Create high-engagement X thread sequences. Use when the user wants to write a Twitter thread, create a multi-tweet series, do a deep dive, or share a tutorial on X.
Generate tests for a completed phase based on Evidence Review criteria and implementation
Post-mortem investigation for failed THRUNT workflows — analyzes git history, artifacts, and state to diagnose what went wrong
Generate a comprehensive project summary from milestone artifacts for team onboarding and review — from 3dcom2711/thrunt-god
Capture a forward-looking idea with trigger conditions — surfaces automatically at the right milestone — from 3dcom2711/thrunt-god
Create a clean PR branch by filtering out .planning/ commits — ready for code review — from 3dcom2711/thrunt-god
Execute a quick task with THRUNT guarantees (atomic commits, state tracking) but skip optional agents
Draft a new plan-scoped ticket from the avanti template into project/tickets/open/
End-to-end ticket workflow -- from ticket analysis through investigation, planning, TDD implementation, committing, and PR creation.
This skill should be used when the user asks to "check ticket", "update issue", "close ticket", "create issue", "list tickets", "move ticket to in-progress", "fetch issue…
Adversarially review a ticket plan against the repo and write a verdict file. Usage: /ticket-plan-review docs/tickets/plans/TP-XXXX-plan.md
Author or refine a ticket implementation plan in a file, verifying against the real repo. Usage: /ticket-plan-start docs/tickets/plans/TP-XXXX-plan.md
One repeatable pass that decides whether a GitHub ticket is a single dispatchable unit of agent work — or names exactly which of the six scope axes it fails and how to fix it.
Triage and prioritize a support ticket or customer issue. Use when a new ticket comes in and needs categorization, assigning P1-P4 priority, deciding which team should handle it,…
Use after implementation to run tier-classified review agents and produce a consolidated verdict.
TigerBeetle coding style for safety-critical Zig code. Use for writing new code aligned with TigerStyle, or analyzing existing code to produce structured reports showing aligned…
Tighten prose against a rule catalog: cut needless words, restore buried verbs and the active voice, and give paragraphs a spine.
Compile a TikZ diagram, rasterize it to PNG with ghostscript, have the tikz-reviewer subagent actually look at the image, apply the surgical fixes it returns, and repeat until…
Full release process for the tim CLI tool. Use this skill whenever the user wants to release, deploy, publish, or cut a new version of tim.
Add a time entry manually — for work done outside a Claude Code session, corrections, or entries not captured by the billing panel.
estimate CC active time for a task using the time rule, with dynamic effort resolution
Summarize recent git work for time registration. Use when the user asks what they worked on, needs a time log, wants a work summary, asks about today's/yesterday's/last week's…
Diagnose and repair the documented autoloop bootstrap failure modes for a registered loop. Idempotent.
Adopt extracted helpers — find dead symbols from forge, wire them into consumers, replace duplicated inline patterns, and gate on dead-symbol delta (Titan Paradigm Phase 4.5)
Clean up all Titan Paradigm artifacts and snapshots, restoring the codebase to pre-Titan state
Run the full Titan Paradigm pipeline end-to-end by dispatching each phase to sub-agents with fresh context windows.
Connect TikTok ads and organic data to Claude over MCP. Detects which data planes are reachable, distinguishes a missing MCP server from an empty one, walks through setup with the…
Generate plain-text TLDR for PRs (for Slack, copied to clipboard). Each entry includes change scope (+N/-M lines, K files), a 1-5 star review-effort rating (time to review) and a…
Use only when explicitly asked to archive/prune/compact/roll over checked tasks from TODO.md into `.ai/todos/TODO_UNTIL_YYYY_MM_DD.md`, leaving unchecked tasks.
Use when batch-resolving approved todos, especially after code review or triage sessions
Use when reviewing pending todos for approval, prioritizing code review findings, or interactively categorizing work items
Track team deadlines, action items, and TODOs via the knowledge base. Can list current items, add new ones, mark items complete, and show upcoming deadlines.
