pascalandy
64 verified skills
ContentAnalysis
Content-adaptive wisdom extraction from videos, podcasts, articles, and YouTube -- dynamic sections built from what the content actually contains, not static templates. USE WHEN extract wisdom, content analysis, analyze content, analyze video, analyze podcast, extract insights, key takeaways, what did I miss, extract from YouTube, insight report, summarize content, what's interesting.
data-ai
ce-ideate
Generate and critically evaluate grounded ideas about a topic. Use when asking what to improve, requesting idea generation, exploring surprising directions, or wanting the AI to proactively suggest strong options before brainstorming one in depth. Triggers on phrases like 'what should I improve', 'give me ideas', 'ideate on X', 'surprise me', 'what would you change', or any request for AI-generated suggestions rather than refining the user's own idea.
data-ai
ce-plan
Create structured plans for any multi-step task -- software features, research workflows, events, study plans, or any goal that benefits from structured breakdown. Also deepen existing plans with interactive review of sub-agent findings. Use for plan creation when the user says 'plan this', 'create a plan', 'write a tech plan', 'plan the implementation', 'how should we build', 'what's the approach for', 'break this down', 'plan a trip', 'create a study plan', or when a brainstorm/requirements document is ready for planning. Use for plan deepening when the user says 'deepen the plan', 'deepen my plan', 'deepening pass', or uses 'deepen' in reference to a plan. For exploratory or ambiguous requests where the user is unsure what to do, prefer ce-brainstorm first.
development
ce-debug
Systematically find root causes and fix bugs. Use when debugging errors, investigating test failures, reproducing bugs from issue trackers (GitHub, Linear, Jira), or when stuck on a problem after failed fix attempts. Also use when the user says 'debug this', 'why is this failing', 'fix this bug', 'trace this error', or pastes stack traces, error messages, or issue references.
development
ce-test-xcode
Build and test iOS apps on simulator using XcodeBuildMCP. Use after making iOS code changes, before creating a PR, or when verifying app behavior and checking for crashes on simulator.
tools
qmd
Explicitly triggered when the user mentions `qmd`. It searches local markdown or QMD collections.
testing
ask-questions
Explicitly triggered when the user mentions `ask-questions`. It runs a structured clarification interview.
testing
eval-rubric
Explicitly triggered when the user mentions `eval-rubric`. It scores an artifact against criteria.
testing
hunk-review
Explicitly triggered when the user mentions `hunk-review`. It works with interactive Hunk diff review sessions.
testing
creative
Creative toolkit for videos, diagrams, generative art, web design, songwriting, and ffmpeg media work. Use for Manim videos, ASCII art or video, Excalidraw diagrams, p5.js sketches, design-system-inspired pages, Suno prompts, and common video or audio editing tasks.
tools
marketing
Full-stack SaaS marketing -- strategy and research, SEO, conversion optimization, content creation, demand generation, and revenue operations across 34 specialized domains routed automatically based on intent.
testing
ubiquitous-language
Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions "domain model" or "DDD".
development
distill
Explicitly triggered when the user mentions `distill`. It distills a local file into notes or a summary.
testing
liteparse
Parse, convert, or extract text from unstructured documents (PDF, DOCX, PPTX, XLSX, images) locally with the LiteParse CLI -- no cloud, no LLM. USE WHEN parse pdf, parse document, extract text, OCR pdf, OCR image, convert docx, convert pptx, convert xlsx, batch parse, page screenshot, render pdf pages, lit cli, liteparse, install liteparse, libreoffice, imagemagick, my parse preferences, LYKRA.
tools
investigation
Structured public-source investigation skill with automatic routing for people investigations, business due diligence, and infrastructure intelligence. USE WHEN find person, locate someone, reconnect, people search, social media search, person public records, people public records search, map public footprint, reverse lookup, phone lookup, email lookup, username lookup, image lookup, verify identity, background on person, company intel, company lookup, business background, leadership review, due diligence, vendor vetting, investment review, go or no-go recommendation, business investigation, organization research, nonprofit research, association research, academic research, government body research, domain lookup, DNS review, subdomain discovery, hosting analysis, infrastructure mapping, IP investigation, URL investigation, hash lookup, threat intel, IOC analysis, technical entity investigation, discover sources, niche OSINT sources, research new tools for a technical case.
