xniperbuilds
UserA research skill for coding agents that refuses to cite what it did not open. Sources every load-bearing claim, quote-checks it against the page it came from, and ends in a verdict with confidence and named gaps.
Categories
Indexed Skills (5)
research-pro-max
Universal research engine for any question that needs real evidence — technical, library/API, codebase, security, product, market, competitor, pricing, academic, legal-adjacent, company due diligence, social/trend, or content research. Use whenever the user says research, investigate, find out, dig into, compare options, evaluate, "is X worth it", "what's the best X", "how does X actually work", "who is X", "should we use X", "should I build this", "research kro", "pata karo", "check kro sahi hai ya nahi" — before any build/buy/adopt/migrate/publish decision that is expensive to reverse, and whenever an answer must be sourced rather than recalled from memory. It names the venues that can actually settle the question before searching, opens primary sources, verifies each claim against the line that supports it, triangulates, and delivers an answer-first brief with per-claim citations, confidence, and named gaps. Prefer this over ad-hoc web searching any time the answer will be acted on.
rework
Find and avoid work that has to be done twice — deep stacks of unverified edits, retry loops on a failing command, and tools that keep erroring. Use whenever a coding agent is going in circles, re-editing the same file over and over, retrying a command that keeps failing, or the user says it's stuck, looping, going back and forth, "you already tried that", "same error again", "phir wahi ghalti", "ye to pehle bhi kiya tha", or asks why a task is taking so many attempts. Also use before stacking another edit onto a file you already changed without running anything, and after a session to see where the loops were.
rule-audit
Find out which of your agent rules are actually enforced and which are only hope — then convert the ones that matter into deterministic enforcement. Use whenever the user says Claude ignored my rules, it pushed to main again, it keeps forgetting my instructions, my CLAUDE.md isn't working, "same mistake again", "I told it not to", "rule follow nahi karta", "phir wahi ghalti" — or asks to add a hook, block a command, enforce a convention, run something automatically after edits, review their CLAUDE.md, or make an instruction actually stick. Also use before writing a new rule, to decide whether it belongs in prose or in the harness, and when a CLAUDE.md has grown long enough that compliance is degrading. It inventories every rule you have, classifies each as enforceable or advisory, generates the hook or permission config for the enforceable ones, tells you plainly which rules can never be enforced, and prunes the rest so the remaining instructions actually get followed.
receipts
Check whether work an agent said it finished actually happened, and stop reporting done without evidence. Use whenever a coding agent claims something is fixed, tests pass, the build succeeded, or it deployed — and whenever the user says it didn't actually work, "you said it was done", "did you actually run it", "prove it", "are you sure", "it's still broken", "kaam hua bhi hai ya nahi", "chala ke dekha?", or asks to verify, double-check, or audit a completed task. Also use before reporting completion on any task, to decide whether the claim is backed by something that was actually run, and after a session to audit which past claims had no evidence behind them.
burnrate
Find out what is actually burning your coding-agent tokens, then cut it — measured from your own session transcripts, never a claimed percentage. Use whenever the user says they are hitting usage limits, burning tokens too fast, "limit khatam ho gaya", "why is this so expensive", "reduce token usage", "my context fills up too fast", "session limit", "running out of quota", asks to make an agent cheaper or more efficient, wants to know where their tokens went, or is evaluating a token-saving tool or skill. Also use before adopting any "saves X% tokens" claim — this skill measures the real split first.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.