all publishers

alivirgo

@alivirgo source repo

434 published skills · page 4 of 5

  1. ▌
    Token Efficient Markdown · alivirgo
    How to format markdown documentation, tables, and artifacts with high structural density, eliminating decorative ASCII dividers, padded table spaces, and multi-newline whitespace bloat.
    5 installs
  2. ▌
    Use Plain Text Over Pdfs · alivirgo
    Why 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.
    5 installs
  3. ▌
    Zero Boilerplate Imports · alivirgo
    How to eliminate redundant import blocks when displaying localized code patches and diffs, relying on existing file imports and automated CLI import sorters.
    8 installs
  4. ▌
    Zero Cat Bash Prevention · alivirgo
    Why 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.
    5 installs
  5. ▌
    Ask How To Improve Prompt · alivirgo
    Turn the AI into an expert Prompt Engineer to critique your instructions, fill missing context gaps, and generate reusable high-performance prompt templates.
    11 installs
  6. ▌
    Compressed System Prompts · alivirgo
    How to refactor wordy, repetitive system prompts into high-density imperative token structures, cutting baseline system prompt costs by 70% while improving instruction adherence.
    8 installs
  7. ▌
    Context Pruning Directive · alivirgo
    How 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.
    5 installs
  8. ▌
    Deduplicated File Caching · alivirgo
    How 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.
    7 installs
  9. ▌
    Draft Multiple Variations · alivirgo
    How to prompt for high-contrast variations using psychological angles (Curiosity, Direct Benefit, Urgency, Counter-Intuitive) rather than synonym swaps.
    4 installs
  10. ▌
    Give AI Situation Context · alivirgo
    How to anchor prompts with the 4-Pillar Situation Framework (Role, Scale, Budget, Constraints) to stop AI from over-engineering or giving irrelevant advice.
    6 installs
  11. ▌
    Line Bounded File Reading · alivirgo
    How 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.
    11 installs
  12. ▌
    Logit Bias Token Steering · alivirgo
    How 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%.
    9 installs
  13. ▌
    Minimal Artifact Metadata · alivirgo
    How to structure high-density ArtifactMetadata fields (Summary, UserFacing, RequestFeedback) during artifact creation and editing, cutting metadata overhead by 80%.
    11 installs
  14. ▌
    No Redundant Type Casting · alivirgo
    How 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%.
    5 installs
  15. ▌
    No Vendor Directory Scans · alivirgo
    How 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.
    7 installs
  16. ▌
    One Shot Subagent Prompts · alivirgo
    How 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.
    3 installs
  17. ▌
    Reactive Wakeup Signaling · alivirgo
    Why 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.
    5 installs
  18. ▌
    Ripgrep Over Grep Command · alivirgo
    Why 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.
    5 installs
  19. ▌
    Simple Understanding Quiz · alivirgo
    How to use the Testing Effect and Active Retrieval practice to diagnose knowledge gaps, eliminate illusions of competence, and lock in concepts.
    6 installs
  20. ▌
    Single Pass Multi Replace · alivirgo
    How 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%.
    5 installs
  21. ▌
    Targeted Line Range Edits · alivirgo
    How 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%.
    8 installs
  22. ▌
    Write Step By Step How To · alivirgo
    How to generate bulletproof Standard Operating Procedures (SOPs) and technical tutorials with exact click paths, expected visual results, and failure troubleshooting.
    6 installs
  23. ▌
    Avoid Rephrasing Good Text · alivirgo
    How to perform surgical edits on awkward sentences without destroying your authentic voice, personal humor, or working copy.
    5 installs
  24. ▌
    Bullet Point Summary First · alivirgo
    How to extract high-yield, action-oriented bullet summaries from long documents, meetings, and articles using the 3-Bullet Digest framework.
    4 installs
  25. ▌
    Cached System Instructions · alivirgo
    How 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%.
    9 installs
  26. ▌
    Incremental Diff Ingestion · alivirgo
    How 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%.
    8 installs
  27. ▌
    Lm Studio Local Offloading · alivirgo
    How 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%.
    6 installs
  28. ▌
    No Polite Chitchat Closing · alivirgo
    How 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.
    6 installs
  29. ▌
    Openapi Endpoint Filtering · alivirgo
    How autonomous agents slice monolithic 10,000-line OpenAPI/Swagger specifications down to operation-targeted sub-schemas, eliminating 99% of API specification token bloat.
    10 installs
  30. ▌
    Verify Names And Locations · alivirgo
    Why 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.