tools
changelog
Explicitly triggered when the user mentions `changelog`. It updates `CHANGELOG.md`.
testing
mermaid
Use when the task asks for a Mermaid diagram such as a flowchart, sequence diagram, ERD, class diagram, state machine, git graph, gantt chart, pie chart, or architecture diagram.
data-ai
distill-prompt
Explicitly triggered when the user mentions `distill-prompt`. It selects a distill prompt style.
testing
beads
Explicitly triggered when the user mentions `bd` or `beads`. It searches the Git-backed issue tracker.
testing
commit
Explicitly triggered when the user mentions `commit`. It handles the commit workflow.
testing
coding-language
Use when writing, debugging, linting, or reviewing Bash, Python, or Starlette/ASGI code.
development
delegate-to-sub
Explicitly triggered when the user mentions `delegate-to-sub`. It routes work to sub-agents.
testing
pseudocode-cas-utilisation
Déclenché explicitement quand l'utilisateur mentionne `pseudocode-cas-utilisation` ou demande de rédiger / formater un cas d'utilisation (CU) métier en français. Produit un document CU lisible avec corridor principal séparé des variantes ancrées à leurs étapes.
development
headless
Explicitly triggered when the user mentions `headless`, `headless-claude`, `headless-codex`, or `headless-opencode`. It provides headless delegation and CLI flag guidance.
tools
marp
Explicitly triggered when the user mentions `marp`. It creates Marp slide decks.
testing
pseudocode
Explicitly triggered when the user mentions `pseudocode`. It expands a plan into user flows.
development
meta-skill-creator
Explicitly triggered when the user mentions `meta-skill-creator`. It creates router or meta-skills.
testing
slidev
Explicitly triggered when the user mentions `slidev`. It creates Slidev decks.
development
cass
Explicitly triggered when the user mentions `cass`. It searches local coding-agent history.
testing
obsidian
Explicitly triggered when the user mentions `obsidian`. It handles Obsidian vault operations.
testing
plantuml-ascii
Use when the task needs a terminal-friendly ASCII or Unicode text diagram generated with PlantUML.
development
grill-me
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
testing
coding-standard
Use when designing, implementing, or reviewing an agent-friendly CLI, including commands, flags, help text, output, errors, and safety behavior.
tools
single-skill-creator
Explicitly triggered when the user mentions `single-skill-creator`. It scaffolds a new `SKILL.md`.
testing
transcript-sk
Explicitly triggered when the user mentions `transcript-sk`. It transcribes YouTube videos.
testing
simple-editor
Explicitly triggered when the user mentions `simple-editor`. It cleans raw personal notes without changing voice.
testing
ce-test-browser
Run browser tests on pages affected by current PR or branch
testing
ce-session-inventory
Discover session files for a repo across Claude Code, Codex, and Cursor, and extract session metadata (timestamps, branch, cwd, size, platform). Invoked by session-research agents — not intended for direct user queries.
development
ce-frontend-design
Build web interfaces with genuine design quality, not AI slop. Use for any frontend work - landing pages, web apps, dashboards, admin panels, components, interactive experiences. Activates for both greenfield builds and modifications to existing applications. Detects existing design systems and respects them. Covers composition, typography, color, motion, and copy. Verifies results via screenshots before declaring done.
development
ce-demo-reel
Capture a visual demo reel (GIF, terminal recording, screenshots) for PR descriptions. Use when shipping UI changes, CLI features, or any work with observable behavior that benefits from visual proof. Also use when asked to add a demo, record a GIF, screenshot a feature, show what changed visually, create a demo reel, capture evidence, add proof to a PR, or create a before/after comparison.
tools
ce-lfg
Full autonomous engineering workflow
tools
ce-compound
Document a recently solved problem to compound your team's knowledge
documentation
ce-agent-native-architecture
Build applications where agents are first-class citizens. Use this skill when designing autonomous agents, creating MCP tools, implementing self-modifying systems, or building apps where features are outcomes achieved by agents operating in a loop.
