SKILLS & AGENTS/Skill 与 Agent·CLAUDE-SKILL

abvx-agent-skills

markoblogo/abvx-agent-skills

中文简介生成中Reviewable capability layer for coding agents: portable skills, workflow patterns, verification gates, token-efficient execution, and bounded agent loops.

打开仓库Open repository 官网Homepage

怎么装：Install: npx skills add markoblogo/decision-map --skill decision-map

02 / 现在的位置02 / Why now

它现在处在什么位置Where it stands right now

首次发现FIRST SEEN

03 OCT 202603 OCT 2026

增长GROWTH

历史不足Not enough history

只有 1 个快照，还不足以计算增长Only 1 snapshots so far — not enough to compute growth

讨论DISCUSSION

暂无None

还没有采集到外部讨论No external discussion collected yet

状态STATUS

持续活跃Active

03 / 它能帮你做什么03 / What it helps you do

它能帮你做成什么What it helps you do

中文能力说明生成中Chinese capability copy is being generated

05 / 安装05 / Install

怎么装How to install

SKILLS-CLI

$

README 里给出的安装方式。The installation method given in the README.

MCP CONFIG

$

MCP 客户端配置，粘贴到对应的配置文件里即可。An MCP client config — paste it into the relevant config file.

两种装法选一个即可 —— 上面那条给命令行用户，下面那条给写代码的用户。Pick one of the two — the first is for command-line users, the second for people writing code.

06 / 限制与风险06 / Limits and risk

限制与风险Limits and risk

风险不是警告，是可信度的一部分。以下结论只基于文档静态扫描，我们不会执行项目里的任何代码。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.

限制LIMITS

需检查Needs review

01需要 API KeyREQUIRES API KEY: 未在文档中发现Not found in the docs
02需要本地环境NEEDS LOCAL RUNTIME: 是Yes
03需要 DockerNEEDS DOCKER: 未在文档中发现Not found in the docs
04难度DIFFICULTY: 需要本地环境Needs a local runtime

PROVENANCE · 这些结论的依据是什么Where these conclusions come from

来源 URLSource URL: https://github.com/markoblogo/abvx-agent-skills
原始数据哈希Raw data hash: 13d3103f9f8d7bfc9f77fb40df601484
解析时间Parsed at: 2026-10-03T11:07:12.014Z
最后一次验证Last verified: 2026-10-03T10:31:51.693Z
增长测量时间Growth measured: —
发现查询Discovery queries: focus:token:code:save-tokens
分类来源Category source: rules
焦点Focus: token (7)

完整解析证据 JSONFull parse evidence JSON

{
  "agents": [
    {
      "agent": "claude-code",
      "evidence": "readme: …*Solo dev in Codex / Cursor / Claude Code / Gemini CLI:** use [docs/sol…"
    },
    {
      "agent": "gemini-cli",
      "evidence": "readme: …odex / Cursor / Claude Code / Gemini CLI:** use [docs/solo-dev-quickst…"
    }
  ],
  "apiKey": null,
  "docker": null,
  "taxonomy": {
    "scores": {
      "design": 0,
      "ai-tools": 1,
      "dev-tools": 5,
      "indie-web": 0,
      "skill-agent": 13,
      "productivity": 0
    },
    "primary": "skill-agent",
    "secondary": "claude-skill"
  },
  "localRuntime": "INSPO_MAX_TOKENS=8000`. Inspo runs locally over stdio without telemetry, but it do",
  "skillMdTotal": 88,
  "skillMdErrors": [],
  "treeTruncated": false,
  "categoryScores": {
    "data": 0,
    "agent": 0,
    "media": 0,
    "design": 0,
    "browser": 0,
    "devtool": 5,
    "security": 1,
    "marketing": 0,
    "productivity": 0
  },
  "classification": [
    {
      "signal": "60 SKILL.md with name + description",
      "weight": 0.95
    },
    {
      "signal": "skills/ directory with 182 markdown files",
      "weight": 0.75
    },
    {
      "signal": "README describes a Claude / Agent Skill",
      "weight": 0.7
    },
    {
      "signal": "name contains 'skill'",
      "weight": 0.4
    },
    {
      "signal": "description mentions AI",
      "weight": 0.2
    }
  ],
  "scannedSources": [
    "readme",
    "skills/agent-friction-ledger/SKILL.md",
    "skills/agent-learning-layer-triage/SKILL.md",
    "skills/agent-operations-contract/SKILL.md",
    "skills/agent-tool-contract-review/SKILL.md",
    "skills/agents-best-practices/SKILL.md",
    "skills/anti-slop-review/SKILL.md",
    "skills/architecture-deepening-review/SKILL.md",
    "skills/assumption-excavation/SKILL.md",
    "skills/authorized-security-router/SKILL.md",
    "skills/book-to-skill/SKILL.md",
    "skills/bounded-evaluation/SKILL.md",
    "skills/bounded-growth-loop/SKILL.md",
    "skills/bounded-orchestration-contract/SKILL.md",
    "skills/brief-first-execution/SKILL.md",
    "skills/browser-verification/SKILL.md",
    "skills/bug-evidence-protocol/SKILL.md",
    "skills/compaction-survival/SKILL.md",
    "skills/complexity-optimizer/SKILL.md",
    "skills/confidence-fragility-review/SKILL.md",
    "skills/context-degradation-review/SKILL.md",
    "skills/corporate-surface/SKILL.md",
    "skills/delivery-baseline-audit/SKILL.md",
    "skills/delivery-preflight-gate/SKILL.md",
    "skills/design-critique-polish/SKILL.md",
    "skills/design-register-bootstrap/SKILL.md",
    "skills/designmd-brand-kit/SKILL.md",
    "skills/diagnose/SKILL.md",
    "skills/doc-grounded-grilling/SKILL.md",
    "skills/doc-to-lora-evaluator/SKILL.md",
    "skills/durable-context-maintenance/SKILL.md",
    "skills/dynamic-workflow-packets/SKILL.md",
    "skills/editorial-surface/SKILL.md",
    "skills/evidence-ledger-research/SKILL.md",
    "skills/filesystem-context-discipline/SKILL.md",
    "skills/fluid-interaction-review/SKILL.md",
    "skills/frontend-product-builder/SKILL.md",
    "skills/frontend-taste-layer/SKILL.md",
    "skills/git-native-context-contract/SKILL.md",
    "skills/goal-loop-designer/SKILL.md",
    "skills/graph-guided-code-reading/SKILL.md",
    "skills/handoff/SKILL.md",
    "skills/happy-handoff/SKILL.md",
    "skills/html-brief-artifact/SKILL.md",
    "skills/html-diagram-artifact/SKILL.md",
    "skills/hypothesis-diversification/SKILL.md",
    "skills/idea-to-ship-gates/SKILL.md",
    "skills/knowledge-base-enrichment/SKILL.md",
    "skills/lean-context-layout/SKILL.md",
    "skills/local-inference-tuning/SKILL.md",
    "skills/loop-hardening-contract/SKILL.md",
    "skills/loop-readiness-review/SKILL.md",
    "skills/loopops-protocol/SKILL.md",
    "skills/lottie-motion-builder/SKILL.md",
    "skills/minimal-diff-builder/SKILL.md",
    "skills/motion-review-gate/SKILL.md",
    "skills/overengineering-review/SKILL.md",
    "skills/personal-workspace-router/SKILL.md",
    "skills/phase-spec-execution/SKILL.md",
    "skills/pipeline-readiness-gate/SKILL.md",
    "skills/plan-to-issues/SKILL.md"
  ],
  "skillMdFetched": 60
}