项目管理里程碑跟踪器（Project Milestone Tracker）——当用户要求代理在代码库/项目会话中规划、跟踪里程碑、记录承诺或事件、生成进度报告时使用。核心：三层里程碑规则（文件依据/客户提供/待确认）+ 原话+时间戳事件记录。
Project milestone tracker: plan and track project milestones, record events with original text + timestamp, generate status reports, using a three-tier milestone rule (contract-sourced / stakeholder-stated / pending-confirmation).
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
A self-contained local tracker for planning and tracking project work in a repo session — no external service, no cloud, pure local files (Python stdlib only).
Use this skill when the user asks the agent to:
It is designed for repo-session work: the agent runs local commands and keeps state in a local JSON file.
Never invent milestone dates. Every milestone must carry a source tier:
| Tier | source | Meaning | Behavior |
|---|---|---|---|
| 1 | file | Extracted from a contract/document | Authoritative; note the source document |
| 2 | client | Stated verbally by stakeholder | Recorded as stated; suggest written confirmation |
| 3 | pending | No milestone info yet | Flag "ask the client" — never self-plan |
All commands run via the bundled script (stdlib only, no install):
python3 scripts/pm_track.py --file .pm.json init "东区改造项目"
python3 scripts/pm_track.py --file .pm.json add-milestone "3月15日竣工验收" --source file --due 2026-03-15 --note "依据合同第四章"
python3 scripts/pm_track.py --file .pm.json add-milestone "甲方口头承诺月底回款" --source client --due 2026-03-31
python3 scripts/pm_track.py --file .pm.json add-milestone "材料进场节点待确认" --source pending
python3 scripts/pm_track.py --file .pm.json add-event "甲方说马上回款" --who 王总 --when "2026-03-10 14:30"
python3 scripts/pm_track.py --file .pm.json status
python3 scripts/pm_track.py --file .pm.json report # markdown report
python3 scripts/pm_track.py --file .pm.json done 1
| Command | What it does |
|---|---|
init <name> | Initialize a project tracker file |
add-milestone <title> --source file|client|pending [--due] [--note] | Add a milestone with a source tier |
add-event <text> [--who] [--when] | Record an event with original text + timestamp |
done <id> | Mark a milestone done |
status | Show all milestones + events + pending warnings |
report | Print a markdown progress report |
$ python3 scripts/pm_track.py --file .pm.json init "门店装修"
$ python3 scripts/pm_track.py --file .pm.json add-milestone "6月10日完工验收" --source file --due 2026-06-10
$ python3 scripts/pm_track.py --file .pm.json add-milestone "水电改造完成" --source client
$ python3 scripts/pm_track.py --file .pm.json add-event "甲方电话说马上回款" --who 李总
$ python3 scripts/pm_track.py --file .pm.json status
📋 Project: 门店装修
=== 里程碑 (2 open) ===
⬜ #1 [file ] 6月10日完工验收 (due 2026-06-10)
⬜ #2 [client] 水电改造完成
=== 事件记录 (1) ===
• [2026-08-25 15:20] (李总) 甲方电话说马上回款
.project-tracker.json, or pass --file).argparse, json, datetime) — no pip installs, no network.A milestone planning checklist and a status report template live in templates/ — copy and adapt.
pending milestones — the whole point of the three-tier rule is that the agent asks the client instead of guessing.text verbatim plus when/who so claims are traceable.report prints markdown to stdout; pipe to a file (> report.md) to save.No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Handle ActiveCampaign contact and marketing tasks through Rube MCP, a connection for agent tools. Find or create contacts, manage tags and subscriptions, enroll contacts in existing automated workflows, and create follow-up tasks.
Research competitors’ live Meta and Google ads to identify opening hooks, offers, calls to action, and landing pages. Receive a sourced creative brief and up to three test ideas adapted to your product.
Analytics your AI agent can actually use. Track, analyze, run A/B experiments, and optimize across all your projects via CLI. Includes a growth playbook so your agent knows HOW to grow, not just what to track.
The English summary is being prepared. Showing the original description.
Teaches when to recall from long-term memory before acting and when to save durable decisions, corrections and failures afterwards. Use when a memory tool or MCP memory server is connected but the agent is not using it consistently, when the user complains that the assistant forgets preferences, conventions or past decisions between sessions, or when setting up persistent memory for a project. Works with any memory backend: a folder of Markdown files, a local MCP server, or a managed service.
The English summary is being prepared. Showing the original description.
Audit local AI coding-agent sessions with agenttrace for cost, tokens, tool failures, latency, anomalies, health, diffs, and CI gates.
The English summary is being prepared. Showing the original description.
Checks which private files (.env, keys, secrets) Claude Code and its subagents reached in this project, whether a value came into an agent's context, and which key to change, by running the open source agentwhy CLI over the session records Claude Code already keeps on disk. Use when the user asks whether the agent or a subagent read their .env or other secrets, which private files a session touched, whether a key leaked into the conversation, or which key to rotate. Runs locally and never prints a secret value.
The English summary is being prepared. Showing the original description.