daily-summary
Produce daily/yesterday work summary (日报) by aggregating Claude Code sessions, Git commits, and Notion task data — git log alone cannot do this.
Skill by jiahao-shao1
Chalk Labs
Need help deploying daily-summary?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/jiahao-shao1-daily-summary
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: data, productivity, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Shell scripts
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/daily-summary
What's inside
- Skill name
daily-summary- Description
- Produce daily/yesterday work summary (日报) by aggregating Claude Code sessions, Git commits, and Notion task data — git log alone cannot do this. Args: today (default), yesterday, 24h, YYYY-MM-DD. Triggers: 'daily summary', 'what did I do today', 'yesterday summary', '日报', '今天干了什么', '工作总结', '某天做了什么'. Not for weekly reports or summarizing files.
- License
- MIT
- Instructions
- 77 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (5)
- README.md
- README.zh-CN.md
- SKILL.md
- trigger_eval.json · evals/
- collect-daily-data.sh · scripts/
SKILL.md (first lines)
# Daily Summary ## Usage Triggered by `/daily-summary` or conversational triggers. Arguments come from the ARGUMENTS line. ``` /daily-summary → today /daily-summary yesterday → yesterday /daily-summary 24h → past 24 hours /daily-summary 2026-03-20 → specific date ``` ## Prerequisites | Dependency | Purpose | Check | |------------|---------|-------| | `collect-daily-data.sh` | Aggregates git log, Claude sessions, Notion tasks | Bundled in `scripts/` | | `notion-lifeos` skill | Notion task data (optional — skipped if missing) | `~/.claude/skills/notion-lifeos/` | | `git` | Commit history | Available on PATH | ## Execution Steps 1. Parse date argument from ARGUMENTS, default to `today` 2. Run data collection script: ```bash bash <skill-base-dir>/scripts/collect-daily-data.sh --date <argument> ``` Where `<skill-base-dir>` is the directory containing this SKILL.md (known at skill load time, i.e., the "Base directory for this skill" path). 3. Read the script's full stdout 4. Generate a Chinese summary based on the collected data ## Summary Requirements ### Output Format ``` ## YYYY-MM-DD Work Summary ### Timeline - **HH:MM-HH:MM** [Project] What was done (1-sentence summary) - **HH:MM-HH:MM** [Project] What was done ... ### Key Outputs - Specific output 1 (e.g., added XX feature, fixed XX bug) - Specific output 2 ... ### Task Completion - Completed: N items - Incomplete: N items (list specific task names) ### Unplanned Work (Work found in Git/Sessions but not tracked in Notion Tasks, if any) ``` ### Guidelines - Infer what was done from user messages — do not copy messages verbatim - Merge multiple messages on the same topic into a single entry - Timeline entries in chronological order - Language: Chinese - No emojis ## Error Handling | Error | Action | |-------|--------| | `collect-daily-data.sh` returns empty | Report "no activity found for this date" — don't generate an empty summary | | Notion tasks unavailable | Skip the Task Completion section, note it was skipped | | No git repos found | Skip git data, rely on Claude Code sessions only | | Date argument invalid | Default to `today`, warn user about invalid input |
From jiahao-shao1/sjh-skills, MIT.
More from jiahao-shao1/sjh-skills
- 0.660score
session-team
jiahao-shao1
Coordinate Claude Code or Codex sessions on one machine, including messaging an existing CC session from Codex.
SkillAFreshness: A★ 39Claude Code +9 - 0.620score
notion-lifeos
jiahao-shao1
User's personal Notion LifeOS (PARA: tasks, notes, projects, Make Time journals) with pre-configured DB IDs + API access — required for any LifeOS interaction.
SkillBFreshness: B★ 39Claude Code +9 - 0.616score
paper-analyzer
jiahao-shao1
Deep critical analysis of one specific paper — dissect experimental setup, extract numbers, evaluate claims against a hypothesis.
SkillBFreshness: B★ 39Claude Code +9 - 0.610score
sync-docs
jiahao-shao1
Update the project's documentation to match recent code changes, then commit.
SkillBFreshness: B★ 39Claude Code +9 - 0.570score
paper-self-review
jiahao-shao1
Self-review for paper paragraphs — diagnose v1 issues and give a revision direction (intro, abstract, method, related work).
SkillCFreshness: C★ 39Claude Code +9 - 0.565score
experiment-registry
jiahao-shao1
Manage ML experiment lifecycle via structured YAML registry — register, record results, compare runs, track status.
SkillCFreshness: C★ 39Claude Code +9 - 0.565score
context-audit
jiahao-shao1
Audit project context management (CLAUDE.md, rules, knowledge) for progressive disclosure compliance.
SkillCFreshness: C★ 39Claude Code +9 - 0.564score
init-project
jiahao-shao1
初始化新项目的 Claude Code 配置。用户说"初始化项目"、"init project"、"配置 Claude Code"时触发。
SkillCFreshness: C★ 39Claude Code +9 - 0.502score
bibtex-fetch
jiahao-shao1
Fetch BibTeX entries from arXiv / Semantic Scholar.
SkillDFreshness: D★ 39Claude Code +9 - 0.500score
web-fetcher
jiahao-shao1
Fetch any URL as clean markdown.
SkillDFreshness: D★ 39Claude Code +9 - 0.500score
project-review
jiahao-shao1
Strategic project review — auto-discovers strategy docs (vision, roadmap, decisions, notes), produces five-dimension snapshot.
SkillDFreshness: D★ 39Claude Code +9 - 0.499score
handoff
jiahao-shao1
Generate a structured handoff summary for the next session.
SkillDFreshness: D★ 39Claude Code +9
Signals
- Stars
- 39
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Apr 25, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/jiahao-shao1/sjh-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from jiahao-shao1
- 0.660score
session-team
jiahao-shao1
Coordinate Claude Code or Codex sessions on one machine, including messaging an existing CC session from Codex.
SkillAFreshness: A★ 39Claude Code +9 - 0.620score
notion-lifeos
jiahao-shao1
User's personal Notion LifeOS (PARA: tasks, notes, projects, Make Time journals) with pre-configured DB IDs + API access — required for any LifeOS interaction.
SkillBFreshness: B★ 39Claude Code +9 - 0.616score
paper-analyzer
jiahao-shao1
Deep critical analysis of one specific paper — dissect experimental setup, extract numbers, evaluate claims against a hypothesis.
SkillBFreshness: B★ 39Claude Code +9 - 0.610score
sync-docs
jiahao-shao1
Update the project's documentation to match recent code changes, then commit.
SkillBFreshness: B★ 39Claude Code +9 - 0.570score
paper-self-review
jiahao-shao1
Self-review for paper paragraphs — diagnose v1 issues and give a revision direction (intro, abstract, method, related work).
SkillCFreshness: C★ 39Claude Code +9 - 0.565score
experiment-registry
jiahao-shao1
Manage ML experiment lifecycle via structured YAML registry — register, record results, compare runs, track status.
SkillCFreshness: C★ 39Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get daily-summary running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
daily-summary skill. Agent Mart. https://agentmart.dev/skills/jiahao-shao1-daily-summary (last updated 2026-10-24)