메뉴
Summarize a Claude.ai conversation export into structured human-readable notes. Use when the user has a saved conversation text file and wants a dated summary .md file written to the current directory.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Write pull request review comments and replies to review threads in the user's voice. Use when reviewing a PR or diff and producing comments, when replying to a bot thread (CodeRabbit, Codex), when triaging or applying review findings, or when staging review feedback in a pr-<number>-review-comments.md file for the user to proofread before posting.
The user's full writing system for prose they author — README and docs text, landing copy, PR and commit descriptions, Linear proposals, design docs, Slack and email messages. Use when drafting or rewriting any human-facing prose, when a draft reads like AI wrote it, when stripping AI slop from documentation, or when relaying research output into a human-facing surface. CLAUDE.md carries the compressed rules; this carries the reasoning, the before/after pairs, and the per-format shapes.
incident.io assistant for working with incidents. View incident details, post updates to incident channels, interact with the incident agent, and query structured incident data. Use whenever the user mentions an incident ID (e.g., "INC-123"), asks about an incident, or uses the /incident command. Trigger proactively when you see an incident reference.
Freshens the repos listed in mani.yaml - syncs each with upstream, runs local gates, fixes CI on the default branch, and rolls template releases out to copier children. Arguments are a space-separated subset of repo names from mani.yaml; default is every repo.
On-demand UX critique for terminal UIs (Bubble Tea, Ratatui, Ink, Textual). Combines hyperskills:tui-design's layout/keybinding/color principles with impeccable's critique rigor (cognitive load, personas, heuristic scoring, P0-P3 severity), adapted for terminals — no CSS, no browser, no WCAG contrast math. Use when reviewing or critiquing a TUI's design, auditing keybinding discoverability, or checking terminal portability (NO_COLOR, monochrome degradation, multiplexer/SSH behavior).
Capture and persist browser screenshots or GIFs for visual review of a web UI. Use when verifying a UI change visually, reviewing a page's design or layout, recording a multi-step interaction (dropdown, hover, form flow), toggling dark mode for a comparison shot, or when a screenshot needs to be written to disk rather than only shown inline.
| name | summarize-chat |
| description | Summarize a Claude.ai conversation export into structured human-readable notes. Use when the user has a saved conversation text file and wants a dated summary .md file written to the current directory. |
Runs summarize_chat.py against a conversation text file and writes a dated summary markdown file
to the current working directory.
ANTHROPIC_API_KEY must be set. The script uses uv run with inline dependencies, so no manual
install step is needed beyond having uv available.
uv run ~/.claude/skills/summarize-chat/summarize_chat.py <file>
Optional flags:
--model <id> — override the Claude model (default: claude-sonnet-4-6)--output <path> — write to a specific path instead of the auto-named defaultThe script prints the output path on success. The default filename is:
<cwd>/<YYYY-MM-DD>-<source-stem>-summary.md
For example, running against chat-776d8ae5.txt on 2026-06-30 produces:
<cwd>/2026-06-30-chat-776d8ae5-summary.md
## Summary
## Decisions and Outcomes
## Context and Reasoning
## Open Questions
## Links and References
## Observations
Sections with nothing real to say are omitted from the output.
When the user runs /summarize-chat with a file path argument, run:
uv run ~/.claude/skills/summarize-chat/summarize_chat.py "<file-path>"
Print the output path on completion and offer to open the file.