All authors
Claude Skills by ngocsangyem
github.com/ngocsangyem330 skills0 installs428 views
- Mk Confluence PageConfluence page CRUD via confluence-as: create/show/update/delete, hierarchy, copy. NOT bulk (mk:confluence-bulk), spec analysis (mk:confluence-spec-analyst), or comments (mk:confluence-collaborate).Votes: 0GitHub stars: 14
- Mk Confluence SearchConfluence CQL search, space list, saved filters, export via confluence-as; CQL injection-safe. NOT single-page CRUD (mk:confluence-page) or bulk writes (mk:confluence-bulk).Votes: 0GitHub stars: 14
- Mk Confluence Spec AnalystRead-only spec analysis on a Confluence page (+children): requirements, acceptance criteria, gaps, user stories report. NOT page CRUD (mk:confluence-page) or ticket scoring (mk:planning-engine).Votes: 0GitHub stars: 14
- Mk ConfluenceRoutes Confluence Cloud tasks to the right mk:confluence-* leaf skill. Use for 'confluence', 'wiki page', 'spec page', or ambiguous intent. NOT an executor -- forks to a leaf skill.Votes: 0GitHub stars: 14
- Mk Context AuditRead-only audit of .codex/ structural overhead: 'remove X save Y tokens' vs the context window. NOT for cost tracking (budget skill); NOT for runtime read/compact decisions (mk:context-engineering).Votes: 0GitHub stars: 14
- Mk Context EngineeringRuntime router for context decisions: read-more/stop/ask/assume/delegate, minimal read-set, compaction timing. Model: Write/Select/Compress/Isolate. NOT for .codex/ overhead audit (mk:context-audit).Votes: 0GitHub stars: 14
- Mk CookSingle-task pipeline: plan → test → build → review (ship separately). Use for a feature or scoped fix. NOT for green-field builds (mk:autobuild) or auto-orchestration (mk:workflow-orchestrator).Votes: 0GitHub stars: 14
- Mk CsoChief Security Officer mode: infrastructure-first audit of secrets, dependency supply chain, CI/CD, LLM/AI security, OWASP Top 10, STRIDE, active verification. Daily/comprehensive, trend tracking.Votes: 0GitHub stars: 14
- Mk DatabaseDesign and safely evolve data models, schemas, migrations, queries, indexes, and ORM data-access boundaries. Discover the existing engine and migration source before proposing syntax.Votes: 0GitHub stars: 14
- Mk Decision FrameworkOperational decision frameworks: triage, escalation, case management, billing ops. Use for 'how to handle X cases', 'build triage', 'escalation protocol'.Votes: 0GitHub stars: 14
- Mk DevelopmentImplementing features or writing code. TDD is opt-in via --tdd / MEOWKIT_TDD=1. Provides code patterns, skill loading, and coding standards.Votes: 0GitHub stars: 14
- Mk DevopsPlan and implement infrastructure, container, CI/CD, deployment-safety, observability, and rollback changes. Does not read dotenv files or approve/release deployments.Votes: 0GitHub stars: 14
- Mk Docs FinderRetrieve current library, framework, and API docs via Context7, Context Hub, and web fallback. Use whenever docs are needed for a library, SDK, or internal spec instead of stale training data.Votes: 0GitHub stars: 14
- Mk Docs InitGenerate initial docs/ from codebase analysis when a project has none. Triggers on 'init docs', 'create/generate documentation'. NOT for updating existing docs (mk:document-release).Votes: 0GitHub stars: 14
- Mk Document ReleasePost-ship docs sync: cross-reference the diff and update README/ARCHITECTURE/CONTRIBUTING/AGENTS.md + CHANGELOG to match what shipped. Use on 'update/sync docs'; suggest after a PR opens.Votes: 0GitHub stars: 14
- Mk ElicitStructured second-pass reasoning after a review or plan verdict: pre-mortem, inversion, red team, Socratic lens, etc. NOT for initial review (mk:review) or new plans (mk:plan-creator).Votes: 0GitHub stars: 14
