technical-skill-finder

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Technical Skill Finder

技术技能发现工具

Purpose

用途

Find recurring pain points from local agent logs and convert them into actionable skill candidates, reuse opportunities, or existing skill updates.

从本地Agent日志中找出反复出现的痛点，并将其转化为可落地的候选技能、复用机会或现有技能更新方案。

When to use

使用场景

You want to discover missing technical skills from historical agent activity.
You want reproducible criteria before creating a new skill.
You want to validate whether an existing skill already covers the pattern.
You want to include optional personal-signal sources (when authorized).

你希望从历史Agent活动中发现缺失的技术技能
你希望在创建新技能前拥有可复现的判定标准
你希望验证现有技能是否已覆盖相关模式
你希望纳入可选的个人信号源（需获得授权）

Inputs

输入参数

```
SCOPE
```
(required): repository paths, workspace, or tool domains to inspect.
```
SOURCES
```
(required): ordered source list to mine.
```
TIMEFRAME
```
(optional): default
```
all
```
unless constrained by user.
```
PRIVACY_POLICY
```
(required): explicit user direction for personal logs.
```
TOP_N
```
(optional): number of highest-priority candidates to return.

```
SCOPE
```
（必填）：要检查的仓库路径、工作区或工具领域
```
SOURCES
```
（必填）：要挖掘的源列表（按顺序排列）
```
TIMEFRAME
```
（可选）：默认值为
```
all
```
，可由用户指定范围
```
PRIVACY_POLICY
```
（必填）：用户针对个人日志的明确指示
```
TOP_N
```
（可选）：要返回的最高优先级候选技能数量

Workflow

工作流程

Initialize source set
- ```
~/.codex/history.jsonl
```
- ```
~/.codex/archived_sessions/*.jsonl
```
- ```
~/.codex/sessions/*.jsonl
```
  and
```
~/.codex/log/*
```
  if present
- Repository-specific telemetry in
```
AGENTS.md
```
  /local docs when available
- ```
Cursor
```
  /
```
Codex
```
  agent logs detected under known dotfiles directories
Normalize extraction signals
- Parse stack traces and classify failure type (
```
auth
```
  ,
```
type-check
```
  ,
```
llm-error
```
  ,
```
git/ci
```
  ,
```
runtime
```
  ,
```
refactor-merge
```
  ,
```
test
```
  )
- Parse recurring command phrases (
```
rg
```
  ,
```
mypy
```
  ,
```
pytest
```
  ,
```
gh
```
  ,
```
git
```
  , package-manager failures)
- Record frequency, recency, and affected project context
Cluster signals
- Group by: domain (python/js/rust/docs/tooling), command lineage, and error signature.
- Deprioritize one-off sessions with low recurrence.
Map to existing skills
- Compare candidate clusters with available skills by
```
name
```
  and
```
description
```
  .
- If overlap is high, propose skill update path.
- If no overlap, propose new skill.
Emit ranking output
- Provide
```
impact
```
  ,
```
frequency
```
  ,
```
confidence
```
  ,
```
skill-fit
```
  , and first-apply command set.
Produce minimal first-iteration artifacts for high-priority candidates
- Candidate title + scope
- Trigger phrase examples
- Required inputs
- Suggested workflow summary
- Evidence snippets (line/file-level)
- Suggested dependencies/tools (e.g.,
```
jq
```
  ,
```
rg
```
  , shell utilities, MCP resources)
Optional extension to personal-signal sources
- Only after explicit approval to read personal channels.
- If MCP is available and user has granted access, run MCP resource discovery and include message-signal-derived patterns.
- Keep this opt-in and isolated from coding-signal output unless user requests a merged plan.

初始化源集合
- ```
~/.codex/history.jsonl
```
- ```
~/.codex/archived_sessions/*.jsonl
```
- 若存在，还包括
```
~/.codex/sessions/*.jsonl
```
  和
```
~/.codex/log/*
```
- 仓库特定的遥测数据（若有，位于
```
AGENTS.md
```
  /本地文档中）
- 在已知点文件目录下检测到的
```
Cursor
```
  /
```
Codex
```
  Agent日志
标准化提取信号
- 解析堆栈跟踪并分类失败类型（
```
auth
```
  、
```
type-check
```
  、
```
llm-error
```
  、
```
git/ci
```
  、
```
runtime
```
  、
```
refactor-merge
```
  、
```
test
```
  ）
- 解析重复出现的命令短语（
```
rg
```
  、
```
mypy
```
  、
```
pytest
```
  、
```
gh
```
  、
```
git
```
  、包管理器失败信息）
- 记录出现频率、最近发生时间及受影响的项目上下文
信号聚类
- 按领域（python/js/rust/docs/tooling）、命令谱系和错误特征进行分组
- 降低低重复率的一次性会话的优先级
映射到现有技能
- 通过
```
name
```
  和
```
description
```
  将候选聚类与现有技能进行对比
- 若重叠度高，提出技能更新方案
- 若无重叠，提出新技能创建建议
输出排名结果
- 提供
```
impact
```
  （影响范围）、
```
frequency
```
  （出现频率）、
```
confidence
```
  （置信度）、
```
skill-fit
```
  （技能匹配度）及首次应用的命令集合
为高优先级候选技能生成最小化的首版工件
- 候选技能标题+范围
- 触发短语示例
- 必填输入参数
- 建议的工作流程摘要
- 证据片段（行/文件级别）
- 建议的依赖项/工具（如
```
jq
```
  、
```
rg
```
  、Shell工具、MCP资源）
可选扩展至个人信号源
- 仅在获得明确许可后才可读取个人渠道数据
- 若MCP可用且用户已授权访问，运行MCP资源发现并纳入来自消息信号的模式
- 除非用户要求合并方案，否则此部分需保持可选，并与代码信号输出隔离

Guardrails

防护规则

Never infer or emit private content from message logs unless explicitly permitted.
Skip binary/corrupt files and summarize only parseable text sources.
Prefer deterministic commands and small scripts over ad-hoc manual parsing.
Always avoid proposing skills with unresolved operational context (credentials, environment, private URLs).
If evidence is ambiguous, return
```
confidence: low
```
and request one more session sample.

除非获得明确许可，否则不得从消息日志中推断或输出私有内容
跳过二进制/损坏文件，仅汇总可解析的文本源
优先使用确定性命令和小型脚本，而非临时手动解析
始终避免提出包含未解决操作上下文（凭证、环境、私有URL）的技能建议
若证据不明确，返回
```
confidence: low
```
并请求额外的会话样本

Outputs

输出结果

```
skill_candidates.md
```
-style report in chat:
- ```
reuse
```
  candidates (existing skill can be extended)
- ```
new
```
  skill candidates (not yet covered)
- top source anchors with references
- recommended next action (create/update)

Read

references/sources.md

for source precedence. Read

references/scorecard.md

for prioritization rules.

聊天窗口中生成
```
skill_candidates.md
```
格式的报告：
- ```
reuse
```
  候选（现有技能可扩展）
- ```
new
```
  技能候选（尚未覆盖的需求）
- 带有引用的顶级源锚点
- 建议的下一步操作（创建/更新）

请阅读

references/sources.md

了解源优先级规则。请阅读

references/scorecard.md

了解优先级排序规则。