Loading...
Loading...
Found 836 Skills
Use this skill when a Legal or HR matter must be classified and routed to the right specialist agent, when a matter crosses both domains and needs parallel review, or when Legal and HR agents disagree and the conflict must be resolved. It defines routing rules, the overlap handoff matrix, the controlled-handoff communication principles, and the conflict-resolution protocol. It does not give legal or HR advice and never makes a final routing decision binding on a human.
Diagnose the release-please release pipeline, read-only. Preview the next version from the merged Conventional-Commit PR titles since the last tag (feat→minor, fix/perf/revert→patch, !/BREAKING→major; docs/chore/ci/refactor/ test/build/style→none), show the open release-please--branches--main PR and its required-check (🔬 Build & Lint) status, detect the recurring stale `autorelease: pending` stall on the last merged release PR (where release-please aborts and releases silently stop firing), and confirm tag-vs-version parity (does a v<package.json version> tag already exist, or is publishing pending — the release.yml version-vs-tag gate). Use when asked why a release didn't fire, what version would cut next, whether the release PR is green, whether the pipeline is stalled, or to check release health. Advisory only — it inspects post-merge main and changes nothing.
Professional DOCX document creation, editing, and formatting using OpenXML SDK (.NET). Three pipelines: (A) create new documents from scratch, (B) fill/edit content in existing documents, (C) apply template formatting with XSD validation gate-check. MUST use this skill whenever the user wants to produce, modify, or format a Word document — including when they say "write a report", "draft a proposal", "make a contract", "fill in this form", "reformat to match this template", or any task whose final output is a .docx file. Even if the user doesn't mention "docx" explicitly, if the task implies a printable/formal document, use this skill.
Helps engineering managers break down knowledge silos and build sustainable documentation and collaboration practices — produces a four-root-cause diagnostic for silos, an Engineering Guilds framework, a minimum-viable documentation approach using ADRs, a structured onboarding model, and a cross-team request decision framework. Use when the user says "knowledge silos," "reinventing the wheel," "nobody reads docs," "onboarding is bad," "teams don't talk," "documentation culture," "cross-team friction," "information doesn't flow," or "new hires struggle to ramp up."
Brutally honest pre-traction revenue audit — the minimum code, infra, features, and process needed to land the FIRST paying user NOW, plus aggressive deletion of anything that doesn't move money. SCOPE — use this specifically when the project has ZERO signups and/or ZERO paying users; it's the reality check for a build that isn't converting yet, not an optimizer for a product that already has traction. Use when the user invokes /make-money, or (in that zero-traction state) says "audit for revenue", "am I wasting time", "why am I not making money", "is this making money", "what should I cut", or asks for a no-bullshit commercial reality check.
Identify the core constraints that truly define a domain, profession, role, product, or debate. Classify these constraints into World/Rules/Interpretation (Hard/Soft/Self-imposed) categories, then analyze how this set of constraints defines identity, completes the problem statement, frames the solution space, and explains actual behaviors. It is particularly useful for distinguishing solution divergences caused by different constraints despite the same goal, and identifying old interpretations that are mistakenly treated as hard facts. USE WHEN the user says 'constraint', 'find constraints', 'what are the constraints of this domain', 'essential constraints', 'what defines its boundaries', 'is this a hard constraint or self-imposed constraint', 'where are the boundaries', 'why does this behavior happen', 'constraint', '/ljg-constraint', or provides any domain/profession/role/product/debate and requests mapping of its defining constraints and solution space. NOT FOR deep-dive generators (use ljg-rank, which focuses on generative power rather than boundaries), vertical deep dives into a single viewpoint (use ljg-think), book decomposition (use ljg-book), or concept dissection (use ljg-learn).
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Can critique architecture. Use why for motivation.
The agentmemory HTTP REST API surface, the primary protocol for talking to the memory server. Use when calling agentmemory over HTTP, when MCP is unavailable and you need a fallback, or when integrating a host that does not speak MCP.
Run /document `pr` | `changelog` | `release-note` | `postmortem` (or let it ask) to write the human facing prose about a change. Drafts from the real commits and diff, writing to the right place. Does not write code, tests, or specs.
No-code automation democratizes workflow building. Zapier and Make (formerly Integromat) let non-developers automate business processes without writing code. But no-code doesn't mean no-complexity - these platforms have their own patterns, pitfalls, and breaking points. This skill covers when to use which platform, how to build reliable automations, and when to graduate to code-based solutions. Key insight: Zapier optimizes for simplicity and integrations (7000+ apps), Make optimizes for power
One-stop skill for the project architecture center — draft new architecture documents, refresh existing architecture documents, or conduct an architecture health check. Automatically determine the mode based on user input: `new` (draft)/ `update` (refresh to the latest code status)/ `check` (view only, generate issue list). The `check` mode has three sub-goals: consistency within a single feature design, alignment between design and code, and consistency among multiple documents under `easysdd/architecture/`. Single-target rule — only modify one document or check one target at a time. Trigger scenarios: User says "fill in an architecture doc", "draft an architecture document", "refresh the architecture directory", "write down the structure of this module", "conduct an architecture check", "is the design internally consistent?", "does the plan match the code?", "are there conflicts among several documents in the architecture folder?", or when it is found in the feature-design / feature-acceptance / implement phase that an architecture action needs to be performed first before proceeding.
The coupon management function of Gate Exchange: query available coupons, check coupon details, view usage rules, and trace coupon source. Use this skill whenever the user asks about their coupons, vouchers, or bonus cards on Gate Exchange. Trigger phrases include 'my coupons', 'do I have any coupons', 'coupon list', 'check my voucher', 'coupon details', 'when does my coupon expire', 'coupon rules', 'how did I get this coupon', 'coupon source'.