Token导航 LogoToken导航

Agent Skill · 研究检索

project-tracking(项目跟踪)

project-tracking 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

project-tracking 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为调用外部服务;许可证信息还不明确,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 61,288。

总安装 353周安装 15GitHub Stars 公开资料未说明下载 124核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:project-tracking(项目跟踪)
来源仓库:https://github.com/fearovex/claude-config
仓库路径:skills/project-tracking
安装命令:
npx skills add https://github.com/fearovex/claude-config --skill project-tracking
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/fearovex/claude-config --skill project-tracking

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

project-tracking 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。适用于项目管理、进度跟踪和资源调度等场景。可通过任务关键词匹配历史记录或待办事项,返回优先级排序结果。

安装前建议确认是否允许访问本地任务文件或外部日历服务。需注意权限控制,避免越权修改或删除关键项目数据。

来源仓库内路径:skills/project-tracking

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/fearovex/claude-config --skill project-trackin…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要调用外部服务,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

project-tracking 怎么安装?

在终端执行 npx skills add https://github.com/fearovex/claude-config --skill project-tracking。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

project-tracking 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

project-tracking 需要什么权限?

权限级别是调用外部服务。该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

project-tracking 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

project-tracking 用的人多吗?

公开数据是累计安装 353 次,近一周安装 15 次,下载 124 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

project-tracking 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
project-tracking

项目跟踪 · 本页

353—调用外部服务未明确有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Triggers: /track-init, /track <description>, /backlog, "qué tenemos pendiente?", "what's pending?", "acordate que hay que...", "remember to...", bug found during implementation, SDD tasks generated by sdd-tasks.

Process

Pre-flight: Detect Repo and Config

Before any flow, resolve owner/repo and load the board config:

# Detect owner/repo from git remote
git remote get-url origin
# Parse: https://github.com/owner/repo.git → owner=owner, repo=repo
# Parse: git@github.com:owner/repo.git → same

Then search engram for the project config:

  • mem_search with query tracking/{repo-name}/config
  • If found, call mem_get_observation to get project number and field IDs
  • If NOT found and the flow requires project operations → warn user to run /track-init first

Flow 1: Bootstrap — /track-init

Run once per repo. Idempotent — safe to run again.

Step 0 — Detect token capabilities

Before attempting to create the project board, check if the token supports Projects V2:

gh project list --owner owner --limit 1 2>&1

If this fails with a permission/scope error, the token likely cannot manage Projects V2.

Known limitation: Fine-grained PATs do NOT support Projects V2 on personal accounts (only organizations). If the repo owner is a personal account and the token is fine-grained, the board MUST be created manually.

When automatic creation is not possible, guide the user:

Your token does not support GitHub Projects V2 for personal accounts.
Please create the board manually (takes 30 seconds):

1. Go to https://github.com/users/{owner}/projects → "New Project"
2. Choose "Board" layout
3. Name it "{repo-name} Board"
4. Add these custom fields (Single Select):
   - Status: Backlog, Todo, In Progress, Review, Done
   - Priority: P0-Critical, P1-High, P2-Medium, P3-Low
   - Type: Epic, Feature, Bug, Chore
5. Tell me the project number (visible in the URL: /projects/N)

I'll handle the rest — labels, capturing IDs, and saving the config.

After the user provides the project number, skip to Step 2 (labels) and continue normally.

Step 1 — Create GitHub Project board (automatic path)

Only if Step 0 confirms the token supports Projects V2:

# Create project linked to the repo
gh project create --owner owner --title "{repo-name} Board" --format json
# Capture: .number → project_number

Then add custom fields:

# Status field (single select)
gh project field-create {project_number} --owner owner \
  --name "Status" --data-type "SINGLE_SELECT" \
  --single-select-options "Backlog,Todo,In Progress,Review,Done"

# Priority field (single select)
gh project field-create {project_number} --owner owner \
  --name "Priority" --data-type "SINGLE_SELECT" \
  --single-select-options "P0-Critical,P1-High,P2-Medium,P3-Low"

