Recently Added
Fresh skills just added to the collection. Be the first to try them out!
test-driven-development
by yotamleo-org
Use when implementing any feature or bugfix, before writing implementation code
systematic-debugging
by yotamleo-org
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
subagent-driven-development
by yotamleo-org
Use when executing implementation plans with independent tasks in the current session
requesting-code-review
by yotamleo-org
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
grilling
by yotamleo-org
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
executing-plans
by yotamleo-org
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available
context7-mcp
by yotamleo-org
Use when the user names a library, framework or API (React, Prisma, Supabase…) — fetch its current docs via Context7.
brainstorming
by yotamleo-org
"You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation)."
i-have-adhd
by yotamleo-org
'Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".'
bwrap_sandbox
by soliplex
Run shell commands and Python in a sandbox, to compute results from files rather than estimating them, with read-only access to uploaded files and a working directory to write to.
stanzas
by soliplex
Answer questions about a poem: quote a stanza or section verbatim, count stanzas or lines, list sections, find which stanza mentions a word, explain what a stanza says, name the verse form, or report the poet and year. Use it whenever a question involves poetry, a poem, a poet, a verse, a stanza, a canto, or a fit. It works on a poem pasted into the conversation, and on a small bundled anthology of well-known poems: ask what it holds, or name a poem and it will say whether it has it. It quotes and analyses existing poems; it does not write new ones.
soliplex-docs
by soliplex
"Soliplex documentation: how to install, configure, run, and use Soliplex -- a self-hosted RAG/AI system with a FastAPI backend, Flutter client, and terminal UI. Covers configuration (rooms, agents, completions, RAG, OIDC, skills, quizzes, AG-UI features), server setup and CLI, environment variables, secrets, Docker deployment, RAG database setup, and client usage. Use when answering questions about installing, configuring, operating, or troubleshooting Soliplex."
task-ledger
by cq-guojia
本地任务台账，跨会话记录在办任务的归属、进度与起止。当用户要登记一件新的事（新建任务 / 建个坑 / 这活我领了）、记录已有任务的进展（接着做 / 记一条进展 / 这轮先记下）、查看任务状态或历史（现在该做什么 / 这活谁在做 / 上周做过什么）时加载；对某个具体任务要求结案或退回时，只认用户的明确指令；只是改代码、讨论方案时不要用。
spx-analysis
by johnnyhsu5509
標普500 (S&P 500 / SPX) 日線技術分析與回測驗證工具（合併版：一次完成回測+分析+建議）。 【觸發條件 — 指令必須指名 SPX 或 ES，未指名者不觸發】 每日例行（完整流程）：「分析SPX」、「分析今日SPX」、「SPX日報」、「分析標普」、「SPX日線分析」 單獨回測：「回測SPX」、「SPX命中了嗎」、「驗證昨日SPX推論」、「SPX預測準嗎」 快速確認（不產報告、純文字，任何視窗皆可）：「SPX期貨確認」、「ES確認」、「ES怎樣」、「SPX開盤確認」、「SPX睡前檢查」 本 SKILL 固定針對 S&P 500 指數（SPX），不分析其他標的。 【重要】並存的 ndx-analysis 為對等的另一套系統。裸指令（如未指名的「期貨確認」「開盤確認」 「睡前檢查」「分析行情」「今天市場怎樣」）一律不得預設觸發本 SKILL——必須先反問用戶 要 SPX 還是 NDX。靜默拿錯一套比報錯更危險。
ndx-analysis
by johnnyhsu5509
那斯達克100 (Nasdaq-100 / NDX) 日線技術分析與回測驗證工具（回測+分析+建議一次完成）。 【觸發條件 — 指令必須指名 NDX 或 NQ，未指名者不觸發】 每日例行（完整流程）：「分析NDX」、「分析今日NDX」、「分析那斯達克」、「NDX日報」、「NDX日線分析」 單獨回測：「回測NDX」、「NDX命中了嗎」、「驗證昨日NDX推論」、「NDX預測準嗎」 快速確認（不產報告、純文字）：「NDX期貨確認」、「NQ確認」、「NQ怎樣」、「NDX開盤確認」、「NDX睡前檢查」 本 SKILL 固定針對 Nasdaq-100 指數（NDX），不分析其他標的。 與 spx-analysis 為並列的兩套系統，不分主從，各自記帳、互不污染。 【重要】裸指令（如未指名的「期貨確認」「開盤確認」「睡前檢查」「分析行情」「今天市場怎樣」） 一律不得預設觸發本 SKILL——必須先反問用戶要 SPX 還是 NDX。靜默拿錯一套比報錯更危險。
ci-runner-health
by KingInYellows
Check self-hosted runner health via SSH, with deep runner diagnostics folded in. Use when the user asks for runner status, whether a runner is healthy, or wants to verify infrastructure before diagnosing CI failures.
ci-lint-workflows
by KingInYellows
Lint GitHub Actions workflows for self-hosted runner issues (W01-W14). Use when checking workflows before pushing or finding common CI pitfalls; previews and confirms before applying any fix.
ci-diagnose
by KingInYellows
Diagnose a CI failure now — fetch the failed run, redact and match its logs against the F01-F12 pattern library, and report root cause with fixes. Use when a GitHub Actions run has failed and you want its root cause and a fix now (for the reference workflow guide, use the diagnose-ci skill).
ci-conventions
by KingInYellows
Shared CI conventions reference (not an executable action) — validation rules, failure patterns (F01-F12), error catalog, and security patterns. Consult when agents or commands need CI-specific validation or pattern-matching reference.
stack-plan-style
by KingInYellows
Display guidance for presenting a stacked-PR plan — ordered branch tree with intent, commit type, and dependency notes. Use when gt-stack-plan presents a stack plan for user confirmation.
curl-bash
by yotamleo-org
Installs the helper toolchain needed by this skill.
luna-vitals-extract
by yotamleo-org
Use to backfill salus health series for one luna time-bucket — writes a per-bucket review artifact, never 50-Vitals/.
plan-status
by KingInYellows
'Show a per-file checkbox progress dashboard of plans/ (open) and plans/complete/ (archived) plan documents. Use when reviewing which plans are ready to archive or checking work-in-flight at a glance.'
optimize
by KingInYellows
"Run a metric-driven optimization pass: parallel candidate variants scored against an LLM-as-judge analytic rubric. Use when comparing approaches against a measurable goal — anywhere 'better' can be expressed as a per-criterion rubric. For session-level plan-adherence and scope-drift review, use /flow:review instead."