TypingMindTypingMindThe best frontend for AI
Skill Gap Analysis logo

Skill Gap Analysis

Organization
devcodex-labs
skill-gap-analysis

Skill 缺口与大语料分析 Owner — 当任务涉及项目/工作区产物扫描、能力盘点、缺少哪些 Skill、全量审查前规模判断、大目录分批、抽样深读、扫描恢复或自我进化候选发现时使用；要求先识别项目并形成规模决策，再进行有边界的证据扫描。

Overview

Publisherdevcodex-labs
Repositorydevcodex
Skill nameskill-gap-analysis
Stars
433
Forks
44
Bundled files
2
LicenseAGPL-3.0
Links
Skill sourceRepositoryHomepage
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by devcodex-labs on GitHub. Read the source before you install it.

Installation

Install the Skill Gap Analysis AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/devcodex-labs/devcodex/tree/main/content/skills/skill-gap-analysis
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/devcodex-labs/devcodex.git /tmp/devcodex
mkdir -p .claude/skills
cp -r /tmp/devcodex/content/skills/skill-gap-analysis .claude/skills/skill-gap-analysis
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Skill Gap Analysis in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Skill Gap Analysis on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Skill Gap Analysis is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Skill Gap Analysis

职责

在分析、审查或能力盘点前先判断目标项目和语料规模，再选择一次性、分批、抽样深读或阻断路线；完成扫描后，把领域信号与现有 Skill Owner、消费者和验证路线交叉去重，形成可复证的缺口决策。

ProjectArtifactScaleRoutingGate

任何 broad scan 前必须按顺序执行：

  1. 识别唯一 project / root / activeRoot；未识别时停止，不得扫描整个工作区。
  2. 只做 bounded inventory，显式排除 node_modules/dist/cache/tmp/backup/smoke/deploy mirror 等派生产物。
  3. 统计 relevantFileCount / parseableBytes / largestFileBytes / directoryConcentration / derivedArtifactRatio / consumerFanOut。
  4. 形成 ScaleDecisionRecord，再允许内容读取或递归检索。

WorkspaceRootScanHygiene（C16 / PI-20260724-01 · 范围与成本规则）

🔴 未绑定唯一项目前，禁止对 workspace/monorepo 根发起递归 inventory。项目路径已知时，禁止再从 workspace 根 -Recurse 查找。

禁止允许
Get-ChildItem <workspaceRoot> -Recurse（含 -Depth ≥1、按名 Filter 全树搜）list_dir 仅一层；Test-Path <workspaceRoot>/<project>
dir /s <workspaceRoot>、find <workspaceRoot> 无项目前缀在已绑定 project root 内有界 Recurse，且排除 node_modules/dist
为「找项目」扫整个 E:\Worker 等 monorepo 根用户 @path / 已知子目录名 / Profile inventory
inventory 展开 node_modules、文档站 doc_build、巨型 dist显式 -Exclude / 工具默认尊重 gitignore 的列表

机器探针：scripts/lib/host-parity-scorecard.js → classifyWorkspaceRootScanSample（workspace-root-recurse = 范围/成本缺陷）。Hook 侧对命中 workspace 根 + Recurse 的 shell 只发出 advisory；执行权限由宿主及其用户配置决定（见 lifecycle-dangerous-command）。

TimeToFirstValueGate（TTFV · 与 compliance/C16 联防）

非 chat 在入口检查与最小 ContextReadPlan 之后，同一用户可见回复必须至少交付其一，否则本轮视为扫描/准备违规：

  1. 可确认的半屏范围卡（路径/批次/排除项）；或
  2. 首批 finding / 分析结论 / 可执行方案要点；或
  3. 明确阻断（项目不明、权限、环境缺失）+ 恢复动作。