# Type field (single select)
gh project field-create {project_number} --owner owner \
  --name "Type" --data-type "SINGLE_SELECT" \
  --single-select-options "Epic,Feature,Bug,Chore"
Step 2 — Create labels
# Type labels
gh label create "type/epic"    --color "6e40c9" --description "Epic" --repo owner/repo
gh label create "type/feature" --color "0075ca" --description "Feature" --repo owner/repo
gh label create "type/bug"     --color "d73a4a" --description "Bug" --repo owner/repo
gh label create "type/chore"   --color "e4e669" --description "Chore" --repo owner/repo

# Priority labels
gh label create "priority/high"   --color "b60205" --description "P1 High" --repo owner/repo
gh label create "priority/medium" --color "fbca04" --description "P2 Medium" --repo owner/repo
gh label create "priority/low"    --color "0e8a16" --description "P3 Low" --repo owner/repo

# Status labels
gh label create "status/backlog"     --color "ededed" --description "In backlog" --repo owner/repo
gh label create "status/in-progress" --color "0052cc" --description "In progress" --repo owner/repo
gh label create "status/review"      --color "e99695" --description "In review" --repo owner/repo
gh label create "status/done"        --color "cfd3d7" --description "Done" --repo owner/repo

If a label already exists, gh label create will fail — catch the error and continue (idempotent behavior).

Step 3 — Capture field and option IDs

Whether the board was created automatically (Step 1) or manually (Step 0), capture the field IDs:

gh project field-list {project_number} --owner owner --format json

Parse the JSON to extract:

  • status_field_id, and option IDs for each status value
  • priority_field_id, and option IDs for each priority value
  • type_field_id, and option IDs for each type value

These IDs are required by gh project item-edit.

Step 4 — Save config to engram

Call mem_save with:

  • title: "Bootstrap project-tracking config for {repo-name}"
  • type: config
  • topic_key: tracking/{repo-name}/config
  • content: project_number, owner, repo, all field IDs and option IDs as a structured map

Confirm to user: "Board linked. Project #{project_number} for {owner}/{repo}. Config saved to engram."


Flow 2: Track — Create Issues and Add to Board

Trigger model (hybrid)
SituationBehavior
/track <description>Create issue immediately, no confirmation
/track with multiple items or backlog sessionCreate all, show list, ask confirmation before executing
sdd-tasks generates tasksPropose creating one issue per task, ask confirmation
User mentions future work ("habría que...", "falta...", "después hay que...")Collect internally. At session end propose: "Detected N trackable items: [list]. Create as issues?"
"acordate que hay que..." / "remember to..."Propose creating an issue immediately
Bug found during implementationPropose creating issue with type/bug label immediately
Issue creation steps

Step 1 — Deduplicate

gh issue list --repo owner/repo --search "{title keywords}" --json number,title

If a similar issue exists, show it and ask: "Issue #N already exists: '{title}'. Create a new one anyway?"

Step 2 — Create issue via MCP

Use mcp__github__create_issue with:

  • owner, repo
  • title: conventional format — type: description (e.g., feat: add OAuth, fix: email validation)
  • body: use the issue body template below
  • labels: array of applicable labels (e.g., ["type/feature", "priority/medium", "status/backlog"])

Issue body template:

## Description
{description}

## Context
- Source: {how this was identified — user request, SDD task, conversation, bug found}
- Session: {date}
- Related: {any related issues or PRs, if known}

## Acceptance Criteria
- [ ] {criterion 1}
- [ ] {criterion 2}

Step 3 — Add to project board

gh project item-add {project_number} --owner owner \
  --url https://github.com/owner/repo/issues/{issue_number} \
  --format json
# Capture: .id → item_id

Step 4 — Set project fields

Load field IDs and option IDs from engram config (tracking/{repo-name}/config). If not in cache, run:

gh project field-list {project_number} --owner owner --format json

Then set each field:

