Loading...
Loading...
Found 1,915 Skills
This skill should be used when the user says phrases like "record a topic", "new topic", "how is this topic", "I have an idea", "help me note this down", or shares a rough content idea that needs evaluation and recording. Even if the user casually mentions a content idea, actively trigger the evaluation process without waiting for the user to explicitly say "record". First, use the five-dimensional logic of dbs-content to diagnose whether the topic is worth doing. Only record it if it is worth doing, and recommend 3-5 similar topics by drawing inferences. Do not trigger: Deepen the topic to generate an outline (use li-topic), directly write scripts (use li-writer), or AI polish or beautify the topic title. Use when the user wants to "record a topic", "log a topic idea", "is this topic worth doing", or shares a rough contentclaise Du.弹应用样子Pr广解除禁 \ 诊断和记录.
How to build scenes: entry, dialogue, pacing, transitions. Use when writing or evaluating how scenes work on the page.
Builds site selection and cannibalization analysis workflows in CARTO. Triggers when the user mentions site selection, cannibalization, cannibalizing, new store location, where to open, optimal location, facility placement, network impact, overlapping catchments, twin areas, similar locations, look-alike areas, find locations like my best, store overlap, revenue impact of new store, commercial hotspots, demand hotspots, location scoring, location ranking, expand network, new branch, franchise placement, EV charging siting, or wants to evaluate candidate sites, quantify overlap between trade areas, or find areas that resemble top-performing locations.
Read all open bugs in production/qa/bugs/, re-evaluate priority vs. severity, assign to sprints, surface systemic trends, and produce a triage report. Run at sprint start or when the bug count grows enough to need re-prioritization.
Expert evaluator for Prometheus label strategy. Audits, designs, and improves label schemas using cardinality scoring, access-pattern alignment, static vs. dynamic label rules, histogram bucket discipline, instrumentation hygiene, and source-side prevention via relabel_config / metric_relabel_configs. Use when the user asks to evaluate, audit, design, or improve Prometheus labels — or asks how to prevent high cardinality at the source. For post-ingest aggregation, see the adaptive-metrics skill. For "why is my Prometheus slow / expensive right now" triage, see prometheus-cardinality-troubleshooter.
Apply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading. Bias toward deletion and the smallest change that solves the problem.
Plan Nemotron customization pipelines from repo steps: SFT, PEFT/LoRA, AutoModel vs Megatron-Bridge, DPO/RLVR/GRPO/RLHF, curate-then-translate, BYOB/MCQ benchmark prep or translation, checkpoint conversion, ModelOpt optimization, and endpoint or checkpoint evaluation.
Performs runtime mobile security exploration of iOS applications using Objection, a Frida-powered toolkit that enables security testers to interact with app internals without jailbreaking. Use when assessing iOS app security posture, bypassing client-side protections, dumping keychain items, inspecting filesystem storage, and evaluating runtime behavior. Activates for requests involving iOS security testing, Objection runtime analysis, Frida-based iOS assessment, or mobile runtime exploration.
Use when writing QGIS expressions for filtering, labeling, symbology, or field calculations. Prevents expression syntax errors and context misconfiguration. Covers QgsExpression parsing, evaluation contexts, field calculator, data-defined properties, and custom functions. Keywords: QgsExpression, expression, field calculator, label expression, data-defined, @qgsfunction, filter, evaluate, calculate field, formula, conditional label, dynamic value.
Generate a Well-Architected-aligned Architecture Decision Record (ADR) that documents a design decision with context, options evaluated, trade-offs, and WA pillar impact.
Produce a comprehensive, evidence-grounded prioritized action plan from any PM input (notes, transcripts, drafts, executive asks, Slack threads, or a raw situation). Outputs one saveable document with an executive summary, input mirror, situation classification (Cynefin), the binding constraint (Theory of Constraints), prioritized questions and open decisions, a ranked action plan with the critical effort plus follow-ons, risks and pre-mortem, copy/paste prompts for downstream pm-skills, and an evidence map. Builds a source ledger and cites exact input quotes; refuses High-confidence plans for Complex or Chaotic situations. Use when you want the critical next effort and how to execute it.
Decide where files live in an ML experimentation project: reusable code in `src/<pkg>/`, one `# %%` script per experiment in `experiments/`, design notes + index in `journal/`, reports in `reports/`, agent-only probes in `scratch/`, narrative digest in `overview/summary.md`. Owns the layout, the file-creation rules (one file per experiment, ask before editing), and the jupytext `# %%` script convention. Never imposes `data/` — the user owns that. TRIGGER — any of: - Starting a new ML project / scaffolding a workspace. - About to create the first experiment file in a project. - About to create `src/<pkg>/data.py` / `features.py` / `pipeline.py` / `evaluate.py` for the first time. - About to write a `.ipynb` for experimentation — redirect to a `# %%` script under `experiments/`. - User asks where something should live, how to organize the project, or how to set up the workspace. - About to add a new experiment iteration — decide new file vs edit existing (ask the user). SKIP when: the file is clearly part of an already-populated module (e.g., adding a function to existing `features.py`); pure refactor inside a single existing file; pipeline declaration mechanics (`build-ml-pipeline`); evaluation mechanics (`evaluate-ml-pipeline`); skore symbol lookup (`python-api`). HOW TO USE: **first run the Detection table** below — if any signal matches, glue to existing conventions (do not rename or move folders). If no signal matches, scaffold the default layout. **Emit the Pre-flight checklist as visible text and read the Stop conditions before any file is created or edited.** Use templates in `templates/`; copy and adapt, do not rewrite from scratch.