禁止：整轮只读 Skill 百科、只跑全库 inventory、或只写超长需求概括却零交付。用户明确「直接开审/跳过确认」时跳过范围确认，立即 B1 交付。

ProgressReportFastPath（PI-20260725-01 · TTFV 进度查询特化）

🔴 用户问「进度 / 发版到哪了 / 验证状态」且已点名项目时，禁止 workspace 根 inventory 与模糊 task 名阻塞首答。

步骤要求
绑定立即绑定 .devcodex/<project>/ 与源码目录；路径直达
真相源顺序① verification/issues/README（或问题总台账）② fixed-awaiting-rerun-classification（若有）③ profile 发布/项目检查点 ④ SUMMARY 近行 ⑤ 仅不足时再读 05-实施进度/报告
首轮交付需求定位 → 进度数字表 → 当前阻断 → 一句话结论
失败同 TTFV 违约；探针 classifyProgressReportFastPathSample → progress-fail

机器探针：scripts/lib/executable-absorption-gates.js → classifyProgressReportFastPathSample；npm run test:executable-absorption-gates。

decision默认判定执行
single-pass全部满足 ≤50 files、≤2 MiB、largest≤256 KiB、fan-out≤10，且用户未提示大目录一次处理，仍保留排除策略
batched任一中等规模、fan-out>10、控制面联动或用户提示目录大按 namespace/目录/文件预算分批，逐批写 checkpoint
sampled+deep-read>500 files、>20 MiB、derived ratio>30% 或目录极端集中全量 inventory + 强语义检索 + 代表文件深读；禁止声称逐字全读
blocked项目/root 不唯一、排除边界不可信、权限/文件系统错误停止 broad scan，先恢复边界

项目 Profile 可以配置更保守阈值，不得放宽上述默认边界；用户明确“大目录/文件很多”时不得降为 single-pass。

ScaleDecisionRecord

至少记录：project、root、activeRoot、inventoryCommand、六项规模指标、decision、reason、exclusionPolicy、batchBudget、checkpointPath、timeoutRetry、invalidRunPolicy。

  • 非 single-pass 缺 checkpointPath 或 batch budget 时不得继续。
  • timeout、错误 glob、派生产物污染或无法解释的数量跳变必须标记 invalid/discarded，不能进入结论。
  • 检查点状态使用 not-started / running / accepted / invalid / blocked；恢复只从最后一个 accepted 批次继续。

Skill 缺口分析流程

  1. 生成 WorkspaceCorpusManifest 与 ExclusionPolicy。
  2. 按规模决策执行 BatchEvidenceLedger，每批记录输入、命令、文件数、有效信号和异常。
  3. 宽口径召回后执行强语义复扫、词边界校准、代表文件深读和历史镜像降权。
  4. 建立 ExistingSkillCoverageMatrix：候选 → 最接近 Owner → 未闭合边界 → current consumer → validation。
  5. 执行 CommonNormGeneralizationGate 与消费者证明；项目局部信号标为 project-local / case-evidence-only。
  6. 为每个真正缺口冻结 trigger、ownedArtifacts、consumerSync、validationRoute 和负向样例。
  7. 至少完成两轮维度不同的 omission-only 零新增，写入 ConvergenceRecord。

输出产物

先归因，再选择能力载体

在原CapabilityGapDecision前，为每个候选记录 cause / evidence / recoveryAction / reassessment / dispositionRef。原因按事实可多选；缺证据时保持undetermined，不以关键词或希望新增的Skill名称反推原因。

cause证据与下一步
existing-not-discovered已有Owner/契约存在但未发现：恢复检索与定位，重新评估残余
existing-not-triggered已定位且适用但未触发：检查原意图/路由消费，恢复触发后重评
existing-not-loaded已触发但内容未实际加载：核对加载回执、摘要和降级，补加载后重评
rule-gap已有Owner实际缺少必要约束：补原Owner残余，交spec-absorption供证
expertise-gap规则存在但缺专业判断/证据：补专业资料或适用能力，不用新规则代替专业判断
tool-environment-gap工具、权限或环境缺失/失败：按宿主边界恢复环境并复证，不能默认重装
undetermined证据不足或冲突：列待证事实与下一合法核验，暂不裁定缺规则

前三种先恢复已有能力并重新观察，不能直接转new-skill或把正文再吸纳一遍。原因不是原有new-skill / existing-subgate / docs-only / reject落点的替代枚举；dispositionRef连接恢复重评后的原决定。spec-absorption消费此记录及实际source证据，只吸纳经重评仍成立的rule-gap。

