deadline-prep
Generate a structured demo outline from your session's change log and git history. Reads .claude/critical_log_changes.csv and git log to produce presentation-ready talking points for end-of-day demos, standups, or delivery deadlines.
- License 许可
- MIT
- 最近更新
- 2026-05-10
- Stars
- ★ 1
- Forks
- 1
01 前言 Front Matter
- name
- deadline-prep
- description
- Generate a structured demo outline from your session's change log and git history. Reads .claude/critical_log_changes.csv and git log to produce presentation-ready talking points for end-of-day demos, standups, or delivery deadlines.
02 资源文件 1
- 参考文档.skill-source.json465 B
03 SKILL.md 正文
Deadline Prep
Generate a structured demo outline from your work session. Combines the change log CSV (from the change-logger hook) with git history to create presentation-ready talking points.
Workflow
Step 1: Gather data sources
Change log (primary source if available):
- Read
.claude/critical_log_changes.csvif it exists - Parse columns: timestamp, tool, file_path, action, details
- Group by: files created, files modified, commands executed
Git history (always available):
git log --oneline --since="today 00:00"
git diff --stat HEAD~10 2>/dev/null || git diff --stat
If the CSV doesn't exist, fall back to git-only mode and note this in the output.
Step 2: Analyze and categorize changes
Group all changes into categories:
| Category | Signals |
|---|---|
| Features shipped | New files, new routes, new components, feat commits |
| Bug fixes | Modified files with fix commits, error handling changes |
| Refactors | Renamed files, structural changes, refactor commits |
| Config/Setup | package.json, tsconfig, CI/CD, Docker changes |
| Tests | Test files created or modified |
| Documentation | README, docs, comments |
Step 3: Generate the demo outline
Create a structured markdown document:
# Demo Outline — [Date]
## What I Shipped
- **[Feature/Fix name]**: One sentence explaining what it does and why it matters
- **[Feature/Fix name]**: One sentence explaining what it does and why it matters
- **[Feature/Fix name]**: One sentence explaining what it does and why it matters
## Architecture Decisions
- **[Decision]**: Why I chose this approach over alternatives
- **[Decision]**: Tradeoff I made and the reasoning
## What I Would Do Next
1. **[Priority 1]**: Why this is the most important next step
2. **[Priority 2]**: What this would unlock
3. **[Priority 3]**: Nice-to-have improvement
## Session Metrics
- Files changed: X
- Lines: +Y / -Z
- Commits: N
- Key files: `path/to/important/file.ts`, `path/to/other.ts`
- Time window: HH:MM - HH:MM
Step 4: Save and present
Save the outline to .claude/demo-outline.md.
Print the full outline to the terminal so the user can review it immediately.
Tips
- Run this 30 minutes before your deadline to have time to review and add personal context
- The "Architecture Decisions" section is what reviewers care about most — add context about tradeoffs
- "What I Would Do Next" shows you think beyond the immediate task
- Edit the generated outline to add your own voice and any context the log missed
- Works best with the
change-loggerhook installed, but functions with git history alone
04 同仓库更多 Skills
zustand-store-ts
Create Zustand stores following established patterns with proper TypeScript types and middleware.
zod-validation-expert
Expert in Zod — TypeScript-first schema validation. Covers parsing, custom errors, refinements, type inference, and integration with React Hook Form, Next.js, and tRPC.
zinc-database
Access ZINC (230M+ purchasable compounds). Search by ZINC ID/SMILES, similarity searches, 3D-ready structures for docking, analog discovery, for virtual screening and drug discovery.
zarr-python
Chunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.
zapier-workflows
Manage and trigger pre-built Zapier workflows and MCP tool orchestration. Use when user mentions workflows, Zaps, automations, daily digest, research, search, lead tracking, expenses, or asks to "run" any process. Also handles Perplexity-based research and Google Sheets data tracking.
zapier-make-patterns
No-code automation democratizes workflow building. Zapier and Make (formerly Integromat) let non-developers automate business processes without writing code. But no-code doesn't mean no-complexity - these platforms have their own patterns, pitfalls, and breaking points. This skill covers when to use which platform, how to build reliable automations, and when to graduate to code-based solutions. Key insight: Zapier optimizes for simplicity and integrations (7000+ apps), Make optimizes for power