Update to PromptingCraft.com
Snapshot Oct 29, 2026 · 12:07 UTC · version 0.4.0
Declared capabilities changed
Full description — Now says: Write, improve and review execution-ready prompts and task handoffs for coding agents such as Codex, Claude Code and Cursor, using source-backed
Observed in instructions or declared skills. Runtime behavior has not been tested.
Up to 10 plugins free · no card required.
All fields and original values.
Full description
Oct 28, 2026 · 18:06 UTC
Turn development discussions into execution-ready prompts for coding agents such as Codex, Claude Code and Cursor, with source-backed official
Oct 29, 2026 · 12:07 UTC
Write, improve and review execution-ready prompts and task handoffs for coding agents such as Codex, Claude Code and Cursor, using source-backed
Long description
Oct 28, 2026 · 18:06 UTC
AI assistants turn a development discussion into one clear, execution-ready prompt for a coding agent such as Codex, Claude Code or Cursor. Model-specific recommendations come only from official OpenAI and Anthropic documentation, and Cu...
Oct 29, 2026 · 12:07 UTC
you write, review and improve prompts for coding agents such as Codex, Claude Code and Cursor. Turn a development discussion into clear, execution-ready instructions for an AI developer. Bundled model-specific records include official Op...
Declared skills
Oct 28, 2026 · 18:06 UTC
[{"description":"Turn a development discussion into an execution-ready coding-agent prompt, or write, improve, or review a Claude Code or Codex handoff. Use for prompt-authoring requests, not merely software-development mentions. Develop...
Oct 29, 2026 · 12:07 UTC
[{"description":"Write, improve or review prompts and task handoffs for coding agents, including instructions for an AI developer. Not for coding execution, image-generation prompts or marketing copy. Developed by the dondego.com team.",...
Composer icon dark url
Oct 28, 2026 · 18:06 UTC
https://files.openai.com/content?id=file_00000000aff88243b76de79c069f5411
Oct 29, 2026 · 12:07 UTC
https://files.openai.com/content?id=file_000000003ec081f4bfca69ae885aa941
Compare saved observations
Download comparison JSONFull technical diff · 11 changed fields
changed /release/description
"Turn development discussions into execution-ready prompts for coding agents such as Codex, Claude Code and Cursor, with source-backed official guidance. Developed by the dondego.com team."
"Write, improve and review execution-ready prompts and task handoffs for coding agents such as Codex, Claude Code and Cursor, using source-backed guidance. Developed by the dondego.com team."
changed /release/id
"pluginrel_0db14ff398c88191bbb7a64b4137e564"
"pluginrel_2f10a485c3d0819189595242b768b786"
changed /release/interface/composer_icon_dark_url
"https://files.openai.com/content?id=file_00000000aff88243b76de79c069f5411"
"https://files.openai.com/content?id=file_000000003ec081f4bfca69ae885aa941"
changed /release/interface/composer_icon_url
"https://files.openai.com/content?id=file_000000007fa4824391431b91b2abd6bc"
"https://files.openai.com/content?id=file_000000006b4081f48e3253ecd1fb3b81"
changed /release/interface/default_prompt
"Turn our discussion into an execution-ready Codex prompt."
"Write a Codex prompt to fix this bug without changing the API."