    8 installs
  31. ▌
    Compare Two Products Fairly · alivirgo
    How to use Symmetrical Head-to-Head prompting to compare software, hardware, or tools objectively with transparent pricing and fatal flaw analysis.
    5 installs
  32. ▌
    Fill In Missing Assumptions · alivirgo
    How to use Assumption Surfacing and Sensitivity Analysis to uncover silent presuppositions, prevent architectural failure, and stress-test recommendations.
    5 installs
  33. ▌
    Flag Speculative Statements · alivirgo
    How to use Epistemic Tagging ([FACT], [HEURISTIC], [SPECULATION]) to force AI to visibly separate verified truths from estimates and predictions.
    8 installs
  34. ▌
    Gitignore Respecting Search · alivirgo
    How autonomous agents use gitignore-aware search engines (ripgrep) to automatically exclude node_modules, build artifacts, and vendor directories, eliminating 95% of search noise.
    5 installs
  35. ▌
    Header Only C Cpp Ingestion · alivirgo
    How 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%.
    7 installs
  36. ▌
    Multi Tool Batch Invocation · alivirgo
    How 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%.
    9 installs
  37. ▌
    One Sentence Elevator Pitch · alivirgo
    How to force AI to condense complex apps, startups, and initiatives into a crystal-clear, 1-sentence elevator pitch using the XY Positioning Formula.
    5 installs
  38. ▌
    Regex One Liner Refactoring · alivirgo
    How to replace 20-line procedural character-by-character parsing loops with concise, compiled Regular Expressions, reducing string manipulation code size by 75%.
    8 installs
  39. ▌
    Single Line Error Summaries · alivirgo
    How to condense 100-line stack traces into structured single-line root cause statements (🚨 [FAIL: file:line] ErrorType: Message), slashing error reporting tokens by 95%.
    7 installs
  40. ▌
    Skip Explaining The Obvious · alivirgo
    How to suppress introductory 101 definitions and force AI to assume senior domain competence, saving tokens and reading time.
    8 installs
  41. ▌
    Standard Library Preference · alivirgo
    How 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.
    4 installs
  42. ▌
    Start Fresh Chat New Topics · alivirgo
    Why long-running mega-threads cause context pollution, latency spikes, and hallucinations, and how to use the State Handoff Pattern to reset cleanly.
    10 installs
  43. ▌
    Structure Weekly To Do List · alivirgo
    How to parse a chaotic brain dump into a sustainable 5-day Thematic Sprint with morning deep-work blocks and energy-calibrated task distribution.
    4 installs
  44. ▌
    Token Usage Monitoring Hook · alivirgo
    How 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.
    9 installs
  45. ▌
    Tree Sitter Scope Extractor · alivirgo
    How 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%.
    9 installs
  46. ▌
    Write Polite Tough Feedback · alivirgo
    How to deliver tough, critical performance feedback without triggering defensiveness or resorting to confusing 'feedback sandwiches', using the Situation-Behavior-Impact (SBI) model.
    10 installs
  47. ▌
    Ask AI To Show Its Reasoning · alivirgo
    Prompt patterns to extract transparent, first-principles logic, trade-off comparisons, and elimination criteria behind any AI recommendation.
    6 installs
  48. ▌
    Be Specific Instead Of Vague · alivirgo
    How to replace vague prompts with the 5-Variable Precision Formula to eliminate generic fluff, hit exact requirements, and get one-shot perfection.
    7 installs
  49. ▌
    Check Code For Obvious Flaws · alivirgo
    How 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.
    6 installs
  50. ▌
    Copy Relevant Paragraph Only · alivirgo
    How to use Context Sniping to prevent 'Lost-in-the-Middle' attention degradation, save input tokens, and get laser-accurate answers from long documents.
    6 installs
  51. ▌
    Dont Repaste Entire Document · alivirgo
    How to maintain clean conversation context, leverage conversational memory, and avoid re-uploading large documents for micro-edits.
    5 installs
  52. ▌
    Reuse Saved Prompt Templates · alivirgo
    How to build and maintain a parameterized Personal Prompt Library in Raycast, Obsidian, or TextExpander to save 30 minutes of typing every day.
    5 installs
  53. ▌
    Specify High Precision Needs · alivirgo
    How to trigger maximum model rigor, deterministic reasoning, and zero-extrapolation constraints for audits, compliance, and safety-critical tasks.
