alivirgo
- 434 skills
- 0 followers
- last month last updated
- ▌ Token Efficient Markdown · alivirgoHow to format markdown documentation, tables, and artifacts with high structural density, eliminating decorative ASCII dividers, padded table spaces, and multi-newline whitespace bloat.
- ▌ Use Plain Text Over Pdfs · alivirgoWhy extracting and pasting clean plain text or Markdown beats raw PDF uploads by eliminating OCR latency, visual token bloat (up to 80% savings), and table scrambling.
- ▌ Zero Boilerplate Imports · alivirgoHow to eliminate redundant import blocks when displaying localized code patches and diffs, relying on existing file imports and automated CLI import sorters.
- ▌ Zero Cat Bash Prevention · alivirgoWhy autonomous agents must use structured native file viewing tools (view_file) rather than terminal shell commands (cat, type, Get-Content), enabling 1-indexed line numbering and slice bounding.
- ▌ Ask How To Improve Prompt · alivirgoTurn the AI into an expert Prompt Engineer to critique your instructions, fill missing context gaps, and generate reusable high-performance prompt templates.
- ▌ Compressed System Prompts · alivirgoHow to refactor wordy, repetitive system prompts into high-density imperative token structures, cutting baseline system prompt costs by 70% while improving instruction adherence.
- ▌ Context Pruning Directive · alivirgoHow agent runtimes dynamically prune stale tool outputs, dead build logs, and historical turns to eliminate quadratic token growth ($O(N^2)$) and prevent attention degradation.
- ▌ Deduplicated File Caching · alivirgoHow agent runtimes intercept redundant file reads within the same conversation trajectory using mtime and SHA-256 hash checks, eliminating 40% of duplicate context ingestion tokens.
- ▌ Draft Multiple Variations · alivirgoHow to prompt for high-contrast variations using psychological angles (Curiosity, Direct Benefit, Urgency, Counter-Intuitive) rather than synonym swaps.
- ▌ Give AI Situation Context · alivirgoHow to anchor prompts with the 4-Pillar Situation Framework (Role, Scale, Budget, Constraints) to stop AI from over-engineering or giving irrelevant advice.
- ▌ Line Bounded File Reading · alivirgoHow autonomous coding agents use StartLine and EndLine parameters to read targeted 30-to-50 line slices rather than unbounded 2,000-line files, eliminating 90% of file ingestion tokens.
- ▌ Logit Bias Token Steering · alivirgoHow to apply logit_bias parameters at the transformer sampling layer to mathematically force 1-token boolean/enum decisions and ban conversational filler words, cutting output tokens by 99%.
- ▌ Minimal Artifact Metadata · alivirgoHow to structure high-density ArtifactMetadata fields (Summary, UserFacing, RequestFeedback) during artifact creation and editing, cutting metadata overhead by 80%.
- ▌ No Redundant Type Casting · alivirgoHow to eliminate redundant type assertions (as unknown as T) and defensive coercion wrapping (str(str(x)), Boolean(y === true)), cutting code generation token bloat by 30%.
- ▌ No Vendor Directory Scans · alivirgoHow agent tools and recursive search crawlers enforce strict glob exclusion on vendor directories (node_modules, venv, target, dist, .git), preventing catastrophic 80,000-token context floods.
- ▌ One Shot Subagent Prompts · alivirgoHow orchestrator agents formulate comprehensive, self-contained task prompts for child subagents (Task, Boundaries, Stop Conditions, Return Schema), eliminating 75% of multi-turn clarification ping-pongs.
- ▌ Reactive Wakeup Signaling · alivirgoWhy autonomous agents must rely on event-driven runtime wakeups instead of polling status loops (manage_task status) while waiting for background jobs, eliminating 95% of waiting token waste.
- ▌ Ripgrep Over Grep Command · alivirgoWhy autonomous agents must use structured native code search tools (grep_search) rather than terminal shell commands (grep -rn), eliminating ANSI formatting noise and capping match overflows.
- ▌ Simple Understanding Quiz · alivirgoHow to use the Testing Effect and Active Retrieval practice to diagnose knowledge gaps, eliminate illusions of competence, and lock in concepts.
