FrancyJGLisboa

@francyjglisboa source repo

21 skills
0 followers
21 hours ago last updated

▌
Live Weather Briefing Skill · francyjglisboa bundle
Create a current, source-linked weather briefing for a named city using the Open-Meteo geocoding and forecast APIs. Activate for requests such as "what is the weather in Sao Paulo?", "prepare a current weather briefing for Tokyo", or "get today's live conditions for New York". Do not use for travel booking, weather alerts, historical climatology, or safety-critical decisions.

0
installs
▌
Detect AI Value Mode From Codebase · francyjglisboa bundle
Analyse a codebase to determine which of the four AI product value modes it embodies — Amplifier, Substitute, Job Creator, or Democratiser — and produce a sober, evidence-grounded verdict report in plain prose (Unicode text only, no emojis). Use this skill when the user wants to understand the strategic positioning or business model of an AI product by reading its code: triggers include "what mode is this", "detect AI value mode", "which quadrant does this fall into", "classify my AI product", or any pairing of a codebase path or pasted code with a question about how the product creates value, who its buyer is, or how it should be positioned. Trigger even when the user does not name the four modes explicitly — intent to classify an AI product from its code is sufficient. When asked for a diagram or infographic version, also renders the verdict as a self-contained HTML poster.

0
installs
▌
Creative Ideation · francyjglisboa bundle
Generate ideas via named methods from creative practice.

0
installs
▌
Session Xray Skill · francyjglisboa bundle
Distill long AI-human sessions into inspectable reasoning models. Activates when users ask to extract the logic from this session, what were the assumptions, summarize the decisions, show the reasoning chain, session retrospective, extract formulas from conversation, what did we decide, assumption ledger, decision trajectory, reasoning graph, ambiguity check, session distillation, logic skeleton, dependency map, session shadow model. Triggers on phrases like what was the reasoning behind this session, extract assumptions from our conversation, map the decisions we made, show me the logic chain, what depends on what, find contradictions in this session, distill this conversation, compress this session, audit this reasoning, trace the decision path, cognitive audit.

0
installs
▌
Whiteboard Math Skill · francyjglisboa bundle
Generate hand-solvable canonical math examples for any AI-built model, algorithm, or analytical pipeline. Activates when users ask to explain the math, show me the equations, create a canonical example, hand calculation, toy model, whiteboard example, validate the math, prove the formula, show intermediate steps, math unit test, sanity check, expected output, shadow model, or interpretability artifact. Triggers on phrases like show me the math behind this, create a hand-solvable example, extract the formulas, build a toy dataset, what are the equations, walk me through the calculation, produce a whiteboard version, map this to a simple example, math transparency, human readable math, algorithm decomposition, formula extraction.

0
installs
▌
Run Gauntlet · francyjglisboa bundle
Execute an existing agent-ready Gauntlet Pack through bounded builder-critic loops, independent evidence collection, formal state transitions, and clean-room final verification. Use when `.gauntlet/manifest.yaml` or an equivalent compiled pack exists and the user wants agents to implement, adapt, repair, or validate the target. Do not use to invent requirements from a vague request; invoke compile-gauntlet first.

0
installs
▌
Frame Failure · francyjglisboa bundle
Interview a subject-matter expert about the outcomes they refuse to accept, and write a Gauntlet request from their answers. Use before compile-gauntlet when the person knows what they want but cannot state what would make it wrong, when a request describes features without consequences, or when a compiled pack would otherwise have no bar beyond the agent's own taste. Do not use to elicit technical decisions, architecture, thresholds, or acceptance commands; those are the compiler's to derive.

0
installs
▌
Compile Gauntlet · francyjglisboa bundle
Convert vague goals, reference repositories, YouTube demonstrations, blogs, social discussions, screenshots, live products, papers, target data sources, or adaptation requests into complete agent-executable Gauntlet Packs. Use before implementation when requirements are underspecified, public evidence must be reconstructed into an independent production-grade product, a repository must be pivoted to new data or domains, acceptance criteria are missing, or agents need an evidence-grounded builder-critic workflow without relying on human technical judgment. Do not use merely to execute an already complete Gauntlet Pack.