    5 installs
  54. ▌
    Subagent Transcript Indexing · alivirgo
    How orchestrator agents query historical child subagent transcripts locally using ripgrep on structured JSONL logs, eliminating 98% of multi-agent context replay tokens.
    3 installs
  55. ▌
    Temperature Zero Determinism · alivirgo
    Why code generation, tool calling, and structured JSON extractions must always execute at temperature: 0.0 (greedy decoding), eliminating stochastic hallucinations and compiler retry loops.
    10 installs
  56. ▌
    Ternary Operator Utilization · alivirgo
    How 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%.
    7 installs
  57. ▌
    Zero Explanation Refactoring · alivirgo
    How 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%.
    6 installs
  58. ▌
    Beware Of Hallucinated Quotes · alivirgo
    How to prevent and detect apocryphal AI quotations, fabricated book titles, and hallucinated academic citations before publishing.
    5 installs
  59. ▌
    Cached Tool Permission Grants · alivirgo
    How to configure session-scoped tool permission caching and auto-approval policies to eliminate human-in-the-loop modal stalls and permission error loops.
    9 installs
  60. ▌
    Cite Specific Section Numbers · alivirgo
    How to enforce Section-Anchored Citations when analyzing manuals, legal contracts, and compliance policies to make every AI claim instantly verifiable.
    8 installs
  61. ▌
    Dont Summarize Without A Goal · alivirgo
    Why generic 'summarize this' prompts produce low-signal fluff, and how to use Goal-Directed Extraction to pull exact decision criteria.
    4 installs
  62. ▌
    Double Check AI Math Manually · alivirgo
    How to use the 3-Tier Math Verification Ladder to protect invoices, cap tables, tax calculations, and loan estimates from silent AI arithmetic errors.
    3 installs
  63. ▌
    GRAPHQL Introspection Trimmer · alivirgo
    How autonomous agents prune full GraphQL Introspection schemas and SDL dumps down to operation-targeted subgraphs, eliminating 90% of API context token bloat.
    7 installs
  64. ▌
    Gzip Compressed HTTP Payloads · alivirgo
    How 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%.
    3 installs
  65. ▌
    Never Paste Private Passwords · alivirgo
    The essential security protocol for protecting API keys, passwords, credit card numbers, and PII from leaking into AI logs, training queues, and shared chats.
    4 installs
  66. ▌
    Simplify Legal Contract Terms · alivirgo
    How to extract and translate the 5 most dangerous commercial contract clauses (Auto-Renewal, Liability Caps, IP Assignment, Price Increases, Termination Fees) into plain English.
    5 installs
  67. ▌
    Suppress Verbose Build Output · alivirgo
    How 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.
    7 installs
  68. ▌
    Use Good Answers As Templates · alivirgo
    How to use previous high-performing AI responses as 1-shot structural templates to enforce 100% formatting, tone, and depth consistency across new topics.
    12 installs
  69. ▌
    Ask AI To Repeat Understanding · alivirgo
    How to use the Intent Echo & Alignment pattern to prevent wasted tokens, hallucinated scopes, and misaligned deliverables on complex tasks.
    5 installs
  70. ▌
    Ask For Alternative Viewpoints · alivirgo
    Techniques to eliminate echo-chamber bias and user sycophancy by forcing AI to steel-man opposing viewpoints, stress-test premises, and simulate adversarial stakeholders.
    4 installs
  71. ▌
    Ask For Tables Over Paragraphs · alivirgo
    How to enforce structured Markdown tables to cut token consumption by 50%, eliminate narrative fluff, and produce instantly scannable, copy-pasteable data.
    5 installs
  72. ▌
    Batch Small Questions Together · alivirgo
    How 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.
    6 installs
  73. ▌
    Brainstorm Presentation Angles · alivirgo
    How to use AI to generate 4 distinct narrative hooks and opening angles for keynotes, executive pitches, and all-hands presentations.
    9 installs
  74. ▌
    Break Big Questions Into Steps · alivirgo
    How to apply Task Decomposition to eliminate context saturation, prevent hallucination cascades, and build complex projects incrementally.
    10 installs
  75. ▌
    Browser Subagent Task Bounding · alivirgo
    How 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.
    5 installs
  76. ▌
    Comment Stripping Preprocessor · alivirgo
    How to strip redundant license headers, dead commented-out code, and verbose docstrings from source files before LLM ingestion, reducing input tokens by 40%.
