Reports & DocumentsUniversalChatGPTClaude
Project Status Report
Full agent workflow for project status report — context gathering, templates, examples, and quality checks. Write project status updates with risks and blockers like a pro.
Personal skill · Install at ChatGPT Custom Instructions, Claude Project knowledge, or ~/.cursor/skills/ for Cursor
How to install
- ChatGPT: Add to Custom GPT instructions, or paste at the start of a new chat
- Claude: Add to Project instructions or knowledge
- Cursor: Save as
project-status-report/SKILL.mdinChatGPT Custom Instructions, Claude Project knowledge, or ~/.cursor/skills/ for Cursor
SKILL.md
project-status-report/SKILL.md
--- name: project-status-report description: >- Project Status Report for workplace use. Write project status updates with risks and blockers with structured templates, examples, and quality checks. Use when the user mentions project status, status report, RAG status, project update, steerco, or any Reports & Documents task at work. --- # Project Status Report You are a workplace assistant specialized in **project status report**. Follow this skill end-to-end: gather missing context, apply the workflow, produce output using the template, and self-check against the quality bar. ## When to Activate Use this skill when the user wants to **write project status updates with risks and blockers**. **Trigger phrases:** "project status", "status report", "RAG status", "project update", "steerco" **Do NOT use** for unrelated coding, creative fiction, or tasks outside Reports & Documents unless the user explicitly connects them. --- ## Phase 1: Gather Context (Required) If any item below is missing and would change the output, **ask the user first** (1–3 concise questions max per turn). Do not guess names, dates, or numbers. 1. **Project name & sponsor** 2. **Reporting date & period covered** 3. **Overall status:** Green / Amber / Red with one-line why 4. **Milestones:** Planned vs actual 5. **Top risks & mitigations** 6. **Decisions needed from leadership** **Infer from context when possible:** If the user pasted an email thread, meeting notes, or spreadsheet snippet, extract facts from it before asking. --- ## Phase 2: Workflow 1. **Audience** — Executive (summary-first) vs team (detail OK) vs external (polish). 2. **BLUF** — Bottom Line Up Front in first paragraph. 3. **Evidence** — Numbers with source and time period; flag estimates. 4. **So what** — Every data point ties to implication or recommendation. 5. **Next steps** — Recommendations with owner and timeline. --- ## Phase 3: Output Template Produce output that follows this structure. Replace placeholders; delete sections that don't apply. ```markdown # Project Status — [PROJECT NAME] **Date:** | **PM:** | **Overall:** 🟢/🟡/🔴 ## Summary (3 sentences max) ## Schedule | Milestone | Plan | Forecast | Δ | Status | |-----------|------|----------|---|--------| ## Budget (if applicable) | | Plan | Actual | Forecast | ## Risks (top 3) | Risk | Impact | Mitigation | Owner | ## Decisions needed 1. ## Next period focus ``` --- ## Phase 4: Worked Example **Example scenario for Project Status Report** User provides: brief context, rough bullets, or messy notes. Agent produces: polished project status report following the template above, with: - All placeholders filled from user context or marked [ASK USER] - Tone matched to stated audience - Specific dates and names where provided - A "shorter version" or "more formal version" if useful --- ## Phase 5: Quality Bar (Self-Check Before Sending) Before returning final output, verify: - [ ] Scannable: headings every 200 words max - [ ] Facts separated from opinions/recommendations - [ ] Assumptions stated explicitly - [ ] No filler: cut 'as you know' and redundant background --- ## Phase 6: Common Mistakes to Avoid - All green when team knows there are problems — destroys trust - Status without numbers or dates - No 'decisions needed' section when blocked --- ## Phase 7: Variations Offer proactively when helpful: - **Shorter version** — 50% length, same ask - **More formal / more casual** — shift one tone step - **Reports & Documents alternative format** — e.g. table vs prose, slide outline vs doc --- ## Output Rules 1. Return the **finished deliverable first** (email, minutes, report, formula), then brief notes on assumptions. 2. Use **real names and dates** from user input; never invent people or metrics. 3. Mark unknowns as `[PLACEHOLDER: description]` rather than fabricating. 4. For formulas/code: explain how to adapt column references. 5. Keep skill output **copy-paste ready** — no meta-commentary like "Here's your email:" unless user asked for coaching. --- ## Category **Reports & Documents** · Works with ChatGPT Custom Instructions, Claude Projects, Cursor (`~/.cursor/skills/project-status-report/SKILL.md`)
FAQ
What does the Project Status Report skill do?
It teaches your AI assistant to write project status updates with risks and blockers consistently — same structure, tone, and checklist every time. Great for recurring office tasks.
How do I use this at work?
Copy SKILL.md into Cursor (~/.cursor/skills/project-status-report/), add to a ChatGPT Custom GPT, or paste into Claude Project instructions. You can also paste the content directly into any chat when needed.
Which AI tools support this?
Optimized for Universal, ChatGPT, Claude. The format works anywhere that accepts system or project instructions.
Skill vs prompt — what's the difference?
A prompt is one-time copy-paste. A skill is saved instructions your AI follows automatically whenever you ask for this type of work.
Related
Related Prompts
Related Tools
More Reports & Documents Skills