Skip to content
Agentmart
Submit a tool

prompt-registry

Maintain the .generated-prompts/ register: read before creating any artifact to infer project conventions, write/update after creation.

Skill by jterratsdev

IndexedBSD-3-Clause
Write a review

Chalk Labs

Need help deploying prompt-registry?

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.

Book a call

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/jterratsdev-prompt-registry-b1951b

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.

We use your email only for this newsletter. Privacy

About

Maintain the .generated-prompts/ register: read before creating any artifact to infer project conventions, write/update after creation. Keeps the latest prompt that produced each component so the team can trace every generated artifact back to its origin. USE FOR: generated prompts, prompt history, prompt register, artifact traceability, prompt registry, generated apex, generated lwc, generated flow, generated component, vibe coding history, prompt persistence, ai prompt log. Active for Developer, Architect, Admin, BA, UX, PM, DevOps, MuleSoft, QA, OmniStudio, CRMA, Data Cloud, Security profiles.

Use cases: design, frontend, testing, devops

No 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/prompt-registry

What's inside

Skill name
prompt-registry
Description
Maintain the .generated-prompts/ register: read before creating any artifact to infer project conventions, write/update after creation. Keeps the latest prompt that produced each component so the team can trace every generated artifact back to its origin. USE FOR: generated prompts, prompt history, prompt register, artifact traceability, prompt registry, generated apex, generated lwc, generated flow, generated component, vibe coding history, prompt persistence, ai prompt log. Active for Developer, Architect, Admin, BA, UX, PM, DevOps, MuleSoft, QA, OmniStudio, CRMA, Data Cloud, Security profiles.
License
BSD-3-Clause
Instructions
75 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Prompt Registry

## Overview

`.generated-prompts/` is a commit-tracked directory at the repo root.
Each file registers the AI prompts that created or substantially changed
artifacts of a given type. One entry per component. Latest prompt only.
The git history holds the version trail.

## Before creating any artifact (MANDATORY)

1. Check if `.generated-prompts/<type>.md` exists.
2. If it exists, read the **entire file** before generating the artifact.
3. Use existing entries to infer:
   - Naming conventions in use
   - Data layer strategy (dynamic queries utility, selector layer, inline SOQL, etc.)
   - Patterns already established (trigger handler style, flow sub-flow depth, etc.)
   - Sharing model decisions
   - Any project-specific constraints recorded in prior prompts
4. Generate the new artifact **consistent with those conventions**.

## After creating or substantially changing an artifact (MANDATORY)

1. Open the corresponding `.generated-prompts/<type>.md`.
2. Search for an existing `## <ComponentName>` heading.
3. **No existing entry** → append a new entry at the bottom of the file.
4. **Entry exists** → update in place: increment **Iterations**, update **Updated**, replace **Prompt** with the refined prompt.
5. Never stack multiple versions. Only the latest prompt lives in the file.

## What counts as a substantial change

| Counts | Does NOT count |
|--------|---------------|
| New method or responsibility | Typo fix |
| New business requirement | Formatting change |
| Pattern change (e.g. @future → Queueable) | Single-line correction |
| Architectural refactor | Test assertion adjustment |
| New integration or dependency | Comment update |

## Register file reference

| File | Artifacts covered | Active profiles |
|------|------------------|-----------------|
| `apex.md` | Apex classes (.cls) | developer, architect |
| `lwc.md` | LWC (.js / .html / .js-meta.xml) | developer, ux |
| `flows.md` | Flows (.flow-meta.xml) | developer, admin, ba |
| `triggers.md` | Apex triggers + handlers (.trigger) | developer |
| `visualforce.md` | Visualforce pages and components | developer |
| `aura.md` | Aura components (.cmp / .app) | developer |
| `omnistudio.md` | OmniScripts, FlexCards, Integration Procedures | omnistudio |
| `metadata.md` | CustomObjects, CustomFields, ValidationRules, PermissionSets, CMDT, Platform Events, FlexiPages, NamedCredentials | developer, architect, admin, security |
| `diagrams.md` | Architecture diagrams (Mermaid / Lucid / draw.io) | architect, ba, ux, pm |
| `cicd.md` | Pipeline YAML, deployment scripts, GitHub Actions, Azure Pipelines | devops, mulesoft |
| `docs.md` | Generated documentation (ADRs, runbooks, data models, user guides) | architect, ba, ux, pm, devops, mulesoft, crma, data360, security |
| `tests.md` | Test plans, Playwright specs, Apex test classes | qa |

## Entry format

```markdown
## <ComponentName>
- **Created:** YYYY-MM-DD
- **Updated:** YYYY-MM-DD   ← omit if never updated
- **Iterations:** N          ← increment on each substantial change

### Key decisions
- <Pattern / constraint / design choice that shaped the component>

### Prompt
\`\`\`
<the final prompt, summarized to key decisions if over 500 words>
\`\`\`
---
```

From jterratsdev/smart-deployment, BSD-3-Clause.

More from jterratsdev/smart-deployment

Signals

Stars
0
Forks
0
Open issues
14
Last commit (this folder)
Aug 5, 2026 (2 months ago)
Last release
Sep 29, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
BSD-3-Clause
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from jterratsdev

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 prompt-registry 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.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying prompt-registry?

CallGet help
Cite this page

prompt-registry skill. Agent Mart. https://agentmart.dev/skills/jterratsdev-prompt-registry-b1951b (last updated 2026-10-24)