Menu
SkillsMP a collecté 37 skills depuis gal-Tab/sir_albert. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 37 skills collectés sur 37.
Self-improving skills loop. Reads recent sessions (index + axcli analytics + transcripts), surfaces recommended skill edits — new trigger phrases, description tweaks, skill merges, new-skill candidates — and emits them as a draft for Gal to approve. Never…
Langue du texte source : anglais
Decision memory: record a call once, auto-apply it every time the same question recurs — never re-decide what's already settled. Use when the user says "/decide", "record this decision", "we decided", "did we decide X before", "log this call", or "is this…
Langue du texte source : anglais
The Discover/Think front door — a Core phase that picks the right thinking lens BEFORE a GTM, Building, or Automation task starts. Front-runs all three working modes; load it before committing to any approach or tool. Triggers: "help me think through X",…
Langue du texte source : anglais
Scope Edit/Write to a directory during debugging or investigation so unrelated files are not accidentally modified. Use when the user says "/freeze", "/freeze <path>", "freeze this path", "scope edits to", "lock to this dir", "/unfreeze", "freeze off".
Langue du texte source : anglais
Close the compound-learning loop: surface past corrections/patterns/playbooks from the project's .compound/ directory, then canonicalize accumulated drafts before they reach wiki-compile. Use when the user says "learnings", "load past corrections", "what did…
Langue du texte source : anglais
HubSpot API-safety check. Before shipping a workflow or code that calls HubSpot, scan for deprecated v1 endpoints and flag them with current v3 replacements so nothing silently breaks in production. Triggers: "hubspot safety", "check hubspot api", "is this…
Langue du texte source : anglais
Triage a failed n8n workflow execution. Paste an n8n execution URL and this skill pulls the failed node, reads the error, and proposes a concrete fix. Uses the n8n-mcp server (n8n at n8n.bigbrain.me). Triggers: "/n8n-triage", "n8n execution failed", "debug…
Langue du texte source : anglais
Defines the shared Building loop and named sub-loop entry points so dashboards, wikis, and MCPs each follow a consistent but distinct flow. Use when the user says "build discipline", "how do I build X", "start a new dashboard", "start a new wiki", "start a…
Langue du texte source : anglais
Pre-ship data-quality check before any dashboard or analysis is shared externally. Run this before presenting numbers to stakeholders or publishing a dashboard. Triggers on "data-review", "check this dashboard before I share", "data quality check", "pre-ship…
Langue du texte source : anglais
Pre-apply gate for GTM changes: validate tag/variable/trigger names against the naming convention and consent posture against the consent map BEFORE any apply-*.ts script runs. Use whenever someone is about to apply a GTM change, wants a pre-apply check, or…
Langue du texte source : anglais
Audit all server-side GTM (sGTM) Facebook and LinkedIn tags for a required parameter set and flag missing or inconsistently-named params. Use whenever someone asks to audit sGTM tag parameters, check tag parameter consistency, verify FB or LinkedIn tag…
Langue du texte source : anglais
Reload the latest handoff for the current project and state the plan back concisely before doing anything, so the user gets productive in ≤2 turns with zero re-explaining. Use when the user says "resume", "/resume", "pick up where we left off", "load the…
Langue du texte source : anglais
Post-merge git reconciliation in one command. Checks whether local and remote are in sync, reports divergence in plain language, and safely cleans up already-merged local branches (ask-before-delete, -d only). Use when the user says "sync", "/sync", "are we…
Langue du texte source : anglais
Wrap the current session for continuity so the user can /clear (or exit) and resume cleanly in a fresh session. Writes a prescriptive cold-start handoff doc AND a ready-to-paste restart prompt, with real git state auto-captured. Use when the user says "hand…
Langue du texte source : anglais
AUTO-LOAD during any brainstorm, discovery, or ideation moment. Convene a council of sharp, opinionated thinkers to explore, sharpen, or attack an idea from multiple angles — challenging assumptions, surfacing blind spots, and finding unexplored directions.…
Langue du texte source : anglais
Apply Monday.com's official brand identity to designs, artifacts, and visualizations. Use when creating Monday.com branded content including (1) HTML/web designs with Monday purple (#6161FF) and brand colors, (2) Charts, graphs, or data visualizations, (3)…
Langue du texte source : anglais
Creates branded monday.com HTML presentations using a design-system-first approach with responsive layouts, keyboard navigation, and professional monday branding. Use when the user asks to create a presentation, build slides, make a deck, or generate a slide…
Langue du texte source : anglais
Apply Monday.com's "Vibe" design system when generating Python (Plotly/Matplotlib), Streamlit, or Tableau visualizations. Use for charts, scorecards, and dashboards—typography (Figtree), color palettes, and data viz best practices.