- ▌ Single Pass Multi Replace · alivirgoHow to edit multiple separated blocks across a single file in one atomic turn using multi_replace_file_content, eliminating line-drift offset errors and cutting edit roundtrips by 70%.
- ▌ Targeted Line Range Edits · alivirgoHow to apply precise line-bounded code edits using replace_file_content ([StartLine, EndLine] windowing) rather than rewriting complete 500-line files, cutting edit output tokens by 95%.
- ▌ Write Step By Step How To · alivirgoHow to generate bulletproof Standard Operating Procedures (SOPs) and technical tutorials with exact click paths, expected visual results, and failure troubleshooting.
- ▌ Avoid Rephrasing Good Text · alivirgoHow to perform surgical edits on awkward sentences without destroying your authentic voice, personal humor, or working copy.
- ▌ Bullet Point Summary First · alivirgoHow to extract high-yield, action-oriented bullet summaries from long documents, meetings, and articles using the 3-Bullet Digest framework.
- ▌ Cached System Instructions · alivirgoHow to structure hierarchical, immutable system instructions to maximize KV-cache hits on Anthropic and OpenAI, slashing Time-to-First-Token (TTFT) by 80% and input costs by 90%.
- ▌ Incremental Diff Ingestion · alivirgoHow autonomous agents use compact unified git diffs (git diff -U3, git diff @{u}..HEAD) instead of full-file ingestion for PR reviews and commit audits, reducing review tokens by 90%.
- ▌ Lm Studio Local Offloading · alivirgoHow autonomous engineering systems route mechanical sub-tasks (git commits, log triage, unit test boilerplate) to local GGUF models via LM Studio/Ollama, cutting cloud API spend by 60%.
- ▌ No Polite Chitchat Closing · alivirgoHow to eliminate conversational closing signatures ('Hope this helps!', 'Let me know if you have questions!') to save output tokens and terminate turns immediately upon deliverable completion.
- ▌ Openapi Endpoint Filtering · alivirgoHow autonomous agents slice monolithic 10,000-line OpenAPI/Swagger specifications down to operation-targeted sub-schemas, eliminating 99% of API specification token bloat.
- ▌ Verify Names And Locations · alivirgoWhy proper nouns, addresses, and job titles are the #1 source of AI hallucinations, and how to use the 4-Point Entity Verification Ladder to prevent embarrassing mistakes.
- ▌ Compare Two Products Fairly · alivirgoHow to use Symmetrical Head-to-Head prompting to compare software, hardware, or tools objectively with transparent pricing and fatal flaw analysis.
- ▌ Fill In Missing Assumptions · alivirgoHow to use Assumption Surfacing and Sensitivity Analysis to uncover silent presuppositions, prevent architectural failure, and stress-test recommendations.
- ▌ Flag Speculative Statements · alivirgoHow to use Epistemic Tagging ([FACT], [HEURISTIC], [SPECULATION]) to force AI to visibly separate verified truths from estimates and predictions.
- ▌ Gitignore Respecting Search · alivirgoHow autonomous agents use gitignore-aware search engines (ripgrep) to automatically exclude node_modules, build artifacts, and vendor directories, eliminating 95% of search noise.
- ▌ Header Only C Cpp Ingestion · alivirgoHow autonomous agents inspect .h/.hpp header files first to understand class contracts and struct layouts before reading heavy .cpp implementation files, slashing C++ context token spend by 85%.
- ▌ Multi Tool Batch Invocation · alivirgoHow autonomous agents emit multiple independent tool calls in a single turn (tool_calls array), enabling parallel execution via Promise.all and slashing turn roundtrips by 70%.
- ▌ One Sentence Elevator Pitch · alivirgoHow to force AI to condense complex apps, startups, and initiatives into a crystal-clear, 1-sentence elevator pitch using the XY Positioning Formula.
- ▌ Regex One Liner Refactoring · alivirgoHow to replace 20-line procedural character-by-character parsing loops with concise, compiled Regular Expressions, reducing string manipulation code size by 75%.
- ▌ Single Line Error Summaries · alivirgoHow to condense 100-line stack traces into structured single-line root cause statements (🚨 [FAIL: file:line] ErrorType: Message), slashing error reporting tokens by 95%.