Use when the user says "toggl", "timesheet", "time tracking", "what did I do today/yesterday", or supplies a date for daily timeline reconstruction.
Turn the opt-in contradiction detector on or off. It is off by default and, when on, uses your own API key or a local model — this plugin never bills you.
Search and install AI assets from TokRepo — the open registry for skills, prompts, MCP configs, scripts, and workflows.
Discovers your full tool environment and amplifies prompts with capability awareness. Suggests optimal tool compositions as non-binding options.
Set up and manage VitePress documentation site with Mermaid diagram support. Use when the user says "render the docs", "start the docs site", "build documentation", "preview…
Operate toolbox with deterministic checks: health -> execute -> truth-xval on failure -> machine-readable status.
Build and maintain a simplified spec-to-proof documentation set for Creusot by extracting properties from component specs, tracking assumptions/trusted boundaries, and generating…
Updates the local TopGun installation to the latest release from GitHub. Invoke when the user says "update topgun", "upgrade topgun", "topgun update", "check for topgun updates",…
Scaffold, read, and audit subsystem topology entries — pointer-only yaml linking each subsystem's canonical code, decision record, operational doc, and test surface.
Recovery strategy when the Write tool fails to create a new file. Use this skill whenever a Write or Edit tool call fails with an error related to creating a new file — such as…
Finds every file and location affected by a GitHub issue change. Use when scoping an issue, finding blast radius, or answering "what does this touch".
The repository-evaluation lens: judge whether a repo is worth your time in a few minutes — by SCANNING its dashboards, not reading its code — scoring three axes: ALIVE, HEALTHY,…
Author Typst slide decks with the Touying package. Use when creating or editing .typ presentations: applying or building Touying themes (metropolis, dewdrop, aqua, stargazer,…
Launch the interactive TUI to browse, search, and navigate the conversation. Use when the user wants to search through what was said, browse tool calls, or explore the session…
Set up turbo-plugin-git-svn (the git<->SVN bridge). Run on explicit request; you may SUGGEST it when `.turbo-plugin/` is missing, but **do NOT auto-trigger**.
Answer a question about money that already moved in Stripe — why a charge failed, what a customer was billed, where an invoice or payout stands — by reading the object chain…
Use when a feature crosses system boundaries and integration risk is high. Implements the thinnest end-to-end path first, then widens pass by pass — always working.
Decompose spec into vertical end-to-end slices, each committable. Use in stage 6 (Tasks). Triggers "tracer bullet", "vertical slice", "smallest commits", or when a plan reads as…
Tracing & incident analyzer: traces why a feature doesn't work after deploy, locates the root cause in code across all layers (frontend → API → backend → DB), generates PlantUML…
Generates actionable trade strategies with entry, exit, stop-loss, and position sizing
商标侵权认定评估——判断当事人行为是否构成商标侵权。 评估混淆可能性（售后混淆/直接混淆）、正当使用抗辩（描述性使用/指示性使用）、平行进口合法性。 输出：侵权认定结论 + 维权路径建议 + 升级决策。
Run a historical backtest using npx neural-trader with Rust/NAPI engine (8-19x faster) and walk-forward validation
Run a heavy neural-trader job (long walk-forward, big Monte-Carlo, parameter sweep, model training) on the Anthropic Managed Agent cloud runtime instead of locally
Regulator-grade feature attribution for any LSTM/Transformer signal — single-entry PageRank ranks the top-K features that drove the prediction (ADR-126 Phase 6, ADR-123…
Optimize portfolio allocation using npx neural-trader mean-variance engine with risk constraints and rebalancing plan
Mean-variance portfolio optimization via Conjugate Gradient — 40-60× faster than the legacy Neumann path (ADR-126 Phase 3, ADR-123 Wedge 8)
Detect current market regime using npx neural-trader — bull/bear/ranging/volatile classification with recommended strategy
Assess portfolio risk using npx neural-trader — VaR, CVaR, Sharpe, position sizing, circuit breaker status