Instruccions per a IA
Disseny d’instruccions i plantilles per a models d’IA
debug-codex-session
weave-os
Investigate a specific Codex CLI session by session ID — correlate the local rollout transcript (~/.codex/sessions/YYYY/MM/DD/rollout-*-<SESSION_ID>.jsonl) with the router's production logs to understand what Codex rendered vs. what the upstream served on the /v1/responses path. Use when given a session ID and asked "why did X render?" (missing thinking, missing routing marker, wrong model, tool-call weirdness) for a Codex conversation routed through the router.
test-codex-locally
weave-os
Run the Weave router locally in docker compose and drive it with codex exec to reproduce and verify routing/translation/marker behavior for Codex's Responses API path. Use when verifying a router fix end-to-end for Codex, reproducing a prod Codex routing bug, confirming routing-marker / force-model / subscription-passthrough behavior, or testing a /force-model route — without touching the user's global Codex config.
debug-claude-session
weave-os
Investigate a specific Claude Code session by session ID — correlate the local transcript (~/.claude/projects/...jsonl) with the router's production logs to understand what the client rendered vs. what the upstream served. Use when given a session ID and asked "why did X render?" for a Claude Code conversation routed through the router.
Cancel Auto Command
anton-abyzov
EMERGENCY ONLY - Cancel running auto session and generate summary report.
SpecWeave Framework Expert
anton-abyzov
SpecWeave framework expert for structure, rules, spec-driven conventions. Use for SpecWeave best practices, increment lifecycle, hooks, tasks.md/spec.md, living docs sync.
Ultrathink LLM-as-Judge Validation
anton-abyzov
Ultrathink LLM-as-Judge validation of completed work. Uses extended thinking and Opus model for thorough, independent evaluation. Use when saying "judge my code", "judge-llm", "deep validate", or as part of /sw:done closure.
TDD Red Phase - Write Failing Tests
anton-abyzov
Write failing tests that define expected behavior. Use when saying "TDD red", "write failing tests", or "test first".
Close Increment (PM Validated)
anton-abyzov
Close increment with PM 3-gate validation (tasks, tests, docs). Use when all tasks complete and saying "close increment", "we're done", or "finish up".
openai-security-threat-model
trailofbits
Repository-grounded threat modeling that enumerates trust boundaries, assets, attacker capabilities,
github-research
romiluz13
"Internal skill. Use cc10x-router for all development tasks."
Increment Progress
anton-abyzov
Show progress for active increments with task/AC completion. Use when saying "show progress", "status", or "how far along".
Background Jobs Monitor
anton-abyzov
View and manage background jobs (cloning, imports, living-docs). Shows job status, progress, and logs. Use when saying "check jobs", "job status", or "background tasks".
Doctor - Installation Health Scanner
anton-abyzov
Run installation health diagnostics - detect ghost commands, stale cache, hash mismatches, and namespace pollution. Use when saying "doctor", "health check", "diagnose installation", or "check installation".
TDD Green Phase - Make Tests Pass
anton-abyzov
Write minimal code to make failing tests pass. Use when saying "TDD green", "make tests pass", or "implement for tests".
bpmn-generator
Stieges
Enterprise BPMN 2.0 diagram generator — converts natural language process descriptions into OMG-compliant BPMN 2.0 XML files and SVG previews via a 4-phase pipeline: Intent Extraction (LLM → JSON Logic-Core) → Validation (deadlock detection, structural soundness) → ElkJS Auto-Layout → BPMN XML + SVG output. Supports: multi-pool collaborations, message flows, boundary events (timer/error/signal), loop/multi-instance markers, data objects, all gateway types with correct gatewayDirection, and all BPMN 2.0 task types. Use this skill whenever the user wants to create, generate, or model a BPMN diagram, process flow, or workflow — even if they say "draw a process", "model this workflow", "make a BPMN for...", "create a Prozessmodell", "visualize this process", or describe a business process in natural language. Also use for editing or extending existing BPMN Logic-Core JSON.
ask-council
doodledood
Multi-model ensemble consultation. Runs 3 models in parallel for diverse perspectives.
seedance
songguoxs
This skill should be used when the user asks to "generate video prompts", "create Seedance prompts", "write video descriptions", mentions "Seedance", "seedance", "即梦", "即梦平台", "视频提示词", "视频生成", "AI视频", "短剧", "广告视频", "视频延长", or discusses video prompt engineering, AI video generation, or Seedance 2.0 workflows.
unicon-mcp
webrenew
Help users connect the Unicon MCP server to Claude Desktop, Cursor, and other MCP clients. Use when setting up MCP config, verifying installs, debugging MCP connection issues, or using Unicon tools for icon search and generation through AI assistants.
intelligent-prompt-generator
huangserva
智能提示词生成器 v2.0 - 支持人像/跨domain/设计三种模式，语义理解、常识推理、一致性检查
speckit-constitution
dceoy
Create or update the project constitution from interactive or provided principle inputs, ensuring all dependent templates stay in sync.
install-skill-tracker
vishalsachdev
This skill installs a complete Claude Code skill tracking system using hooks to automatically log skill usage, execution duration, token usage, and user prompts for later analysis. Use this skill when setting up activity tracking in a Claude Code project to identify patterns, monitor costs, and discover opportunities for new skills.
plugin-help
wasp-lang
Shows the Wasp plugin's available features, commands, and skills.
typst
lucifer1004
"Typst document creation and package development. Use when: (1) Working with .typ files, (2) User mentions typst, typst.toml, or typst-cli, (3) Creating or using Typst packages, (4) Developing document templates, (5) Converting Markdown/LaTeX to Typst"
pj-init
ssiumha
Initializes multi-repo workspace CLAUDE.md. Use when managing multiple repositories as a single project.