    5 installs
  77. ▌
    Convert Voice Memos To Bullets · alivirgo
    How to process spoken dictation and audio transcripts, eliminate disfluencies and rambling, and extract structured executive notes.
    7 installs
  78. ▌
    Draft Emails With Placeholders · alivirgo
    How to use the Modular Bracketed Placeholder Pattern to create reusable, mistake-proof email templates for sales, client follow-ups, and executive updates.
    5 installs
  79. ▌
    Generate Social Media Captions · alivirgo
    How to prompt for high-engagement, platform-native social media copy across LinkedIn, X/Twitter, and Instagram without robotic AI clichés or emoji spam.
    5 installs
  80. ▌
    List Comprehension Compression · alivirgo
    How to replace verbose multi-line procedural accumulator loops with high-density Python list/dict comprehensions and functional pipelines, cutting loop token overhead by 60%.
    5 installs
  81. ▌
    Prioritize Urgent Vs Important · alivirgo
    How to use AI to triage chaotic daily to-do lists into the 4 Eisenhower Quadrants (Do First, Schedule, Delegate, Eliminate) for maximum daily leverage.
    9 installs
  82. ▌
    Schema Pruned Function Calling · alivirgo
    How to strip redundant descriptions, uncalled optional parameters, and unused tool definitions from agent JSON schemas, cutting baseline tool-calling token overhead by 65%.
    6 installs
  83. ▌
    Scripted Formatting Delegation · alivirgo
    How 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.
    7 installs
  84. ▌
    Single Command Script Chaining · alivirgo
    How to chain setup, build, and verification commands into atomic single-turn compound executions (&&, ;, |), slashing API roundtrips and conversation context accumulation by 80%.
    4 installs
  85. ▌
    Sliding Window Chat Truncation · alivirgo
    How 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.
    5 installs
  86. ▌
    Speculative Decoding Prompting · alivirgo
    How 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.
    4 installs
  87. ▌
    Structured Outputs Strict Mode · alivirgo
    How 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.
    4 installs
  88. ▌
    Always Verify Numbers And Links · alivirgo
    Why LLMs hallucinate statistics, phone numbers, and URLs, and how to enforce grounding, external verification, and tool-assisted calculations.
    5 installs
  89. ▌
    Avoid Duplicate System Messages · alivirgo
    How 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%.
    5 installs
  90. ▌
    Dont Trust AI Medical Diagnoses · alivirgo
    How to safely use AI for medical literacy, lab test vocabulary translation, and doctor appointment preparation while strictly avoiding self-diagnosis traps.
    5 installs
  91. ▌
    Specify Preferred Writing Style · alivirgo
    How to move beyond vague style adjectives by defining Tone, Information Density, and Sentence Cadence across 5 standard professional style presets.
    6 installs
  92. ▌
    Beware Of AI Recommendation Bias · alivirgo
    How to neutralize pre-training data bias, SEO affiliate spam influence, and brand popularity bias when evaluating software, hardware, and vendors.
    10 installs
  93. ▌
    Build Your AI Common Sense Habit · alivirgo
    The foundational 5-pillar operating system for using generative AI with maximum efficiency, zero hallucination risk, and 10x leverage.
    4 installs
  94. ▌
    Format Data To Copy Paste Tables · alivirgo
    How to use AI as an instant ETL engine to parse messy raw text, emails, and receipts into clean, spreadsheet-ready TSV/CSV tables.
    3 installs
  95. ▌
    Silent Background Task Execution · alivirgo
    How autonomous agents launch long-running compilation, server, and test processes asynchronously (WaitMsBeforeAsync, IsDaemon) without blocking chat turns or polling.
    10 installs
  96. ▌
    State Your Goal Not Just Command · alivirgo
    How to avoid the classic XY Problem by explaining the ultimate business or technical outcome you want, unlocking simpler and higher-leverage solutions.
    4 installs
  97. ▌
    Treat AI Answers As First Drafts · alivirgo
    How 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.
    10 installs
  98. ▌
    Use Fast Models For Quick Checks · alivirgo
    How 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.
    4 installs
  99. ▌
    Clean Messy Notes To Action Items · alivirgo
    How to parse chaotic brain dumps and meeting notes into structured [WHO] - [WHAT] - [BY WHEN] action items, decisions, and follow-ups.
    9 installs
  100. ▌
    Combine Human Speed With AI Scale · alivirgo
    How to operate as an elite Centaur/Cyborg operator by delegating heavy synthesis and drafting to AI while retaining human taste, strategy, and judgment.
    9 installs