Loading...
Loading...
Found 1,058 Skills
Use when the user needs technical SEO audits, meta tag optimization, structured data markup, Core Web Vitals improvement, or search engine visibility enhancement. Trigger conditions: site audit request, meta tag review, Schema.org implementation, page speed optimization, indexability issues, sitemap or robots.txt configuration, hreflang setup, Open Graph or Twitter Card tags, rich snippet eligibility.
Use when the user needs prompt design, optimization, few-shot examples, chain-of-thought patterns, structured output, evaluation metrics, or prompt versioning. Triggers: new prompt creation, prompt optimization, few-shot example design, structured output specification, A/B testing prompts, evaluation framework setup.
Design and operate reconciliation processes that ensure data accuracy across portfolio management custodian and clearing systems. Use when building or evaluating a daily position cash or transaction reconciliation process, investigating discrepancies between internal systems and custodian records, diagnosing recurring break patterns especially from corporate actions or pricing differences, setting tolerance thresholds for position cash or market value matching, implementing three-way reconciliation across advisor system custodian and clearing firm, designing break investigation workflows with aging and escalation, normalizing data across multi-custodian feeds from Schwab Fidelity or Pershing, reconciling cost basis tax lots or accrued income across systems, evaluating reconciliation platforms like Arcesium Duco or Advent Geneva, or preparing for regulatory examinations on books and records accuracy.
Use this skill when users ask for frontend library/framework usage, APIs, best practices, or examples (e.g. Vue, Vite, React, Tailwind). Always fetch up-to-date docs with Context7.
Use when creating Frappe Whitelisted Methods (Python API endpoints) for v14/v15/v16. Covers @frappe.whitelist() decorator, frappe.call/frm.call invocations, permission checks, error handling, response formats, and client-server communication. Keywords: whitelisted, API endpoint, frappe.call, frm.call, REST API, @frappe.whitelist, allow_guest, API endpoint example, frappe.whitelist syntax, how to expose function.
Validates .env files and environment variable configurations against project requirements. Checks for missing required variables, type mismatches, insecure defaults, unreferenced variables, and common configuration errors. Compares .env against .env.example, code references, and deployment manifests. Produces a structured validation report with severity-ranked findings. Triggers on: "validate env file", "check environment variables", "env file audit", "missing env vars", "env validation", "check .env", "environment config check", "validate configuration", "env file review", "dotenv validation". Use this skill when verifying environment configuration completeness and correctness before deployment or after onboarding. NOT for secret scanning (use repo-sentinel or secret-scanner). NOT for general config file editing (use filesystem skill).
Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read/write commands, return stable JSON, manage auth, and pair with a companion skill.
**Mandatory** before any commit or push. Run Definition-of-Done checks from change scope and report exact pass/fail per command.
Apply discourse analysis to examine how language constructs meaning, power relationships, and social reality in texts and communications. Use this skill when the user needs to analyze how a text frames an issue, uncover hidden assumptions in language, examine power dynamics in communication, or deconstruct media/corporate/political messaging — even if they say 'what's really being said here', 'how is this framing the issue', or 'analyze the language in this document'.
Maintain JSONL-only profiler performance test cases under csrc/ops/<op>/test in ascend-kernel. Collect data using torch_npu.profiler (with fixed warmup=5 and active=5), aggregate the Total Time(us) from ASCEND_PROFILER_OUTPUT/op_statistic.csv, and output a unified Markdown comparison report (custom operator vs baseline) that includes a DType column. Do not generate perf_cases.json or *_profiler_results.json. Refer to examples/layer_norm_profiler_reference/ for the reference implementation.
Remove AI-generated traces from text. Suitable for editing or reviewing text to make it sound more natural and human-written. Based on the comprehensive guide of "Signs of AI Writing" from Wikipedia. Detects and fixes the following patterns: exaggerated symbolism, promotional language, superficial analysis ending with -ing, vague attribution, overuse of dashes, rule of three, AI vocabulary, negative parallelism, excessive connecting phrases.
Build standalone custom pages using Amis low-code framework, independent of object records. Pages are defined as paired .page.yml (metadata) and .page.amis.json (UI schema) files in main/default/pages/. Covers page types (app, list, record), render_engine configuration, pageAssignments for desktop/mobile, and Amis schema with components like service, crud, chart, form, wizard, tabs. Includes examples for dashboards, reports, and custom forms.