0
installs
▌
Bdistill Xray · francyjglisboa bundle
Probe any AI model's behavioral patterns across 6 dimensions — tool use, refusal boundaries, formatting defaults, reasoning style, persona stability, and grounding/hallucination resistance. The model probes itself, no API key needed. Generates a visual report. Triggers on "x-ray", "probe behavior", "behavioral analysis", "model evaluation", "how does this model behave". Outputs behavioral profile with scores.

0
installs
▌
Bdistill Export · francyjglisboa
Export a bdistill knowledge base into any format — system prompt for Claude Projects/Cursor/Copilot/ChatGPT, Python harness module with build_prompt(), JSON for agent consumption, Excel with quality color-coding, audit checklist CSV, or fine-tuning JSONL. Triggers on "export", "system prompt", "harness", "training data", "Excel export", "export for Claude Project". Outputs file on disk.

0
installs
▌
Bdistill Extract · francyjglisboa bundle
Extract structured, adversarially validated domain knowledge or IF-THEN decision rules from AI training knowledge. Builds a compounding knowledge base — one file per domain, deduplicated across sessions. Triggers on "extract knowledge", "build KB", "distill", "extract rules", "decision thresholds", "what do you know about". Outputs JSONL entries to {domain}.jsonl.

0
installs
▌
Bdistill Predict · francyjglisboa bundle
Assemble structured predictions with decomposed evidence, adversarial self-challenge, and calibrated probability. Supports binary YES/NO mode (prediction markets, any yes/no question) and directional mode. Optionally recalls from your KB and searches the web for current data. Triggers on "predict", "forecast", "what happens if", "probability of", "will X happen". Outputs prediction card with evidence chain.

0
installs
▌
Bdistill Abstract · francyjglisboa bundle
Extract structural rules from one domain, abstract to bare skeletons at three granularity levels, then re-instantiate in other domains to discover non-obvious cross-domain correspondences. Filters with mandatory web-grounded novelty check AND adversarial validity challenge AND reverse round-trip validation. Triggers on "abstract rules", "cross-domain", "structural analogy", "what pattern in X applies to Y", "transfer rules between domains". Outputs validated cross-domain rule correspondences with structured testable predictions.

0
installs
▌
Bdistill Discover · francyjglisboa
Map any professional domain into extractable topics with seed terms and a recommended extraction plan. Triggers on "I work in", "what can you extract about", "help me get started", "map my domain", "I don't know what to extract". Outputs structured domain map with seed terms for bdistill-extract.

0
installs
▌
Bdistill Validate · francyjglisboa bundle
Detect confabulated claims by re-asking entries with rephrased questions and measuring variance — both numeric stability (do the numbers stay the same?) and structural stability (do the conditions, scope, and reasoning stay the same?). Use after bdistill-extract to filter your KB before export. Triggers on "validate KB", "consistency check", "are these numbers real", "verify thresholds", "detect hallucination", "stability check". Outputs stability scores per entry.

0
installs
▌
Bdistill Operationalize · francyjglisboa bundle
Connect exported rules to live data for automated monitoring. Loads a bdistill rules export, fetches current data from free APIs or local feeds, contrasts each rule's conditions against reality, and reports which rules triggered with current values and impact estimates. Works with any domain — weather, market, compliance, clinical. Triggers on "operationalize", "monitor", "check against live data", "contrast rules", "what's triggered". Outputs decision report.

0
installs
▌
Agent Skills Platform · francyjglisboa bundle
Create cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill, audit this skill, is this skill safe, vet a skill before installing, what does this skill access. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, spec validation, and security auditing of third-party skills before install.

1
install
▌
Pr Blocker Summarizer · francyjglisboa bundle
Summarizes open pull requests into a blockers-first standup digest. Activates when the user asks to summarize open PRs, find blocked pull requests, generate a PR standup, or triage review backlog from a PR export.

1
install
▌
Weekly Crm Report · francyjglisboa bundle
Cleans a weekly CRM export and produces a regional sales summary. Activates when the user asks to clean a CRM export, deduplicate sales rows, calculate regional totals, or generate a weekly sales report from a CSV.

1
install
▌
Stock Analyzer · francyjglisboa
Provides comprehensive technical analysis for stocks and ETFs using RSI, MACD, Bollinger Bands, and other indicators. Activates when user requests stock analysis, technical indicators, trading signals, or market data for specific ticker symbols.

3
installs
▌
Agent Skill Creator · francyjglisboa
Create cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.

3
installs

21 published skills