- ▌ Skip Explaining The Obvious · alivirgoHow to suppress introductory 101 definitions and force AI to assume senior domain competence, saving tokens and reading time.
- ▌ Standard Library Preference · alivirgoHow to leverage modern built-in standard library utilities (functools, structuredClone, crypto.randomUUID, itertools) instead of writing custom helper boilerplate or pulling in heavy third-party dependencies.
- ▌ Start Fresh Chat New Topics · alivirgoWhy long-running mega-threads cause context pollution, latency spikes, and hallucinations, and how to use the State Handoff Pattern to reset cleanly.
- ▌ Structure Weekly To Do List · alivirgoHow to parse a chaotic brain dump into a sustainable 5-day Thematic Sprint with morning deep-work blocks and energy-calibrated task distribution.
- ▌ Token Usage Monitoring Hook · alivirgoHow to implement client-side middleware hooks to meter per-turn input/output tokens in real-time, alerting on consumption spikes and enforcing session budget caps.
- ▌ Tree Sitter Scope Extractor · alivirgoHow to use Tree-sitter concrete syntax trees to extract strictly the enclosing function or class scope (+ imports) for a target line, cutting file inspection tokens by 90%.
- ▌ Write Polite Tough Feedback · alivirgoHow to deliver tough, critical performance feedback without triggering defensiveness or resorting to confusing 'feedback sandwiches', using the Situation-Behavior-Impact (SBI) model.
- ▌ Ask AI To Show Its Reasoning · alivirgoPrompt patterns to extract transparent, first-principles logic, trade-off comparisons, and elimination criteria behind any AI recommendation.
- ▌ Be Specific Instead Of Vague · alivirgoHow to replace vague prompts with the 5-Variable Precision Formula to eliminate generic fluff, hit exact requirements, and get one-shot perfection.
- ▌ Check Code For Obvious Flaws · alivirgoHow to run the 5-point Zero-Trust code audit to catch hallucinated package APIs, security leaks, unhandled exceptions, and edge-case crashes before running in production.
- ▌ Copy Relevant Paragraph Only · alivirgoHow to use Context Sniping to prevent 'Lost-in-the-Middle' attention degradation, save input tokens, and get laser-accurate answers from long documents.
- ▌ Dont Repaste Entire Document · alivirgoHow to maintain clean conversation context, leverage conversational memory, and avoid re-uploading large documents for micro-edits.
- ▌ Reuse Saved Prompt Templates · alivirgoHow to build and maintain a parameterized Personal Prompt Library in Raycast, Obsidian, or TextExpander to save 30 minutes of typing every day.
- ▌ Specify High Precision Needs · alivirgoHow to trigger maximum model rigor, deterministic reasoning, and zero-extrapolation constraints for audits, compliance, and safety-critical tasks.
- ▌ Subagent Transcript Indexing · alivirgoHow orchestrator agents query historical child subagent transcripts locally using ripgrep on structured JSONL logs, eliminating 98% of multi-agent context replay tokens.
- ▌ Temperature Zero Determinism · alivirgoWhy code generation, tool calling, and structured JSON extractions must always execute at temperature: 0.0 (greedy decoding), eliminating stochastic hallucinations and compiler retry loops.
- ▌ Ternary Operator Utilization · alivirgoHow to condense 6-line mutable if/else blocks into single-line ternary expressions and nullish coalescing operators (condition ? a : b, a ?? b), cutting conditional statement tokens by 55%.
- ▌ Zero Explanation Refactoring · alivirgoHow to deliver pure executable code blocks and unified diffs with zero conversational commentary during automated refactoring tasks, enabling direct IDE parsing and cutting output tokens by 65%.
- ▌ Beware Of Hallucinated Quotes · alivirgoHow to prevent and detect apocryphal AI quotations, fabricated book titles, and hallucinated academic citations before publishing.
- ▌ Cached Tool Permission Grants · alivirgoHow to configure session-scoped tool permission caching and auto-approval policies to eliminate human-in-the-loop modal stalls and permission error loops.
- ▌ Cite Specific Section Numbers · alivirgoHow to enforce Section-Anchored Citations when analyzing manuals, legal contracts, and compliance policies to make every AI claim instantly verifiable.
