Loading...
Loading...
Found 13 Skills
Orchestrate GitHub issue authoring by classifying request type, routing to a type-specific issue-author skill, and enforcing shared safety gates before mutation.
This skill should be used when processing meeting transcripts to auto-detect meeting type (leadgen, partnership, coaching, internal) and extract type-specific structured analysis. Triggers on "process meeting", "analyze meeting", "meeting summary", or after syncing new Fathom/Granola transcripts.
Multi-layer caching with type-specific TTLs, get-or-generate pattern, memory and database layers, and graceful invalidation without cache stampede.
MANDATORY prerequisite — load this skill BEFORE every `generate_diagram` tool call. Routes to type-specific guidance (generic flowchart, architecture flowchart) and tells you when to proceed directly, when to use a different diagram type, or when the tool isn't the right fit at all.
Classify a PPT brief into one of four types (Pitch / Research / Teaching / Narrative), then generate a high-level chapter skeleton personalized to the topic for that type. Different PPT types require different argumentation frameworks and different chapter structures — a research PPT is not a pitch, and a pitch is not a narrative. Use this at the very start of PPT planning, before formulating the thesis. It pairs with ppt-research-setup and other type-specific setup skills for detailed per-chapter reasoning.
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must never be mixed.
Guides Android code reviews with type-specific checklists and MVVM/Compose pattern validation. Use when reviewing Android PRs, pull requests, diffs, or local changes involving Kotlin, ViewModel, Composable, Repository, or Gradle files. Triggered by "review PR", "review changes", "check this code", "Android review", or code review requests mentioning bitwarden/android. Loads specialized checklists for feature additions, bug fixes, UI refinements, refactoring, dependency updates, and infrastructure changes.
Optimize existing Triton kernels for NVIDIA TileIR backend on Blackwell GPUs (sm_100+). Adds TileIR-specific autotune configs: occupancy, num_ctas, TMA descriptors. Covers kernel classification (dot-related, norm-like, elementwise, reduction), type-specific transformations, and PTX-vs-TileIR benchmarking. Triggered by: "optimize for TileIR", "add TileIR configs", "Blackwell optimization", "TMA descriptors", "2CTA mode", "occupancy tuning". Kernels use standard `import triton`; TileIR activates via ENABLE_TILE=1 when nvtriton is installed.
Use when creating or changing a Bagisto product type — the product_types config, an AbstractType subclass, or type-specific cart, pricing and inventory behaviour. Trigger phrases include "product type", "AbstractType", "configurable", "bundle", "grouped", "downloadable", "virtual product", "subscription product", "prepareForCart".
**INTERNAL USE ONLY — invoked by `service-de-headless-channel-configure` orchestrator.** Insert an Enhanced messaging `MessagingChannel` record (plus its child `MessagingChannelUsage` as a free server-side side-effect) of any supported type — WhatsApp, LINE, Apple Business Chat, Facebook, or SMS (Text). Given a `{MESSAGE_TYPE}` and the corresponding type-specific inputs, runs the shared preflight → Connect-insert → verify flow and branches only where a type genuinely differs (request body, prerequisites, error classes). Uses the sanctioned `POST /services/data/v{V}/connect/livemessage/channels` Connect REST endpoint — no Aura session, no token extracted into shell state. **Users should always invoke `service-de-headless-channel-configure` instead — it handles insert → route → activate in one flow.** Use this skill when inserting a messaging channel of any type; it replaces the four former per-type creation skills.
Top-level orchestrator: given a messaging channel type and its type-specific inputs, produces an activated Enhanced `MessagingChannel` in the target Salesforce org — without the Meta/LINE/Apple setup popups. Prompts for `{MESSAGE_TYPE}` if not supplied, then sequences insert → route → consent → activate via the type-agnostic dispatcher (`service-de-channel-create`) plus the shared routing/consent/activation leaves. Resumes from partial state on re-run. Use this skill when the user wants to set up an Enhanced messaging channel (WhatsApp, Facebook, LINE, Apple, or SMS/Text) end-to-end from the command line, bypassing the in-org setup popups.
Evaluate every produced output (code, report, plan, data, API response) against type-specific quality criteria, score 1-10, make accept/reject decisions, and provide actionable improvement suggestions. Triggers on "evaluate", "check", "review", "quality control", "is this good enough", "score it", or before passing output to the next step in an agentic workflow.