automation-handover
Hand a verified automation over to its users with a short explanation, a visible demo through the real UI, a demonstrated stop path, and one small user action…
Skill by smlfg
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/smlfg-automation-handover
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: design
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
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/automation-handover
What's inside
- Skill name
automation-handover- Description
- Hand a verified automation over to its users with a short explanation, a visible demo through the real UI, a demonstrated stop path, and one small user action they perform themselves. Use when an automation is technically accepted and needs to be handed to the people who'll run it.
- License
- MIT
- Instructions
- 37 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Automation Handover Hand over one coherent function in the agreed scope after its technical verification. Standalone. Unverified parts stay explicitly open; a demo doesn't replace missing technical acceptance. A guided user action is not a general approval gate for technical work. ## Explanation and visible demo - Briefly explain: what triggers the function, what the background service does, where the user sees the result. Read the explanation aloud if wanted and a speech capability is available; otherwise say so and provide a short speakable text. Use the existing environment; don't require a specific local program. - Bring the right page and area visibly to the front. Announce scrolls and tab changes concretely. Show one proven test case through the actual UI to a usable result. Really open linked originals and relevant files: message text, file name and an opened attachment are different evidence. - Explanation and browser control follow one flow: explain the section, show the matching action, leave the result readable. With several agents, agree on one speaker and one browser driver. - Show one relevant, documented failure and explain detection, effect and proven recovery. An existing error view may suffice; don't re-provoke side effects just for the demo. Without a safe real failure test, label the behaviour unverified. ## Stop and own operation - Show the actual stop path. Explain separately whether it prevents new triggers, ends running work, or only pauses. For an agreed stop demo, read the state back, check open work separately, and restore the agreed end state. Claim catch-up of missed events only with evidence. - Provide one small user action with a recognisable result (open an original, trigger an approved test case). Say beforehand how they'll recognise success. Hand over the browser explicitly and pause your browser calls and changes to the observed object until they report done. A generic "ok" doesn't prove a successful action; check the result where access and scope allow. ## Operating guide and close - Leave a short guide with actual paths: start/trigger, check success, recognise and fix errors, stop, restart, known limits. Link existing evidence instead of scattering internals into the guide. - Record technical acceptance, demo shown, user action successfully performed, and production activation separately. While an agreed user action or other criterion is missing, that part stays open; independent work may continue. ## Example ```text Explain (30 s): "New invoice mail arrives → flow parses it → row appears in Invoices." Demo: sent test mail 14:02 → row 61 visible → attachment opened. Failure: run #120 (malformed PDF) → alert mail → manual re-run fixed it. Stop: Flow → Turn off. Prevents new triggers; running run #121 finished normally. Your turn: forward test-invoice.eml to the inbox. Success = a new row within 2 min. Status: tech-accepted ✓ demo ✓ user action ✓ production ✗ (owner decides) ``` ## Use case You built an automation for a non-technical colleague. Instead of a link and "it's live", this skill runs a short guided handover: they see it work, see it fail and recover, learn how to stop it, and do one real action themselves.
From smlfg/HAI-skills-registry, MIT.
More from smlfg/HAI-skills-registry
- 0.570score
pdf-to-md
smlfg
Convert PDFs (lecture slides, scripts, books) into clean Markdown/text an agent can read and search, with automatic fallback to Tesseract OCR for scanned PDFs.
SkillAFreshness: AClaude Code +9 - 0.570score
archify-swarm
smlfg
Map a repository's architecture with several cheap/free models in parallel, verify every claimed file:line deterministically against the committed code, and…
SkillAFreshness: AClaude Code +9 - 0.565score
commit
smlfg
Create atomic git commits with a secrets/artifact safety check, green tests, and explicit human approval per commit.
SkillAFreshness: AClaude Code +9 - 0.565score
cross-model-review
smlfg
Get independent second, third and fourth opinions from different model families on a problem or solution, then synthesise convergence (validated) versus…
SkillAFreshness: AClaude Code +9 - 0.565score
experiment-to-project
smlfg
Turn an AI/agent experiment with several failed or half-working attempts into an evaluated, measurable project.
SkillAFreshness: AClaude Code +9 - 0.565score
github-community-checklist
smlfg
Audit a GitHub repo's community health files (description, README, license, code of conduct, contributing, security policy, issue/PR templates).
SkillAFreshness: AClaude Code +9 - 0.565score
skilleval
smlfg
Run the same task through several models or agents and score the artifacts against a pre-agreed, machine-checkable quality axis.
SkillAFreshness: AClaude Code +9 - 0.565score
subprocess-cli-pitfalls
smlfg
Diagnose Linux CLI commands that run in milliseconds in a terminal but hang or crawl when called via Python subprocess (or any non-TTY caller like cron or an…
SkillAFreshness: AClaude Code +9 - 0.565score
coursepack
smlfg
Push an entire course folder into Google NotebookLM and generate prioritised study media (audio, video, study guide) per topic and per exercise sheet, driven…
SkillAFreshness: AClaude Code +9 - 0.565score
podcast
smlfg
Produce an audio podcast from source material (doc, text, link, topic) via Google NotebookLM's MCP server.
SkillAFreshness: AClaude Code +9 - 0.565score
spoiler-free-shorts
smlfg
Add a short (60–90 s) NotebookLM video to each task of an existing interactive learning page, using a parallel example so the short never solves the task…
SkillAFreshness: AClaude Code +9 - 0.565score
visual-explainer
smlfg
Generate self-contained HTML explainers with SVG diagrams and interactive step-by-step animations for algorithms, data structures, systems or concepts.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 15, 2026 (13 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/smlfg/HAI-skills-registry
- Website
- human-agent-interface.com
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from smlfg
- 0.606score
HAI-MCP
smlfg
Model-agnostic MCP control plane for HAI: bounded missions, owner-gated actions, drift checks.
ConnectorAFreshness: ALocal★ 1↓ 47/wkClaude Code +5 - 0.570score
archify-swarm
smlfg
Map a repository's architecture with several cheap/free models in parallel, verify every claimed file:line deterministically against the committed code, and…
SkillAFreshness: AClaude Code +9 - 0.570score
pdf-to-md
smlfg
Convert PDFs (lecture slides, scripts, books) into clean Markdown/text an agent can read and search, with automatic fallback to Tesseract OCR for scanned PDFs.
SkillAFreshness: AClaude Code +9 - 0.565score
agentic-gate-verification
smlfg
Decide whether agentic work may proceed, be marked done, merge, or spawn more work.
SkillAFreshness: AClaude Code +9 - 0.565score
cross-model-review
smlfg
Get independent second, third and fourth opinions from different model families on a problem or solution, then synthesise convergence (validated) versus…
SkillAFreshness: AClaude Code +9 - 0.565score
commit
smlfg
Create atomic git commits with a secrets/artifact safety check, green tests, and explicit human approval per commit.
SkillAFreshness: AClaude Code +9
Cite this page
automation-handover skill. Agent Mart. https://agentmart.dev/skills/smlfg-automation-handover (last updated 2026-10-24)