lmk
Use when the user says 'LMK when you're done', 'let me know', 'notify me', 'ping me when you're done', or says you are stepping away and wants a phone push…
Skill by courtneyr-dev
Chalk Labs
Need help deploying lmk?
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/courtneyr-dev-lmk
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
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/lmk
What's inside
- Skill name
lmk- Description
- Use when the user says 'LMK when you're done', 'let me know', 'notify me', 'ping me when you're done', or says you are stepping away and wants a phone push when the work finishes.
- License
- MIT
- Instructions
- 30 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (2)
- SKILL.md
- lmk-notify.sh · scripts/
SKILL.md (first lines)
# lmk — Pushover push when the task finishes ## Overview An end-of-task delivery requirement, not a separate task: complete and verify the requested work first, then send exactly one notification. The push is a heads-up — the conversation always carries the complete result. ## Sending ```bash ~/.claude/skills/lmk/scripts/lmk-notify.sh "Short task title" "One to three short lines: what finished and the outcome" ``` Credentials load from the macOS Keychain inside the script. Never inline them in commands, output, or this file. Priority is normal by default. `-p -1` quiet — only when the user asked for quiet delivery. `-p 1` high — only for a genuinely important alert. `-p 2` emergency — only when the user explicitly requested an emergency alert. ## Message content - Title names the task; the message says what finished and its outcome, so the push identifies which task it belongs to. - Keep it generic: no URLs, email addresses, contact names, file paths, document names, payment details, health information, or credentials — unless the user explicitly asked for that exact detail in the push. - Final outcome only. No progress pushes unless you explicitly asked for them. ## Verifying delivery - Sent = script exits 0 and prints JSON containing `"status":1`. Note the returned `request` id in the conversation for troubleshooting. - `"status":0` = not sent: report the `errors` array in the conversation. - Any other failure (network error, missing credentials) = not sent: report it plainly. Never claim the push was sent without seeing `"status":1`. - Exit 2 = credentials missing from the Keychain (service `pushover-lmk`, accounts `user_key` and `app_token`). Ask the user to re-add them there; never store them in git-tracked files.
From courtneyr-dev/agent-skills, MIT.
More from courtneyr-dev/agent-skills
- 0.529score
ollie
courtneyr-dev
Use when working with the Ollie block theme or Ollie Pro: building a page or site in Ollie, styling, colors, typography, buttons, spacing, block markup…
SkillBFreshness: BClaude Code +9 - 0.529score
anti-slop-git-writing
courtneyr-dev
Use when writing a commit message, PR or MR title and body, GitHub or GitLab issue, bug report, or code-review comment, and when a bug found while testing or…
SkillBFreshness: BClaude Code +9 - 0.529score
job-search
courtneyr-dev
Run a repeatable job-search scan across job boards, company ATS pages, email alerts, LinkedIn, and community chat; diff against the previous run to separate…
SkillBFreshness: BClaude Code +9 - 0.529score
credit-routing
courtneyr-dev
Use at the start of any non-trivial task, when deciding whether to delegate, when a task has failed twice, before escalating model or effort, or when the user…
SkillBFreshness: BClaude Code +9 - 0.529score
obsid-link-builder
courtneyr-dev
Use when asked to create or normalize shareable obsid.net links for Obsidian notes, convert obsidian:// links, or check the URL encoding of vault and file…
SkillBFreshness: BClaude Code +9 - 0.529score
church-bulletin-to-obsidian
courtneyr-dev
Use when the user shares a church bulletin (image or text) or says 'church bulletin' and wants the sermon-notes file for the vault.
SkillBFreshness: BClaude Code +9 - 0.529score
plaud
courtneyr-dev
Use when the user says 'Plaud', 'my recordings', 'what did I record', or wants a Plaud transcript, summary, digest, follow-up, or export.
SkillBFreshness: BClaude Code +9 - 0.529score
gatherer
courtneyr-dev
Use when the user says 'gather my work', 'what's on my plate', or 'daily gather', or when a review needs your open GitHub issues and PRs, watched Trac…
SkillBFreshness: BClaude Code +9 - 0.524score
github-repo
courtneyr-dev
Use when the user says 'make my repo look good', 'prepare this repo for open source', or asks to audit or add a README, CONTRIBUTING, SECURITY…
SkillBFreshness: BClaude Code +9 - 0.524score
codex-first
courtneyr-dev
Use when a task is mechanical enough to specify completely (implementation from a settled design, refactor, migration, tests, coverage, CI fix, dependency…
SkillBFreshness: BClaude Code +9 - 0.524score
email-draft-review
courtneyr-dev
Use when the user says 'draft my email replies', 'handle my inbox', 'triage Gmail', or asks to prepare (never send) replies to the emails that need answers.
SkillBFreshness: BClaude Code +9 - 0.524score
field-notes-draft
courtneyr-dev
Use when the user says 'Field Notes', asks for the Thursday or Friday Field Notes review, wants newsletter candidates ranked, or wants the Saturday issue…
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 21, 2026 (1 month ago)
- Last release
- Sep 5, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/courtneyr-dev/agent-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from courtneyr-dev
- 0.570score
block-runner
courtneyr-dev
Turn WordPress page content or authored design HTML into valid, native, editable Gutenberg blocks, or plan a reusable named registered block for deterministic…
SkillAFreshness: AClaude Code +9 - 0.559score
better-documents
courtneyr-dev
Use when asked to write or review a memo, deck, proposal, report, brief, one-pager, or email, or when Courtney says 'review my doc', 'does this land', 'is…
SkillAFreshness: AClaude Code +9 - 0.559score
agents-md-lint
courtneyr-dev
Audit and trim AI agent instruction files (AGENTS.md, CLAUDE.md, CONVENTIONS.md, .cursorrules, etc.) by testing which facts an AI agent can discover from code…
SkillAFreshness: AClaude Code +9 - 0.559score
add-expert
courtneyr-dev
Add a new expert to the Remotion experts page — places the headshot in docs and promo-pages, appends the entry to experts-data.tsx, and renders the expert card.
SkillAFreshness: AClaude Code +9 - 0.559score
aim
courtneyr-dev
Use when the user is starting a new decision, framing a question for AI, or about to prompt for analysis on a real call.
SkillAFreshness: AClaude Code +9 - 0.556score
book-review
courtneyr-dev
Draft a long-form book review from your Reader highlights — synthesizing the book with your broader reading history to generate original arguments
SkillAFreshness: AClaude 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 lmk 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
lmk skill. Agent Mart. https://agentmart.dev/skills/courtneyr-dev-lmk (last updated 2026-10-24)