melech-make-it-click
Recover when the agent's explanation did not land by finding the smallest thing blocking understanding and replacing the failed mental model with a concrete…
Skill by AdirD
Chalk Labs
Need help deploying melech-make-it-click?
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/adird-melech-make-it-click
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: 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 and code. 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/melech-make-it-click
What's inside
- Skill name
melech-make-it-click- Description
- Recover when the agent's explanation did not land by finding the smallest thing blocking understanding and replacing the failed mental model with a concrete one.
- License
- MIT
- Instructions
- 61 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- examples.md · references/
SKILL.md (first lines)
# Make It Click The user invoked this because your previous explanation was smart, dense, or technically correct, but they still do not understand it. Do not defend, summarize, or merely shorten that explanation. **Find the smallest thing preventing the user from understanding. Explain that first using the most concrete route available. Do not simplify the entire previous answer; replace its failed mental model.** ## Recover the thread Use the conversation, especially the user's latest wording, to infer the exact sticking point. Often it is much smaller than the topic: - "Are we dropping the remaining data?" - "Where does this value exist while the program runs?" - "Why does this extra identifier exist at all?" Answer that question first, even if the previous answer covered ten other things. If the user's confusion is visible from context, do not ask them to identify it again. If two or more sticking points are equally plausible, ask one narrow question that distinguishes them instead of guessing. ## Change the route The previous route already failed. Choose a different one: - walk one concrete input through the system; - show a tiny value or code example; - state the before/after in plain language; - use an analogy only when it maps cleanly; - remove an unnecessary concept if complexity—not wording—is the problem. Prefer real nouns and actions over category names. Introduce one idea at a time. Define unavoidable jargon at the moment it appears. ## Response shape 1. Lead with the direct answer to the likely sticking point. 2. Build the smallest concrete model that makes that answer true. 3. Reconnect it to the original topic in one sentence. 4. Stop. Offer deeper detail only after the core idea has landed. There is no mandatory analogy, numbered walkthrough, or ELI5 voice. Match the route to the confusion. The outcome is understanding, not a particular format. ## Hard boundaries - Do not repeat the same explanation with shorter words. - Do not restart the whole topic from first principles unless that is the gap. - Do not preserve jargon just because it is precise. - Do not dump every caveat, branch, implementation detail, or adjacent concept. - Do not speak to the user like a child or announce that you are "dumbing it down." - Do not turn the recovery into another essay. - Do not ask "does that make sense?" before giving the new explanation. For grounded examples of three different recovery routes, see [`references/examples.md`](references/examples.md).
From AdirD/agent-shell-hamelech, MIT.
More from AdirD/agent-shell-hamelech
- 0.662score
melech-cost
AdirD
Show what coding-agent sessions cost for every worktree of the current repo — Cursor, Claude Code, and Codex — as handoff-style cards with dollars and tokens.
SkillAFreshness: A★ 45Claude Code +9 - 0.662score
melech-plan-review
AdirD
Review a solution before approving it, like a GitHub changes tab: a file tree of red and green pseudo-code the user can comment on inline, then answer…
SkillAFreshness: A★ 45Claude Code +9 - 0.662score
melech-live-browser
AdirD
Operate the user's already-open, logged-in Chrome tabs through Chrome DevTools MCP.
SkillAFreshness: A★ 45Claude Code +9 - 0.662score
melech-handoff
AdirD
List and continue coding-agent transcripts across Cursor, Claude Code, Codex, Gemini, and other local agents.
SkillAFreshness: A★ 45Claude Code +9 - 0.659score
melech-tidy
AdirD
Adaptive diff reduction — prune dead code residue, shake prompt bloat, remove cosmetic diff noise, and propose edge-case trades that drop rare-case handling…
SkillAFreshness: A★ 45Claude Code +9 - 0.659score
melech-debug-mode
AdirD
Debug or verify a local UI end to end in the user's existing Chrome tab, with temporary runtime probes and a manual browser fallback.
SkillAFreshness: A★ 45Claude Code +9 - 0.656score
melech-pr-gardener
AdirD
Tend one explicit GitHub author's open PRs and keep them green — one stateless pass per scheduled run.
SkillAFreshness: A★ 45Claude Code +9 - 0.651score
melech-smart-comments
AdirD
Preserve code intent with selective comments and protect meaningful existing comments.
SkillAFreshness: A★ 45Claude Code +9 - 0.651score
melech-8020
AdirD
Find the smallest useful path to a product or engineering outcome.
SkillAFreshness: A★ 45Claude Code +9 - 0.622score
melech-roi
AdirD
Grade whether a change's complexity and blast radius are actually worth the benefit it delivers, using an itemized ROI receipt and rankings among solutions…
SkillBFreshness: B★ 45Claude Code +9 - 0.617score
melech-consult
AdirD
Get an independent verdict on an AI-proposed plan, fix, architecture, or claim by verifying its premises against the real artifact, then dispatching a panel…
SkillBFreshness: B★ 45Claude Code +9 - 0.616score
melech-cr-clone-trainer
AdirD
Build or resync a private reviewer that learns your GitHub code-review style.
SkillBFreshness: B★ 45Claude Code +9
Signals
- Stars
- 45
- Forks
- 5
- Open issues
- 0
- Last commit (this folder)
- Sep 15, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/AdirD/agent-shell-hamelech
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from AdirD
- 0.662score
melech-cost
AdirD
Show what coding-agent sessions cost for every worktree of the current repo — Cursor, Claude Code, and Codex — as handoff-style cards with dollars and tokens.
SkillAFreshness: A★ 45Claude Code +9 - 0.662score
melech-handoff
AdirD
List and continue coding-agent transcripts across Cursor, Claude Code, Codex, Gemini, and other local agents.
SkillAFreshness: A★ 45Claude Code +9 - 0.662score
melech-live-browser
AdirD
Operate the user's already-open, logged-in Chrome tabs through Chrome DevTools MCP.
SkillAFreshness: A★ 45Claude Code +9 - 0.662score
melech-plan-review
AdirD
Review a solution before approving it, like a GitHub changes tab: a file tree of red and green pseudo-code the user can comment on inline, then answer…
SkillAFreshness: A★ 45Claude Code +9 - 0.659score
melech-debug-mode
AdirD
Debug or verify a local UI end to end in the user's existing Chrome tab, with temporary runtime probes and a manual browser fallback.
SkillAFreshness: A★ 45Claude Code +9 - 0.659score
melech-tidy
AdirD
Adaptive diff reduction — prune dead code residue, shake prompt bloat, remove cosmetic diff noise, and propose edge-case trades that drop rare-case handling…
SkillAFreshness: A★ 45Claude 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 melech-make-it-click 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
melech-make-it-click skill. Agent Mart. https://agentmart.dev/skills/adird-melech-make-it-click (last updated 2026-10-24)