xingtu1996
UserAI Agent 技能聚合仓：29 个生产级 SKILL.md（跨工具 + DSH 兼容）｜29 production-grade AI agent skills, cross-tool & DeepSeek Harness compatible
Categories
Indexed Skills (30)
ponytail
Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use on ANY coding task: writing, adding, refactoring, fixing, reviewing, or designing code, and choosing libraries or dependencies. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", or complains about over-engineering, bloat, boilerplate, or unnecessary dependencies. Do NOT use for non-coding requests (general knowledge, prose, translation, summaries, recipes).
caveman-explore
Read-only repository explorer. Use PROACTIVELY for cold-start exploration, broad cross-file localization, or when a direct search has failed and you need to find where something lives. Skip it when the issue already names the exact file or symbol, or a previous turn already returned usable file:line evidence. Returns only compact path:line citations; its reads and greps never enter the main conversation.
cavecrew
Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use cavecrew", "spawn investigator/builder/reviewer", "save context", "compressed agent output".
caveman-commit
Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.
caveman-compress
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman-compress FILEPATH or "compress memory file"
caveman-discover
Find every LLM workflow in the current repository and label it, so Caveman Cloud groups spend by what the code actually does (support-reply, nightly-digest) instead of one anonymous bucket. Use when the user pastes the Caveman discovery prompt, says "discover workflows", or asks to break LLM spend down by workflow. The repo should already route through the Caveman gateway (the caveman-setup skill does that part).
caveman-evidence-review
Review Caveman Cloud evidence read-only: costs, Cave Score, Cave Plan, workflows, traces, latency, errors, compression, routing, and verified savings. Use when the user asks what Caveman found, where LLM spend goes, why cost or quality changed, which workflows need attention, or asks for a trace or analytics review. Prefer Caveman MCP tools; fall back to CLI JSON.
caveman-help
Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".
caveman-learn
Close the loop on a Caveman learn report — review the ranked token sinks and apply cost-lowering fixes (trim config, offload recurring context to cavemem) with per-edit consent. Use when the user runs "caveman learn", asks to lower their agent's token cost, wants to trim a heavy CLAUDE.md, or wants to offload context they re-paste every session into cavemem.
caveman-manage
Inspect Caveman Cloud's eval-gated experiment lifecycle and block unsafe execution. Use when the user asks to start, approve, cancel, promote, or roll back a Caveman experiment, or asks what action an experiment's evidence supports. Read evidence first; do not execute lifecycle mutations until server-authoritative transition and evidence gates ship.
caveman-optimize
Turn Caveman's exact report-only repository observations into an operator-chosen optimization candidate with a paired baseline/candidate evaluation. Use when the user asks to inspect an optimization observation, evaluate a candidate change, or act on the current Caveman optimization report. Require a logged-in Caveman CLI connection and explicit approval; never infer money or actuation from a profile.
caveman-review
Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.
caveman-setup
Wire the current repository through the Caveman Cloud gateway so every LLM request is measured — cost, tokens, latency — with zero behavior change. Use when the user pastes the Caveman setup prompt, says "set up caveman", or wants LLM spend observability added to an app. Requires the gateway URL and a Cave API key (the setup prompt carries both).
caveman
Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
ponytail-help
Quick-reference card for all ponytail modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /ponytail-help, "ponytail help", "what ponytail commands", "how do I use ponytail".