# Set Status
gh project item-edit --project-id {project_number} --owner owner \
  --id {item_id} \
  --field-id {status_field_id} \
  --single-select-option-id {status_option_id}

# Set Priority
gh project item-edit --project-id {project_number} --owner owner \
  --id {item_id} \
  --field-id {priority_field_id} \
  --single-select-option-id {priority_option_id}

# Set Type
gh project item-edit --project-id {project_number} --owner owner \
  --id {item_id} \
  --field-id {type_field_id} \
  --single-select-option-id {type_option_id}

Step 5 — Confirm to user

Created #14: feat: add OAuth with Google — added to board as Backlog/P1-High [Feature]

Flow 3: Query — /backlog and status questions

Default: full board summary
gh project item-list {project_number} --owner owner --format json --limit 100

Parse JSON and group items by Status field value. Output:

## Project Board: {project-name}

### In Progress (2)
- #14 feat: OAuth with Google [P1-High]
- #12 fix: Email validation [P0-Critical]

### Review (1)
- #13 feat: User profile page [P1-High]

### Backlog (3)
- #15 feat: Dashboard redesign [P2-Medium]
- #16 chore: Update dependencies [P3-Low]
- #17 feat: Export to PDF [P2-Medium]

### Done (last 5)
- #11 fix: Login redirect loop [P1-High]

Show statuses in order: In Progress → Review → Todo → Backlog → Done (last 5 only to avoid noise).

Filtered queries
CommandFilter applied
/backlog bugsOnly items with Type = Bug
/backlog highOnly items with Priority = P0-Critical or P1-High
/backlog in-progressOnly items with Status = In Progress
/backlog todoOnly items with Status = Todo
/backlog reviewOnly items with Status = Review

Status Transitions

Move an issue on the board with:

# Manual trigger
/track move #14 in-progress
/track move #14 review
/track move #14 done

# Underlying command
gh project item-edit --project-id {project_number} --owner owner \
  --id {item_id} \
  --field-id {status_field_id} \
  --single-select-option-id {in_progress_option_id}

Automatic integration points:

  • Claude starts working on issue → move to "In Progress"
  • Claude opens PR for issue → move to "Review" (integrates with branch-pr skill)
  • PR merged / issue closed → move to "Done"

Rules

  • GitHub Issues + Projects is the source of truth for WHAT needs to be done — backlog, tasks, stories, bugs
  • Engram remains the source of truth for decisions, discoveries, and technical context — these are complementary, not competing
  • Never create duplicate issues — always run gh issue list --search before creating
  • Issue titles follow conventional format: type: description (e.g., feat: add OAuth, fix: email validation)
  • Labels use lowercase with / separator: type/feature, priority/high, status/backlog
  • Every issue MUST have at least the Type field set on the project board
  • /track-init is idempotent — running it twice must not create duplicate labels or projects; handle errors from gh label create gracefully
  • Project config (IDs) MUST be saved to engram after bootstrap with topic_key: tracking/{repo-name}/config
  • Before any gh project item-edit call, load field IDs from engram; if not found re-derive with gh project field-list
  • Batch creation requires confirmation — when proposing multiple issues at once, show the full list and wait for user approval before creating any
  • Propose, don't assume type/priority — when auto-detecting trackable items from conversation, infer reasonable defaults but show them to the user before creating
  • Prefer MCP for issue creation (mcp__github__create_issue) and gh CLI for all project board operations
  • When /track-init has not been run (no engram config, no linked project), detect this and suggest running it before any board operation
  • Fine-grained PATs do NOT support Projects V2 on personal accounts — only Classic PATs or org-scoped fine-grained tokens work. When this is detected, guide the user to create the board manually and proceed with ID capture only
  • Both automatic and manual board creation paths converge at Step 3 (capture IDs) — the rest of the workflow is identical regardless of how the board was created

平台分布

Codex

35.51%
按下载量换算44

Claude

30.72%
按下载量换算38

Cursor

17.82%
按下载量换算22

Gemini CLI

9.3%
按下载量换算12

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

调用外部服务

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills