Build immersive, cinematic 2.5D interactive websites using scroll storytelling, parallax depth, text animations, and premium scroll effects — no WebGL required. Use this skill for any web design task: landing pages, product sites, hero sections, scroll animations, parallax, sticky sections, section overlaps, floating products between sections, clip-path reveals, text that flies in from sides, words that light up on scroll, curtain drops, iris opens, card stacks, bleed typography, and any site that should feel cinematic or premium. Trigger on phrases like "make it feel alive", "Apple-style animation", "sections that overlap", "product rises between sections", "immersive", "scrollytelling", or any scroll-driven visual effect. Covers 45+ techniques across 8 categories. Always inspects, judges, and plans assets before coding. Use aggressively for ANY web design task.
Use this skill whenever someone wants to consolidate, review, or rebalance a multi-member household investment portfolio. Triggers include: 'family portfolio', 'household net worth', 'consolidated investment view', 'portfolio rollup', 'asset allocation drift', 'rebalance my family', 'overall portfolio across family', 'father's + mother's + my investments together', 'spouse and I combined portfolio', 'review our investments', 'asset class breakdown', 'concentration risk', 'too much in one asset', 'how much equity vs debt'. ALSO trigger when the user describes holdings across multiple people in the same household and asks any 'should we' / 'how are we doing' question. Computes: per-member portfolio totals, asset allocation by class (Indian equity, foreign equity, debt, gold, real estate, REIT, cash), drift detection against age-appropriate target allocations, single-holding concentration warnings (any holding > 25% of family NW), and annual income projection per member. Designed for typical 2-3 member Indian families (parents + adult child), with target allocations that adjust by age.
Use when adding, retiring, or auditing feature flags. Triggers on "add a flag", "ship behind a flag", "rollout plan", "kill switch", "stale flags", "flag debt", "LaunchDarkly", "GrowthBook", "Statsig", "Unleash", "Flipt", or any progressive-delivery question. Ships flag debt scanner, rollout planner, and kill-switch auditor (all stdlib Python), 4 references on flag taxonomy + provider trade-offs + rollout strategies + lifecycle, plus a /flag-cleanup slash command.
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
Use when the user asks to fix, debug, or make a specific feature/module/area work end-to-end. Triggers: 'make X work', 'fix the Y feature', 'the Z module is broken', 'focus on [area]'. Not for quick single-bug fixes — this is for systematic deep-dive repair across all files and dependencies.
Use when the user asks to capture a full-page screenshot, long screenshot, or complete page capture of a web page. Handles SPA scroll containers, lazy-loaded images, and very tall pages via Chrome DevTools Protocol with zero external dependencies.
Design GCP architectures for startups and enterprises. Use when asked to design Google Cloud infrastructure, deploy to GKE or Cloud Run, configure BigQuery pipelines, optimize GCP costs, or migrate to GCP. Covers Cloud Run, GKE, Cloud Functions, Cloud SQL, BigQuery, and cost optimization.
Helm chart development agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw — chart scaffolding, values design, template patterns, dependency management, security hardening, and chart testing. Use when: user wants to create or improve Helm charts, design values.yaml files, implement template helpers, audit chart security (RBAC, network policies, pod security), manage subcharts, or run helm lint/test.
Use Hugging Face Hub via MCP server tools. Search models, datasets, Spaces, papers. Get repo details, fetch documentation, run compute jobs, and use Gradio Spaces as AI tools. Available when connected to the HF MCP server.
Use when a security incident has been detected or declared and needs classification, triage, escalation path determination, and forensic evidence collection. Covers SEV1-SEV4 classification, false positive filtering, incident taxonomy, and NIST SP 800-61 lifecycle.