- ▌ Dont Summarize Without A Goal · alivirgoWhy generic 'summarize this' prompts produce low-signal fluff, and how to use Goal-Directed Extraction to pull exact decision criteria.
- ▌ Double Check AI Math Manually · alivirgoHow to use the 3-Tier Math Verification Ladder to protect invoices, cap tables, tax calculations, and loan estimates from silent AI arithmetic errors.
- ▌ GRAPHQL Introspection Trimmer · alivirgoHow autonomous agents prune full GraphQL Introspection schemas and SDL dumps down to operation-targeted subgraphs, eliminating 90% of API context token bloat.
- ▌ Gzip Compressed HTTP Payloads · alivirgoHow agent client SDKs and MCP runtime bridges compress large conversation JSON payloads using gzip and zstd, slashing network transfer latency and socket timeouts by 80%.
- ▌ Never Paste Private Passwords · alivirgoThe essential security protocol for protecting API keys, passwords, credit card numbers, and PII from leaking into AI logs, training queues, and shared chats.
- ▌ Simplify Legal Contract Terms · alivirgoHow to extract and translate the 5 most dangerous commercial contract clauses (Auto-Renewal, Liability Caps, IP Assignment, Price Increases, Termination Fees) into plain English.
- ▌ Suppress Verbose Build Output · alivirgoHow to use native quiet flags (--silent, -q) and stream redirection (> /dev/null, | Out-Null) on package installations and builds, eliminating 99% of stdout progress bar token pollution.
- ▌ Use Good Answers As Templates · alivirgoHow to use previous high-performing AI responses as 1-shot structural templates to enforce 100% formatting, tone, and depth consistency across new topics.
- ▌ Ask AI To Repeat Understanding · alivirgoHow to use the Intent Echo & Alignment pattern to prevent wasted tokens, hallucinated scopes, and misaligned deliverables on complex tasks.
- ▌ Ask For Alternative Viewpoints · alivirgoTechniques to eliminate echo-chamber bias and user sycophancy by forcing AI to steel-man opposing viewpoints, stress-test premises, and simulate adversarial stakeholders.
- ▌ Ask For Tables Over Paragraphs · alivirgoHow to enforce structured Markdown tables to cut token consumption by 50%, eliminate narrative fluff, and produce instantly scannable, copy-pasteable data.
- ▌ Batch Small Questions Together · alivirgoHow grouping related micro-queries into a single prompt eliminates quadratic context buildup, reduces API costs by up to 75%, and cuts round-trip wait times.
- ▌ Brainstorm Presentation Angles · alivirgoHow to use AI to generate 4 distinct narrative hooks and opening angles for keynotes, executive pitches, and all-hands presentations.
- ▌ Break Big Questions Into Steps · alivirgoHow to apply Task Decomposition to eliminate context saturation, prevent hallucination cascades, and build complex projects incrementally.
- ▌ Browser Subagent Task Bounding · alivirgoHow to constrain browser subagents with deterministic stop conditions, step ceilings (max 5-8 steps), and selector-targeted DOM extraction to prevent runaway token costs and infinite navigation loops.
- ▌ Comment Stripping Preprocessor · alivirgoHow to strip redundant license headers, dead commented-out code, and verbose docstrings from source files before LLM ingestion, reducing input tokens by 40%.
- ▌ Convert Voice Memos To Bullets · alivirgoHow to process spoken dictation and audio transcripts, eliminate disfluencies and rambling, and extract structured executive notes.
- ▌ Draft Emails With Placeholders · alivirgoHow to use the Modular Bracketed Placeholder Pattern to create reusable, mistake-proof email templates for sales, client follow-ups, and executive updates.
- ▌ Generate Social Media Captions · alivirgoHow to prompt for high-engagement, platform-native social media copy across LinkedIn, X/Twitter, and Instagram without robotic AI clichés or emoji spam.
- ▌ List Comprehension Compression · alivirgoHow to replace verbose multi-line procedural accumulator loops with high-density Python list/dict comprehensions and functional pipelines, cutting loop token overhead by 60%.
- ▌ Prioritize Urgent Vs Important · alivirgoHow to use AI to triage chaotic daily to-do lists into the 4 Eisenhower Quadrants (Do First, Schedule, Delegate, Eliminate) for maximum daily leverage.