Langue du texte source : anglais
Validate, test, and explain regex patterns for Google Analytics 4 (GA4) and Google Tag Manager (GTM). Use whenever someone writes, debugs, or asks about a GA4 regex — including audiences, explorations, custom definitions, data stream filters,…
Langue du texte source : anglais
Hand the current conversation off to a fresh background Claude Code agent that picks up the work immediately, in either execution or plan/discovery mode. Use this skill whenever the user asks to "hand this off", "spin up a background agent", "continue this in…
Langue du texte source : anglais
Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.
Langue du texte source : anglais
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
Langue du texte source : anglais
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
Langue du texte source : anglais
Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
Langue du texte source : anglais
Draft a LinkedIn post in Gal's Hebrew voice — trigger on "write a LinkedIn post", "draft a linkedin post", "post about this on linkedin", "כתוב לי פוסט ללינקדאין", "נסח פוסט ללינקדאין".
Langue du texte source : anglais
Draft and send Slack messages in Gal's voice (Hebrew or English) — trigger on "send a Slack", "send a summary on slack", "draft a slack message", "write this for slack", "כתוב/נסח הודעה לסלאק".
Langue du texte source : anglais
Generate professional, monday.com-branded SVG graphics for GitHub README files. Use this skill whenever the user wants to create SVG banners, hero images, pipeline diagrams, architecture flows, scanner/feature maps, data visualizations, status bars, terminal…
Langue du texte source : anglais
Generate implementation plans as rich, interactive HTML files styled with monday.com's dark theme. Use this skill whenever the user asks to write a plan, create an implementation plan, plan a feature, write a technical spec for implementation, or break down a…
Langue du texte source : anglais
Capture knowledge from the current session and file it back into the sir_albert knowledge base. Use when the user says "save this to the wiki", "file this knowledge", "add this to my KB", "remember this for future sessions", "compound this insight", "compound…
Langue du texte source : anglais
Assemble a virtual "Board of Advisors" offering 4 distinct perspectives on a problem, decision, or strategy. Use when the user asks for "board of advisors", "multiple perspectives", "evaluate this decision from different angles", or "4 points of view".
Langue du texte source : Plusieurs langues
Act as a Devil's Advocate using pre-commitment adversarial reasoning to prevent early lock-in and expose blind spots. Use when the user asks to "play devil's advocate", "stress test this", "what are the risks of", "challenge my idea", or when choosing between…
Langue du texte source : Plusieurs langues
Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.
Langue du texte source : anglais
Triggered when the owner asks to improve your operations, behavior, or skills, or when performing a periodic self-reflection. Converts vague dissatisfaction or observed inefficiencies into concrete technical improvements (e.g., editing MEMORY.md, SOUL.md,…
Langue du texte source : anglais
Automatically triage and inject text requests into the monday.com MOPs iteration board. Triggers when the user asks to add a task, open a ticket, or add an item to the MOPs iteration or queue (e.g., "Add a task for X", "Open a ticket for Y in the iteration",…
Langue du texte source : anglais
Install a PreToolUse hook that blocks dangerous git commands before they execute — force pushes, hard resets, branch deletions, working-tree nukes, and more. Use this skill whenever the user asks to set up git safety rules, git guardrails, protect a repo from…
Langue du texte source : anglais
Analyze a GitHub repository to provide a concise, strategic summary of its purpose, features, activity, and status. Use when the user asks to "check this repo", "analyze this github project", or asks for the status/details of a GitHub link.
Langue du texte source : anglais
Turn a conversation, idea, or feature request into a detailed, actionable PRD (Product Requirements Document) rendered as an interactive HTML file with monday.com's dark theme. Use this skill whenever the user says "write a PRD", "create a PRD", "make a…
Langue du texte source : anglais