AGENT SKILL

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

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.csv if 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-logger hook installed, but functions with git history alone

04 同仓库更多 Skills

Sansar35
Sansar35/claude-agent

zustand-store-ts

Create Zustand stores following established patterns with proper TypeScript types and middleware.

★ 1
Sansar35
Sansar35/claude-agent

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.

★ 1
Sansar35
Sansar35/claude-agent

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.

★ 1
Sansar35
Sansar35/claude-agent

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.

★ 1
Sansar35
Sansar35/claude-agent

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.

★ 1
Sansar35
Sansar35/claude-agent

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

★ 1