Use this skill whenever an Indian investor asks about mutual fund taxation, capital gains on MFs, ELSS lock-in, or debt MF tax treatment. Triggers include: 'mutual fund tax', 'equity MF LTCG', 'debt fund tax', 'Section 50AA', 'ELSS lock-in', 'SIP lock-in', 'when can I redeem ELSS', 'hybrid fund taxation', '65% equity threshold', 'arbitrage fund tax', 'gold MF vs gold ETF', 'international FoF tax', 'liquid fund tax', 'short-term capital gains MF', 'long-term capital gains MF', '₹1.25 lakh exemption', 'grandfathered debt MF', 'MF FoF taxation'. CRITICAL: ALSO trigger PROACTIVELY whenever a user mentions buying or holding a debt MF, gold MF, international FoF, or conservative hybrid purchased AFTER 1 April 2023 — these fall into the Section 50AA trap (slab-rate taxation on ALL gains, no LTCG benefit, no indexation). The user usually doesn't know about this and the skill must surface it. Computes: equity LTCG (12.5% above ₹1.25L/year), Section 50AA debt trap detection, ELSS per-SIP lock-in tracking (36 months per installment), hybrid fund classification using 65% equity threshold, grandfathering for pre-April-2023 debt MF units.
Use this skill whenever the user discusses Indian real estate transactions — buying, selling, renting, or analyzing residential, commercial, or agricultural property in India, especially Madhya Pradesh / Bhopal. Triggers include: 'stamp duty', 'property registration', 'capital gains on property', 'indexation', 'grandfathering 23 July 2024', 'Section 50C', 'Section 54 / 54EC / 54F / 54B exemption', 'CII cost inflation index', 'REIT tax', 'agricultural land', 'urban vs rural land', 'Section 2(14)(iii)', 'TDS on property purchase', '194-IA', '194-IB rent TDS', 'rental income tax Section 24', 'SAMPADA portal', 'MP-RERA', 'Bhopal property prices'. ALSO trigger when the user mentions a city in MP (Bhopal, Indore, Jabalpur, Sehore, Vidisha), or when a property transaction value is mentioned alongside any of: 'should I buy', 'should I sell', 'tax planning', 'invest in real estate'. Computes: MP stamp duty (10.5% total), capital gains with grandfathering decision (Path A 12.5% no-index vs Path B 20%+indexation, lower wins for Resident Ind/HUF on pre-23-Jul-2024 acquisitions), Section 50C deemed value check (10% tolerance), exemption recommender (54/54EC/54F/54B), REIT distribution classifier (interest slab, dividend exempt, rental slab, capital repayment untaxed), rental income under Section 24, TDS on purchase (1%) and rent (2% from Oct 2024), Bhopal agricultural land classification (urban if ≤8 km from BMC aerial).
Use this skill whenever an Indian taxpayer asks about old vs new tax regime, which regime saves more money, deduction caps, or tax computation for FY 2025-26 / AY 2026-27. Triggers include: 'old vs new regime', 'which tax regime', 'should I switch regime', 'how much tax do I save', '80C', '80CCD', '80D', '80TTB', '87A rebate', 'senior citizen tax', 'super senior tax', 'standard deduction', 'tax slabs India', 'Form 10-IEA', 'compute Indian income tax'. ALSO trigger proactively when an Indian salary or income figure appears in conversation and the user is making any financial decision — regime choice is upstream of almost every tax planning question in India. Computes both regimes side-by-side, enforces statutory caps (80C ₹1.5L, 80CCD(1B) ₹50K, 80D age-based, 80TTB ₹50K senior-only), handles general/senior 60-79/super-senior 80+ slabs separately, applies Section 87A rebates (₹60K new regime up to ₹12L, ₹12,500 old regime up to ₹5L), and adds 4% cess. NOT for foreign-source income tax (use lrs-foreign-investment-tax). NOT for capital gains on property or MF (use indian-real-estate-bhopal or indian-mutual-fund-tax).
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
This skill should be used when the user asks to "design interview processes", "create hiring pipelines", "calibrate interview loops", "generate interview questions", "design competency matrices", "analyze interviewer bias", "create scoring rubrics", "build question banks", or "optimize hiring systems". Use for designing role-specific interview loops, competency assessments, and hiring calibration systems.
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
csiddhant796-blipSkill