Loading...
Loading...
Found 523 Skills
Generates Qt Quick Test cases (TestCase, SignalSpy, tryCompare) for QML components. Use for "write QML tests", "qml test", "qt quick test".
Use when the user is investigating QML / Qt Quick performance — both vague complaints ("the UI feels laggy", "this is slow", "frames are dropping", "the app stutters") and explicit asks to profile, find hotspots, or optimize bindings, signals, or rendering. Runs qmlprofiler on a 2D QML application, parses the .qtd trace, and analyzes hotspots against the source with frame-time, memory, and pixmap-cache summaries. Does NOT cover Qt Quick 3D.
Use when the user asks to "track our share of voice", "what share of the conversation do we own vs competitors", or "trend our SOV this quarter"; computes SOV% = brand mentions ÷ (brand + competitor panel mentions) per platform per period on a LOCKED competitor panel — a panel switch invalidates the trend (restart the series and log the break; the ECHO O3 rule) — plus a sentiment-weighted SOV variant (sentiment labeled Estimated unless human-coded) and a Wikipedia-pageviews attention-share alternative; built from keyless listening connectors, gdelt.py news echo, and user exports — public counts only, closed platforms are never scraped. Not for backlink or offsite SEO signals — use offsite-signal-analyzer. 声量份额/竞品声量对比/提及份额/注意力份额
Use when the user asks to "find influencers", "build an influencer list", or "discover creators in [niche]"; produces a multi-platform candidate pool, per-influencer profiles, authenticity red-flag screening, and a tiered shortlist with preliminary triage signals. Not for STAR scoring or ranking a known shortlist — use fit-scorer. 达人挖掘/找达人/创作者名单
Use when a developer wants to iterate on ONE specific Agent Observability / LLM Obs trace whose output they didn't like — re-running that trace against their LOCAL code, seeing a concise diff of the old vs new output, and looping (change code → replay → diff) until satisfied. Invoked as /agent-observability-replay-trace <trace-id> [changes to test]. Signals: "replay this trace"; "iterate on a trace"; "this trace's output is wrong, fix it and re-run"; "re-run trace <id> with <change>"; pasting a trace id from the Agent Observability UI with a description of what to fix. It fetches the trace via the datadog-llmo MCP or the pup CLI, edits code, re-runs the app to emit a NEW trace, and diffs the two — no local server, no browser. For agents traced with ddtrace / LLM Obs (Python first-class), with JSON-serializable entry input. Do NOT use for: scored Experiments or the browser "Replay" button (that's agent-observability-replay-experiment), building an experiment from a dataset/CSV, writing evaluators, root-causing failed traces, or RUM/HTTP session replay.
Break down complex problems into a well-structured framework that is hierarchical, non-overlapping, and exhaustive. It is suitable for scenarios where you need to sort out chaotic information, express ideas clearly to others, or analyze problems comprehensively. Use this skill when you are faced with a bunch of scattered elements and cannot form a holistic view, or when you need to make a structured report to others. It is not applicable to highly structured problems or quick decision-making scenarios that require intuitive judgment. Key trigger signals: "Too much information to sort out", "How to express this clearly", "Is anything missing?", "Help me break down this problem."
Innovate with two systematic approaches: Recombinative Innovation (collect external elements and recombine them) and Mutational Innovation (dismantle internal existing structures and modify them). All innovations must meet three elements simultaneously: New Elements + Value Increment + Feasibility. Applicable scenarios include breaking through existing frameworks, seeking new products/solutions, or solving the problem of "innovation relying on luck". Not applicable to pure execution-oriented optimization improvements (which do not require new elements). Key trigger signals: "Need new ideas", "How to innovate", "Creative exhaustion", "Serious product homogenization".
Use biological evolution logic (genetic variation + natural selection) to address uncertainty, and iterate products or teams through the cycle of MVP launch → market feedback screening → variation and innovation → accumulating advantages. It applies to scenarios with unclear goals, rapidly changing environments, and inability to plan in advance. It is not suitable for deterministic projects with clear goals and clear paths (planning is more efficient). Planning and evolution are complementary like Yin and Yang: Planning = Yang (efficiency), Evolution = Yin (addressing uncertainty). Key trigger signals: "Unsure what users want", "The market changes too fast", "Plans can't keep up with changes", "Let's get started first"
Use the 'Dialysis Prism' framework to penetrate the surface of problems and identify their root causes. Resolve persistent recurring issues through three steps: calibrating Goal B, reconstructing Method A, and eliminating Variable C. It applies to scenarios where the same problem keeps recurring despite various attempted solutions, as well as analytical scenarios that require precise problem definition before resolution. Use this skill when you find that 'patchwork' solutions are ineffective. It is not suitable for scenarios in entirely new fields with no historical methods to reference, nor for purely uncertain events (which fall under the probability/risk domain and require the use of mirror-world). Key trigger signals: 'Why does this problem happen again?', 'Why can't we solve it for good?', 'I've tried so many methods but none work', 'What exactly is the root cause of this problem?'
Make rational and objective decisions using a four-step process: Focus on goals to filter trivial matters → Find a third option to break through option limitations → Avoid cognitive biases → Quantify and score to make the final choice. Suitable for scenarios where you are struggling with major decisions, options seem to be mutually exclusive, or you worry about being misled by intuition. Not applicable to daily low-risk small decisions (over-quantification is a waste of time). Key trigger signals: "Torn between choosing A or B", "Don't know how to choose", "Not satisfied with either but have to pick one", "Help me make a decision".
Design and operationalize SRE dashboards that surface reliability, latency, error, saturation, and capacity signals across services. Use when building observability views for SLOs, incident response, and executive reliability reporting.
Activated when users are about to make major decisions based on second-hand information (reports, rumors, others' summaries), or when the team shows a tendency to "make decisions without on-the-ground research". Typical trigger signals: "I've read several industry reports", "Just send someone to do the research", "Based on my experience, it should be like this". Non-activation scenarios: Decisions are already based on sufficient first-hand information, low-risk minor decisions don't require in-depth research, or reliable data sources are already under continuous monitoring. Difference from the "Seek Truth from Facts Information Processing Skill": This skill focuses on "how to collect high-quality first-hand information", while the latter focuses on "how to process and refine information after obtaining it".