AGENT SKILL

timezone

Set the time zone Claude Code shows times in — the "done 7:55 PM" at the end of a turn, and the clock every command Claude runs sees. Use when the user asks to change, pick, set, fix or clear their time zone, or says the times shown are wrong (a remote server on UTC is the usual cause). Writes one key, env.TZ, into the user's own settings file.

License 许可
MIT
最近更新
2026-11-14
Stars
★ 2
Forks
0

01 前言 Front Matter

lane
coding
name
timezone
strictness
standard
description
Set the time zone Claude Code shows times in — the "done 7:55 PM" at the end of a turn, and the clock every command Claude runs sees. Use when the user asks to change, pick, set, fix or clear their time zone, or says the times shown are wrong (a remote server on UTC is the usual cause). Writes one key, env.TZ, into the user's own settings file.
allowed-tools
Bash, AskUserQuestion

02 资源文件 1

03 SKILL.md 正文

Time zone

Claude Code prints the time a turn finished in its own process's time zone. On a server whose clock is UTC, that is UTC. Setting env.TZ in the user's settings file moves it to the user's zone (platform.md § Fact 27). This skill picks the zone, writes that one key, and reads it back.

Resolve the script first, in every Bash call:

TZB="${CLAUDE_CONFIG_DIR:-$HOME/.claude}/skills/timezone/bin/wf-timezone"; [ -x "$TZB" ] || TZB="${CLAUDE_PROJECT_DIR:-$PWD}/.claude/skills/timezone/bin/wf-timezone"

Steps

  1. Show. Run "$TZB" --root "${CLAUDE_PROJECT_DIR:-$PWD}" show --json. It returns the current setting, this machine's zone, a guess from the user's own commit times, and up to four candidates, each with its local time now.

  2. Ask once. One AskUserQuestion call, one question:

    • header Time zone; question: Which time zone should Claude Code show times in?
    • one option per candidate, in the order given. Label: the zone, plus (current) when current is true or (recommended) when recommended is true. Description: Now <now> and the candidate's note.
    • say in the question that the blank field takes any zone name, like America/New_York or Europe/Berlin, and that none removes the setting.

    If the user already named a zone in their message, skip the question and use it.

  3. Apply. A zone: "$TZB" set <zone>. none: "$TZB" clear. An unknown name is refused with exit 2 and a plain message; ask again with the same question.

  4. Report the receipt. Quote the verified on disk line and the now line the script printed, not a summary of them. Then say: Claude Code's own "done" time uses the new zone after Claude Code is restarted, and commands Claude runs use it straight away. If show listed an overridden_by entry, say that project's own settings still win there.

When the write is refused

Claude Code may refuse an agent's write to a user settings file. Then give the user the exact command to run themselves, built from set_command (or clear_command) in the show --json output, with the REPL ! prefix, on one line:

! /home/you/.claude/skills/timezone/bin/wf-timezone set America/New_York

Never hand over JSON to paste. The script writes the same key, keeps every other byte of the file, and records what it wrote in <config>/workforce/.settings-owned.json.

What it changes

One key in ${CLAUDE_CONFIG_DIR:-~/.claude}/settings.json, so it reaches every project on the machine. TZ also reaches every command Claude runs, so date and anything else reading local time follows it. clear removes the key and gives the file back exactly as it was before set.

04 同仓库更多 Skills

odysseyalive
odysseyalive/claude-workforce

ui-design

Set a RENDERED interface's design direction before it is built, then evaluate what shipped. `direct` reads the project's CSS stack, asks about the case, researches real references for the job each screen does, hands the pick to the user, and writes the project's design record; `review` and `sweep` grade declared-vs-rendered slots (no missing or placeholder art), applied theme vs framework default, visual hierarchy, typography, colour roles, CTA, WCAG 2.2 AA contrast and focus, reflow at 320 CSS pixels, situation ergonomics, and AI-slop/templated-default tells. Use `direct` before the first UI build on a surface or for a new component pattern; use `review` after a UI-shipping change is written, when asked to design-review a page, or to decide whether a surface looks right to ship. Grades against a cited catalog with stable rule IDs and BLOCKS on hard-fail red flags. `review` and `sweep` are report-only.

★ 2
odysseyalive
odysseyalive/claude-workforce

text-eval

Evaluate written prose for AI-generation tells and register drift — mechanical character and punctuation defects, clustered judgment-class signals, citation integrity, and conversational register. Use after writing or editing any prose a person will read, when asked to check whether text reads as AI-generated, or before publishing copy. Grades against a cited catalog with clustering thresholds and hard rows that fire on first occurrence. Report-only.

★ 2
odysseyalive
odysseyalive/claude-workforce

shared-artifact

The house style for any shareable online artifact — a claude.ai Artifact, a published HTML page, a report or brief someone will be sent a link to. Use before writing or republishing any artifact page, when asked to create, share, publish or clean up an online artifact, and when deciding between an HTML page and a Claude Docs document. Carries the token set, the dark-mode contract, the briefing-binder layout, a starter template, and the sharing hygiene rules.

★ 2
odysseyalive
odysseyalive/claude-workforce

security-evaluator

Evaluate a code change for web-security flaws — OWASP Top 10:2025 classes as source-review classes, taint signals from source to sink, and a per-language sink appendix. Use after writing or editing code that handles input, auth, data access, templating, deserialization, or external requests; when asked to security-review a change, check for injection/XSS/SSRF/authz flaws, or evaluate the security of what was just written. Report-only, candidate-tier by construction.

★ 2
odysseyalive
odysseyalive/claude-workforce

records-code-map

The code map for this project — where a file's sections and definitions are by line number, which files and lines mention a topic, and which checks, fixtures and cases cover a file. Use before searching or reading code to find something, before changing a file, and when deciding which test to run after an edit. The map is generated from the files on every call and never stored.

★ 2
odysseyalive
odysseyalive/claude-workforce

code-evaluator

Evaluate code to prevent common AI coding mistakes — dead code, duplication, complexity hotspots, reinvented helpers, leftover scaffolding. Two functions plus a pre-write advisor. Use after writing or editing code, when asked to review code quality, clean up the codebase, find unused code, find duplicates, check complexity, or evaluate what an AI just wrote. Commands: review (post-write), sweep (full codebase).

★ 2