- ▌ Schema Pruned Function Calling · alivirgoHow to strip redundant descriptions, uncalled optional parameters, and unused tool definitions from agent JSON schemas, cutting baseline tool-calling token overhead by 65%.
- ▌ Scripted Formatting Delegation · alivirgoHow autonomous coding agents delegate codebase-wide indentation, line-wrapping, and styling to local deterministic formatters (prettier, ruff, gofmt) rather than burning LLM tokens on reformatting.
- ▌ Single Command Script Chaining · alivirgoHow to chain setup, build, and verification commands into atomic single-turn compound executions (&&, ;, |), slashing API roundtrips and conversation context accumulation by 80%.
- ▌ Sliding Window Chat Truncation · alivirgoHow agent runtimes enforce a 3-zone sliding window (Immutable Anchor, Compressed Milestone Summary, Active Sliding Buffer) to keep conversation context bounded under 12,000 tokens across 100+ turns.
- ▌ Speculative Decoding Prompting · alivirgoHow to structure prompts and utilize Predicted Outputs (OpenAI/vLLM) to maximize speculative draft token acceptance rates, speeding up code generation by 3x at zero cost.
- ▌ Structured Outputs Strict Mode · alivirgoHow to use OpenAI and Gemini Strict Mode (strict: true) and CFG-guided decoding (Pydantic/Zod) to guarantee 100% schema adherence, eliminating markdown wrapping and JSON parse retries.
- ▌ Always Verify Numbers And Links · alivirgoWhy LLMs hallucinate statistics, phone numbers, and URLs, and how to enforce grounding, external verification, and tool-assisted calculations.
- ▌ Avoid Duplicate System Messages · alivirgoHow to consolidate fragmented system instructions into a single static cacheable header, maximizing Anthropic and OpenAI prompt cache hit rates and cutting input token costs by 90%.
- ▌ Dont Trust AI Medical Diagnoses · alivirgoHow to safely use AI for medical literacy, lab test vocabulary translation, and doctor appointment preparation while strictly avoiding self-diagnosis traps.
- ▌ Specify Preferred Writing Style · alivirgoHow to move beyond vague style adjectives by defining Tone, Information Density, and Sentence Cadence across 5 standard professional style presets.
- ▌ Beware Of AI Recommendation Bias · alivirgoHow to neutralize pre-training data bias, SEO affiliate spam influence, and brand popularity bias when evaluating software, hardware, and vendors.
- ▌ Build Your AI Common Sense Habit · alivirgoThe foundational 5-pillar operating system for using generative AI with maximum efficiency, zero hallucination risk, and 10x leverage.
- ▌ Format Data To Copy Paste Tables · alivirgoHow to use AI as an instant ETL engine to parse messy raw text, emails, and receipts into clean, spreadsheet-ready TSV/CSV tables.
- ▌ Silent Background Task Execution · alivirgoHow autonomous agents launch long-running compilation, server, and test processes asynchronously (WaitMsBeforeAsync, IsDaemon) without blocking chat turns or polling.
- ▌ State Your Goal Not Just Command · alivirgoHow to avoid the classic XY Problem by explaining the ultimate business or technical outcome you want, unlocking simpler and higher-leverage solutions.
- ▌ Treat AI Answers As First Drafts · alivirgoHow to use AI to conquer the blank page (0 to 80% in 30 seconds) while applying the 4-step Human Finishing Pass to reach 100% polish and authenticity.
- ▌ Use Fast Models For Quick Checks · alivirgoHow to route tasks between Fast/Small models (Haiku, Flash, GPT-4o-mini) and Heavy/Frontier models (Sonnet, GPT-4o, o1) to cut costs 90% and slash latency.
- ▌ Clean Messy Notes To Action Items · alivirgoHow to parse chaotic brain dumps and meeting notes into structured [WHO] - [WHAT] - [BY WHEN] action items, decisions, and follow-ups.
- ▌ Combine Human Speed With AI Scale · alivirgoHow to operate as an elite Centaur/Cyborg operator by delegating heavy synthesis and drafting to AI while retaining human taste, strategy, and judgment.