产物必填内容
WorkspaceCorpusManifestnamespace、路径类型、文件/字节、派生边界
ScaleDecisionRecord规模指标、四态决策、预算与理由
BatchEvidenceLedger批次、checkpoint、命令、状态、invalid-run
ExistingSkillCoverageMatrix候选与现有 Owner 的覆盖/重叠/缺口
CapabilityGapDecisionnew-skill / existing-subgate / docs-only / reject
ConvergenceRecord每轮维度增量、新增数、连续零新增

所有覆盖结论同时执行 audit-common 的 ReviewCoverageClaimIntegrityGate。WorkspaceCorpusManifest 只能证明 inventory-covered；关键词检索只能证明 machine-scanned；代表文件深读必须明确 sampledSet/unreadSet/inferenceBoundary。只有逐文件 FileEvidenceLedger 才能声明逐字全读。

与 incremental-project-analysis 分界

本 Skillincremental-project-analysis
规模路由、corpus inventory、Skill 缺口 vs Owner知识快照、digest 失效、BatchProgress 强制交付、GlobalBacklog、精度合同、双层验证
「怎么分批扫、缺什么能力」「扫完的事实如何复用、如何对用户分批交付与综合」

batched / sampled+deep-read 的 analyze 路径在形成 ScaleDecision 后应同时调用 incremental-project-analysis 的交付与精度门禁；本 Skill 不把快照状态机整坨并入。

反模式

  • 未识别项目就从 workspace root 递归扫描。
  • 项目名已知仍对 monorepo 根 Get-ChildItem -Recurse -Depth N 找目录（PI-20260724-01 复发样例）。
  • 先全量扫描超时，再补写“应该分批”。
  • 把备份、安装包、浏览器 Profile、translation cache 或 lockfile 当能力证据。
  • 只按关键词计数，不读代表样本、不反查现有 Skill。
  • 用抽样深读结果宣称“逐字审查所有文件”。
  • 同一批次失败后继续沿用部分输出，或用后续成功命令覆盖前序失败。
  • 做完分批扫描却不调用 incremental Skill，导致无 ProgressCard / 无快照 / 假完整主题清单。
  • 首轮用户可见回复只有流程/Skill 预热、无范围卡/finding/阻断（TTFV 失败）。

验证

至少包含：小项目 single-pass 正向、用户大目录强制 batched、>500 文件 sampled+deep-read、unresolved project blocked、错误 OR glob、派生污染、timeout 无 checkpoint、历史 already-fixed 未去重等正负向样例。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Skill Gap Analysis AI skill do?

Skill 缺口与大语料分析 Owner — 当任务涉及项目/工作区产物扫描、能力盘点、缺少哪些 Skill、全量审查前规模判断、大目录分批、抽样深读、扫描恢复或自我进化候选发现时使用；要求先识别项目并形成规模决策，再进行有边界的证据扫描。

Why use Skill Gap Analysis on TypingMind?

Because you install it once and use it with any model. Skill Gap Analysis is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Skill Gap Analysis in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/devcodex-labs/devcodex/tree/main/content/skills/skill-gap-analysis. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Skill Gap Analysis?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Skill Gap Analysis?

As many as you like. As long as a model supports skills, you can use Skill Gap Analysis with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Skill Gap Analysis AI skill free?

Yes. It is published on GitHub by devcodex-labs under the AGPL-3.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
NousResearch logo

Pinecone

NousResearch
OrganizationPopular

Managed vector DB for production RAG and search.

53.5K
250.4K
1 files
View
NousResearch logo

Qdrant

NousResearch
OrganizationPopular

Vector search engine for production RAG systems.

53.5K
250.4K
2 files
View
NousResearch logo

Tensorrt Llm

NousResearch
OrganizationPopular

High-throughput LLM inference on NVIDIA GPUs.

53.5K
250.4K
3 files
View
anthropics logo

Internal Comms

anthropics
OrganizationPopular

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal…

21.8K
184K
4 files
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