tools
ce-work
Execute work efficiently while maintaining quality and finishing features
testing
ce-brainstorm
Explore requirements and approaches through collaborative dialogue before writing a right-sized requirements document and planning implementation. Use for feature ideas, problem framing, when the user says 'let's brainstorm', or when they want to think through options before deciding what to build. Also use when a user describes a vague or ambitious feature request, asks 'what should we build', 'help me think through X', presents a problem with multiple valid solutions, or seems unsure about scope or direction — even if they don't explicitly ask to brainstorm.
development
ce-code-review
Structured code review using tiered persona agents, confidence-gated findings, and a merge/dedup pipeline. Use when reviewing code changes before creating a PR.
development
meta-skill-creator
Explicitly triggered when the user mentions `meta-skill-creator`. It creates router or meta-skills.
testing
map-filesystem
Explicitly triggered when the user mentions `map-filesystem-abstract`. It generates or updates atlas files.
testing
nia-docs
Explicitly triggered when the user mentions `nia-docs`. It browses documentation sites through that tool.
tools
wiki-map
Explicitly triggered when the user mentions `wiki-map`. It ingests, queries, lints, or compiles a markdown wiki.
development
ce-compound-refresh
Refresh stale learning docs and pattern docs under docs/solutions/ by reviewing them against the current codebase, then updating, consolidating, replacing, or deleting the drifted ones. Trigger this skill when the user asks to refresh, audit, sweep, clean up, or consolidate stale docs in docs/solutions/ (phrases like "refresh my learnings", "audit docs/solutions/", "clean up stale learnings", "consolidate overlapping docs", "compound refresh", "/ce-compound-refresh"), or when ce-compound has just captured a new learning and flagged a specific older doc in docs/solutions/ as now inaccurate or superseded — invoke with the narrow scope hint ce-compound provides. Also trigger when the user points at a specific learning or pattern doc under docs/solutions/ and calls it stale, outdated, overlapping, or drifted. Do not trigger for general refactor, migration, debugging, or code-review work unless the user has explicitly directed attention to docs/solutions/ itself.
development
ce-optimize
Run metric-driven iterative optimization loops. Define a measurable goal, build measurement scaffolding, then run parallel experiments that try many approaches, measure each against hard gates and/or LLM-as-judge quality scores, keep improvements, and converge toward the best solution. Use when optimizing clustering quality, search relevance, build performance, prompt quality, or any measurable outcome that benefits from systematic experimentation. Inspired by Karpathy's autoresearch, generalized for multi-file code changes and non-ML domains.
development
ce-doc-review
Review requirements or plan documents using parallel persona agents that surface role-specific issues. Use when a requirements document or plan document exists and the user wants to improve it.
testing
ce-session-extract
Extract conversation skeleton or error signals from a single session file at a given path. Invoked by session-research agents after they have selected which sessions to deep-dive — not intended for direct user queries.
data-ai
ce-report-bug
Report a bug in the compound-engineering plugin
tools
ce-gemini-imagegen
This skill should be used when generating and editing images using the Gemini API (Nano Banana Pro). It applies when creating images from text prompts, editing existing images, applying style transfers, generating logos with text, creating stickers, product mockups, or any image generation/manipulation task. Supports text-to-image, image editing, multi-turn refinement, and composition from multiple reference images.
development
ce-resolve-pr-feedback
Resolve PR review feedback by evaluating validity and fixing issues in parallel. Use when addressing PR review comments, resolving review threads, or fixing code review feedback.
development
writer-sk
Explicitly triggered when the user mentions `writer-sk`. It rewrites prose for clarity and concision.
testing
liteparse
Explicitly triggered when the user mentions `liteparse`. It parses documents and runs OCR locally.
testing
map-filesystem
Explicitly triggered when the user mentions `map-filesystem-abstract`. It generates or updates atlas files.
testing
obsidian
Explicitly triggered when the user mentions `obsidian`. It handles Obsidian vault operations.
testing
ontology-map
Explicitly triggered when the user mentions `ontology-map`. It builds, refreshes, or checks an ontology.
development
cass
Explicitly triggered when the user mentions `cass`. It searches local coding-agent history.
testing
nia-docs
Explicitly triggered when the user mentions `nia-docs`. It browses documentation sites through that tool.
tools