- Mk EvaluateExperimental behavioral evaluator. Drives a running artifact via browser/curl/CLI and records rubric evidence; the runner is not yet a fully implemented automated evaluation system.Votes: 0GitHub stars: 14
- Mk FigmaRead-first Figma gateway via Figma MCP: analyze designs, implement 1-3 screens, extract tokens, produce Evidence Packet. Advanced ops gated on explicit intent. Use for 'figma', 'design tokens'.Votes: 0GitHub stars: 14
- Mk FixDiagnoses and fixes bugs, type/lint errors, CI failures, and runtime errors, root-cause first. NOT for investigation without a fix (mk:investigate) or build-only compile errors (mk:build-fix).Votes: 0GitHub stars: 14
- Mk FreezeSession-scoped edit restriction: blocks Edit/Write outside an allowed path, to scope changes to one module or prevent unrelated fixes. NOT for blocking destructive shell commands (mk:careful).Votes: 0GitHub stars: 14
- Mk Frontend DesignUse when designing UI components, reviewing visual design, building design systems, or checking accessibility. Auto-activates on frontend design tasks and UI reviews.Votes: 0GitHub stars: 14
- Mk GhpmGitHub project management via gh CLI: issues, Projects v2 boards, labels, milestones, handoff summaries. NOT for code review (mk:review-pr), PR creation, or git ops (mk:resolving-merge-conflicts).Votes: 0GitHub stars: 14
- Mk GrillRelentlessly interview the user about THEIR plan, one question at a time, until shared understanding. Checkpoints answers so progress survives a reset. Do NOT use to propose solutions.Votes: 0GitHub stars: 14
- Mk HelpWorkflow navigator: scans project state (plans, reviews, tests, git) and recommends the next pipeline step. Use for 'what next?' or 'where am I?'. NOT for complexity routing (mk:scale-routing).Votes: 0GitHub stars: 14
- Mk HenshinConvert existing code into agent-consumable CLI/MCP server + companion skill. Use for 'agentize', 'expose as MCP', 'wrap as CLI'. NOT new code from scratch (mk:bootstrap) or review (mk:review).Votes: 0GitHub stars: 14
- Mk Html VideoRender an HTML/CSS/JS template to local MP4 via headless Chromium (Playwright) + ffmpeg. NOT live browser recording, screen recording, or AI video gen (mk:multimodal).Votes: 0GitHub stars: 14
- Mk Improve Codebase ArchitectureSurfaces architectural friction and proposes deepening refactors (shallow to deep modules). Renders via mk:preview. NOT for debate (mk:party); NOT for plan critique (mk:plan-ceo-review).Votes: 0GitHub stars: 14
- Mk IntakeTicket/PRD intake: product-area classification, completeness scoring, RCA, technical assessment. Works with Jira, Linear, GitHub, or manual paste. Use to analyze or triage a ticket.Votes: 0GitHub stars: 14
- Mk InvestigateSystematic root-cause debugging that produces a diagnostic report (mk:fix applies the fix; mk:build-fix owns compile failures). Use for 'debug this', 'why is this broken', 'root cause'.Votes: 0GitHub stars: 14
- Mk Jira AdminJIRA project/user/group/scheme/automation admin via jira-as. Requires admin role; destructive ops need 2-step confirm. NOT per-issue ops (mk:jira-issue/lifecycle) or JSM admin (mk:jira-jsm).Votes: 0GitHub stars: 14
- Mk Jira AgileJIRA agile via jira-as: epics, sprints, backlog, ranking, story points, velocity. Board ID != project key. NOT issue CRUD (mk:jira-issue) or time tracking (mk:jira-time).Votes: 0GitHub stars: 14
- Mk Jira AnalystRead-only full Jira ticket analysis incl. media + linked issues via jira-analyst agent; produces comment-ready findings. NOT complexity scoring (mk:jira-evaluator) or estimation (mk:jira-estimator).Votes: 0GitHub stars: 14
