-first approach with mandatory citations. Use when researching topics, answering factual questions, or any task…
onboard
Creates C3 architecture documentation from scratch using staged Socratic discovery. Use when the user asks to "adopt C3", "init C3", "initialize C3", "start…
doc-coauthoring
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision…
dify-docs-api-reference
Rule pack for the Service API specs ({en,zh,ja}/api-reference/openapi_service.json): spec conventions, app-type scoping, code-verification rules, and the audit…
dify-docs-terminology-check
Audit terminology consistency across documentation against the codebase UI labels and the glossary — in prose and in the UI strings shown in screenshots.…
docs
Review the current conversation context and git changes, then persist durable repository knowledge into `dev-docs/*.md` by domain and into `AGENTS.md` for…
blog-post
Create a blog post via guided prompts with git context auto-populated. Use when writing a quick update, retrospective, tutorial, deep dive, or devlog entry.
lwy-mao-methodology
Use Mao Zedong's three philosophical works as practical decision / analysis / writing frameworks. Three lenses: contradiction (《矛盾论》, opposing forces & root…
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with…
isekaizero-storyline-architect
Designs, structures, and formats interactive generative AI storylines, characters, Dungeon Mind RPG mechanics, and Visual Novel Mode asset packages…
bibcite
Manage paper citations and .bib files through the bibcite CLI instead of hand-editing them. Use whenever a task involves adding a paper reference or \cite,…
got-controller
Graph of Thoughts (GoT) Controller - Manages research graph state, executes graph operations (Generate, Aggregate, Refine, Score), and optimizes research path quality. Use this skill when the research topic is complex or multifaceted, requires strategic exploration (depth vs. breadth), or demands high-quality research.
research-executor
Execute the complete 7-phase deep research process. Receive structured research tasks, automatically deploy multiple parallel research agents, and generate comprehensive research reports with complete citations. Use this skill when the user has a structured research prompt.
synthesizer
Synthesize the findings of multiple research agents into a coherent, structured research report. Resolve contradictions, extract consensus, and create a unified narrative. Use this skill when multiple research agents have completed their research, findings need to be combined into a unified report, and contradictions exist among the findings.