adversarial-review
行途自媒体"多专家对抗审查"技能（豆包工作优化版）。对公众号封面/标题/正文/数据/方案 做多角色交叉对抗审查，消除单视角盲区。支持怀疑论者/优化者/审计员/��滤器四角色并行， Round 2 脚本交叉验证（不用 LLM 法官），仅保留高置信度发现。 触发词：对抗审查、交叉审查、多视角审查、审文章、审标题、审封面、审查方案、数据核查。 依据：RULES.md PUB-017（多专家对抗审查）+ 行途内容工厂五关 + 原版 adversarial-review。 版本：豆包工作优化版 v1.0（2026-09-03）；原版归档 .backups/skills_原版归档_20260903/adversarial-review_原版_{tfm-ng,ctf-gitlab}
codemax-report
行途自媒体"数据核实 + 用量分析"技能（豆包工作优化版）。两大能力： ① cc-switch 本地库核实（~/.cc-switch/cc-switch.db）：核实文章数字——缓存命中率、 缓存读倍数、成本、Token 量级，防编造（对齐 PUB-018 脱敏 + "凭印象硬编是大忌"红线）。 ② CodeMax 平台汇报（保留原版 API 直拉能力）：用户/模型/项目/趋势 + 阶段对比 HTML + 模型切换观察。 触发：核实数字、数字对不对、缓存命中率、cc-switch 数据、token 账单、CodeMax 汇报、AI 用量分析、 模型对比、模型切换、TTFT、卡顿排查。 数据源：~/.cc-switch/cc-switch.db（本地 SQLite）+ CodeMax API（codemax_stats.sh）。 版本：豆包工作优化版 v1.0（2026-09-03）；原版归档 .backups/skills_原版归档_20260903/codemax-report_原版_{tfm-ng,ctf-gitlab}
de-ai-flavor
行途自媒体"去 AI 味"文案优化技能（豆包工作优化版）。把公众号文章、封面文案、 标题、摘要、小红书笔记、微信消息中 AI 腔/黑话/机械句式改成人话，保留技术准确性与关键数字。 触发：去 AI 味、改得自然点、别太 AI、像人话、黑话太多、措辞优化、润色文章、标题党去AI感。 适用：行途公众号「省 token」系列及一切对外内容——只要语言太"AI 味"。 依据：RULES.md PUB-013（去AI味5法）+ 行途成稿偏好速查 + SignalDistilled 哲学（数字第一语言）。 版本：豆包工作优化版 v1.0（2026-09-03）；���版归档 .backups/skills_原版归档_20260903/de-ai-flavor_原版_tfm-ng
caveman-stats
Show real token usage and estimated savings for the current session. Reads directly from the Claude Code session log — no AI estimation. Triggers on /caveman-stats. Output is injected by the mode-tracker hook; the model itself does not compute the numbers.
lean-build
Build feature work with high overbuilding risk. Use for new behavior, product slices, or integrations where repository reuse, strict scope, and an explicit stop condition matter.
migration
Implement reversible compatibility-safe transitions. Use for schema, data, API, protocol, configuration, or dependency migrations requiring rollback and preservation proof.
ponytail-audit
Whole-repo audit for over-engineering. Like ponytail-review, but scans the entire codebase instead of a diff: a ranked list of what to delete, simplify, or replace with stdlib/native equivalents. Use when the user says "audit this codebase", "audit for over-engineering", "what can I delete from this repo", "find bloat", "ponytail-audit", or "/ponytail-audit". One-shot report, does not apply fixes.
ponytail-debt
Harvest every `ponytail:` comment in the codebase into a debt ledger, so the deliberate shortcuts and deferrals ponytail leaves behind get tracked instead of rotting into "later means never". Use when the user says "ponytail debt", "/ponytail-debt", "what did ponytail defer", "list the shortcuts", "ponytail ledger", or "what did we mark to do later". One-shot report, changes nothing.
ponytail-gain
Show ponytail's measured impact as a compact scoreboard: less code, less cost, more speed, from the benchmark medians. One-shot display, not a persistent mode, and not a per-repo number. Trigger: /ponytail-gain, "ponytail gain", "what does ponytail save", "show ponytail impact", "ponytail scoreboard".
ponytail-review
Code review focused exclusively on over-engineering. Finds what to delete: reinvented standard library, unneeded dependencies, speculative abstractions, dead flexibility. One line per finding: location, what to cut, what replaces it. Use when the user says "review for over-engineering", "what can we delete", "is this over-engineered", "simplify review", or invokes /ponytail-review. Complements correctness-focused review, this one only hunts complexity.
safe-refactor
Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket structural edits.
fact-check-gate
行途成稿"事实核查门禁"技能。把文章/观点/数据/方案里的说法拆成可验证事实、推论、 价值判断三部分，联网核查事实并打五档标记（已证实/需收窄/争议/证据不足/明显错误）， 再查推理链漏洞，输出补强版与可信度结论——防 AI 幻觉、防编造第三方产品机制。 触发：事实核查、数字对不对、这个说法靠谱吗、核实数据、防编造、成稿前核查、 查证、这机制是真的吗、帮我把这段话核一遍。 依据：RULES.md PUB-018（脱敏+防编造红线）+ BCI B-009（编造第三方项目机制踩坑）+ xingtu-prompts/review/fact-check.md。 版本：v1.0（2026-09-11，豆包工作沉淀）。
investigate-first
Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-ranked hypotheses.
surgical-patch
Fix bugs and small behavior changes at the narrowest responsible layer. Use when regression proof, preserved surrounding behavior, and task-relevant tests matter.
verify-and-stop
Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and last-mile proof.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.