- Mk Jira BulkBulk JIRA ops (10+ issues): transition/assign/priority/clone/delete via jira-as; dry-run mandatory. NOT single-issue ops (mk:jira-issue, mk:jira-lifecycle).Votes: 0GitHub stars: 14
- Mk Jira CollaborateJIRA comments, attachments, watchers, notify via jira-as. Internal-vs-public comment safety enforced. NOT issue CRUD (mk:jira-issue) or issue links (mk:jira-relationships).Votes: 0GitHub stars: 14
- Mk Jira DevGenerate dev artifacts from Jira tickets via jira-as: branch names, PR descriptions, parsed commits, PR-to-issue links. NOT running git/gh (mk:ship) or issue CRUD (mk:jira-issue).Votes: 0GitHub stars: 14
- Mk Jira EstimatorHeuristic read-only story-point estimation for one Jira ticket via jira-estimator agent. NOT complexity analysis (mk:jira-evaluator) or full RCA (mk:jira-analyst).Votes: 0GitHub stars: 14
- Mk Jira EvaluatorEvaluate Jira ticket complexity and inconsistencies via jira-evaluator agent, read-only. NOT estimation (mk:jira-estimator) or full RCA (mk:jira-analyst).Votes: 0GitHub stars: 14
- Mk Jira FieldsJIRA custom field discovery + configuration via jira-as. Create/configure-agile need admin. NOT setting per-issue field values (mk:jira-issue update).Votes: 0GitHub stars: 14
- Mk Jira IssueJIRA issue CRUD via jira-as. NOT lifecycle (mk:jira-lifecycle), comments (mk:jira-collaborate), bulk (mk:jira-bulk), links (mk:jira-relationships), or time/sprint (mk:jira-time/agile).Votes: 0GitHub stars: 14
- Mk Jira JsmJIRA Service Management via jira-as: service desks, requests, customers, orgs, queues, SLAs, approvals. Requires JSM tenant + agent role. NOT core issue ops (mk:jira-issue) or admin (mk:jira-admin).Votes: 0GitHub stars: 14
- Mk Jira LifecycleDrive JIRA workflow lifecycle via jira-as: transition, assign, resolve, reopen, versions, components. NOT issue CRUD (mk:jira-issue) or bulk transitions (mk:jira-bulk).Votes: 0GitHub stars: 14
- Mk Jira OpsJIRA-side cache + project-context discovery via jira-as, diagnostic-only, no Atlassian state changes. NOT issue CRUD or project admin (mk:jira-admin).Votes: 0GitHub stars: 14
- Mk Jira RelationshipsManage JIRA issue relationships via jira-as: link, unlink, blockers, dependencies, clone, bulk-link. NOT sprint/epic relationships (mk:jira-agile).Votes: 0GitHub stars: 14
- Mk Jira SearchJIRA search + filter management via jira-as; JQL injection-safe. NOT single-issue CRUD (mk:jira-issue) or bulk writes (mk:jira-bulk).Votes: 0GitHub stars: 14
- Mk Jira TimeJIRA time tracking via jira-as: log work, worklogs, estimates, reports, bulk-log. Edit/delete confirms first (data loss). NOT sprint capacity (mk:jira-agile).Votes: 0GitHub stars: 14
- Mk JiraRouting skill — recommends the correct mk:jira-* leaf for any Jira task. Triggers: 'jira', 'jira ticket', ambiguous Jira intent. NOT an executor — every actual operation forks via a leaf skill.Votes: 0GitHub stars: 14
- Mk Lazy Agent LoaderDeprecated compatibility shim. Agent routing reads the canonical inventory under .codex/agents/ directly; do not use this skill for agent selection.Votes: 0GitHub stars: 14
- Mk Lint And ValidateLinting and static analysis after code edits. Triggers on lint, format, check, validate, types. NOT for full build verification (mk:verify) or test coverage (mk:testing).Votes: 0GitHub stars: 14
- Mk LlmsGenerate llms.txt files from project docs per the llmstxt.org spec, for AI-friendly documentation indexes and discoverability. Use to create or update llms.txt for AI assistants.Votes: 0GitHub stars: 14
- Mk LoopAutonomously improve one measurable metric via bounded, git-tracked iterations: one scoped change, verify, keep or revert. NOT for cleanup (mk:cook), known-cause bugs (mk:fix), or shipping (mk:ship).Votes: 0GitHub stars: 14