Loading...
Loading...
Found 2,589 Skills
Use when you have a rough idea and want to refine it into a well-formed proposal before submitting to Nexus. Must check directive first - all ideas must align with current organizational focus.
Read back adr-patterns + adr-edges namespaces, surface dangling refs / supersede cycles / status mismatches; exit 1 on cycles
Maintain repository integrity and documentation. Use for auditing structure, checking config validity, and reviewing inventory. Use proactively to validate the repository or sync documentation. Examples: - user: "Validate the repo" → run audit_repo.py - user: "Check agents" → run audit_repo.py, review errors - user: "Update documentation" → run sync_docs.py - user: "Check for issues" → run full audit
Best practices and rules for securing FiveM resources against cheaters and exploits. Use this skill when writing or reviewing server-side and client-side code to ensure malicious events, unauthorized entity creations, and client trust issues are prevented. Focuses on strict server authority and safe event handling.
This skill should be used when the user wants to create a new agent skill, scaffold a SKILL.md, validate an existing skill against repo rules, or refactor a skill to match this monorepo's conventions. Common triggers include "build a skill for X", "create a new skill", "scaffold a skill", "add a skill that does Y", "make me a skill", "audit this skill against our rules", and "refactor this skill to match repo conventions". Enforces kebab-case naming, verbatim trigger phrases, selective XML for example boundaries, and a RED→GREEN→REFACTOR cycle. Skip when modifying source code, debugging an existing skill, or writing non-skill markdown.
Creates, updates, validates, and displays the architectural DNA of a project through two shared documents: docs/specs/architecture.md (technology stack, architectural rules, security constraints, AI guardrails) and docs/specs/ontology.md (domain glossary / Ubiquitous Language). Use BEFORE brainstorm as a project setup step, or at any point in the SDD lifecycle to validate specs/tasks against architecture principles. Triggers on 'create constitution', 'update constitution', 'constitution check', 'validate against constitution', 'project principles', 'architectural guardrails', 'setup project architecture', 'define ontology'.
Submit a kid-facing English content PR to the football-english repo (zxkane/football-english). Use this whenever the user asks to "submit this week's quiz", "publish a weekly quiz", "submit a daily reading", "add today's reading", "publish a daily article", "open a daily PR", "open a quiz PR", or hands over essay paragraphs (with optional KET/PET points, vocabulary, audio, image, questions) and expects them to land in the kid-facing site. The repo publishes two kinds of content — weekly quizzes (essay + 3-20 graded questions, one per ISO week) and daily readings (essay + TTS audio + image + structured KET/PET points + optional 0-3 small questions, irregular cadence). This skill picks the right shape, writes the JSON, validates it, and opens the PR end-to-end. Trigger this skill even if the user doesn't use the words "quiz", "daily", or "PR" — any handover of essay paragraphs intended for this repo qualifies.
Validates planning artifacts and reviews code for quality, consistency, and completeness. Use to lint planning documents (cross-references, dependencies, format) or to review changed code (security, coherence, scope, quality).
从智慧芽（PatSnap）数据库查询专利法律状态信息。当用户提到专利法律状态、专利有效性核查、专利状态查询、专利事件历史、简单法律状态、转让、许可、质押、异议、诉讼、复审等法律事件、patent legal status, patent validity, patent events, transfer/license/pledge, PatSnap, patent status lookup时触发此技能。当用户询问专利是否处于有效、无效、审中、过期、授权、撤回或撤销状态，或想通过专利ID或公开号查询法律状态时也应触发。
Build and validate HelixDB dynamic inline-query requests for POST /v1/query. Use when the task involves dynamic queries, inline query JSON, the inline AST (steps, predicates, expressions, projections), parameter_types, DateTime coercion, query warming, or debugging a request body sent directly to the Helix gateway. See REFERENCE.md for every AST variant and EXAMPLES.md for copy-pasteable payloads.
Runs validator checks only without AI reviews for requests such as "run validator checks", "check without reviews", or "validate before commit without AI review".
Capture noteworthy review violations for the eval framework. Use when validator-run finds review failures — judges violations and saves notable ones to evals/inventory.yml.