changed /release/interface/default_prompts
[ "Turn our discussion into an execution-ready Codex prompt.", "Review this Claude Code task without changing its scope.", "Apply relevant official guidance and preserve my requirements." ]
[ "Write a Codex prompt to fix this bug without changing the API.", "Help me tell Claude Code what to implement from our discussion.", "Review my Cursor agent prompt for missing requirements." ]
changed /release/interface/logo_url
"https://files.openai.com/content?id=file_0000000079188243a3960d797628b26e"
"https://files.openai.com/content?id=file_0000000059f8820a85c3cfc45ff99a3b"
changed /release/interface/logo_url_dark
"https://files.openai.com/content?id=file_00000000265c8243be6f8bd5162c3c5c"
"https://files.openai.com/content?id=file_00000000791081f4af3d476dcf1e319f"
changed /release/interface/long_description
"PromptingCraft.com helps AI assistants turn a development discussion into one clear, execution-ready prompt for a coding agent such as Codex, Claude Code or Cursor.\n\nIt identifies the task contract (requirements, decisions already made, permissions and open questions), checks applicable official guidance from AI developers, writes a draft, critiques it against the contract, and returns one final copyable prompt. Optional ideas stay optional, unresolved choices stay open, and no new permissions are added.\n\nIt can also review an existing prompt: it points out unnecessary instructions and changes in scope, and when a prompt is already suitable it says so and leaves it unchanged.\n\nModel-specific recommendations come only from official OpenAI and Anthropic documentation, and Cursor behavior from Cursor's documentation. A public source registry records where each recommendation comes from, and the project's own methodology is labeled separately from official guidance.\n\nThe skill works on its own. The optional PromptingCraft.com guidance server (mcp.promptingcraft.com) adds read-only access to the same ledger: it lists official guidance for a target agent, model family and topic, returns a record with its source, limits and verification date, and checks whether an official source page changed since it was verified. Its tools take only fixed categories and identifiers as input and do not ask for task text.\n\nChecking current guidance depends on the tools and access available in the conversation. When the server or live retrieval is unavailable, PromptingCraft.com says so and states whether it used other official sources, dated cached guidance or none.\n\nPromptingCraft.com writes and reviews prompts only. It does not run the development task, edit code or grant permissions, and it does not guarantee better downstream results. It needs no account, credentials or setup, and no PromptingCraft.com service receives your prompts. Evaluation methods, results and limits are published at promptingcraft.com/benchmarks.\n\nPromptingCraft.com is developed independently and is not affiliated with or endorsed by OpenAI, Anthropic or Cursor.\n\nDeveloped by the dondego.com team."
"PromptingCraft.com helps you write, review and improve prompts for coding agents such as Codex, Claude Code and Cursor. Turn a development discussion into clear, execution-ready instructions for an AI developer.\n\nIt identifies the task contract (requirements, decisions already made, permissions and open questions), checks applicable official guidance from AI developers, writes a draft, critiques it against the contract, and returns one final copyable prompt. Optional ideas stay optional, unresolved choices stay open, and no new permissions are added.\n\nIt can also review an existing prompt: it points out unnecessary instructions and changes in scope, and when a prompt is already suitable it says so and leaves it unchanged.\n\nBundled model-specific records include official OpenAI and Anthropic guidance and scoped DeepSeek and Kimi API tool-use guidance; Cursor behavior comes from Cursor documentation. A public source registry records where each recommendation comes from, and the project's own methodology is labeled separately from official guidance.\n\nThe skill works on its own. The optional PromptingCraft.com guidance server (mcp.promptingcraft.com) adds read-only access to its deployed guidance ledger: it lists official guidance for a target agent, model family and topic, returns a record with its source, limits and verification date, and checks whether an official source page changed since it was verified. Its tools take only fixed categories and identifiers as input and do not ask for task text.\n\nChecking current guidance depends on the tools and access available in the conversation. When the server or live retrieval is unavailable, PromptingCraft.com says so and states whether it used other official sources, dated cached guidance or none.\n\nPromptingCraft.com writes and reviews prompts only. It does not run the development task, edit code or grant permissions, and it does not guarantee better downstream results. It needs no PromptingCraft.com account or credentials; installation and connection availability depend on the host. The guidance tools take only fixed categories and identifiers, and no PromptingCraft.com service receives your prompts. Evaluation methods, results and limits are published at promptingcraft.com/benchmarks.\n\nPromptingCraft.com is developed independently and is not affiliated with or endorsed by OpenAI, Anthropic or Cursor.\n\nDeveloped by the dondego.com team."
changed /release/skills
[
{
"description": "Turn a development discussion into an execution-ready coding-agent prompt, or write, improve, or review a Claude Code or Codex handoff. Use for prompt-authoring requests, not merely software-development mentions. Developed by the dondego.com team.",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "PromptingCraft.com",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "pen",
"short_description": "Source-backed agent prompts"
},
"name": "promptingcraft",
"plugin_release_skill_id": "pluginrsk_6acdf50d424c81919a4ef541b1734f75"
}
][
{
"description": "Write, improve or review prompts and task handoffs for coding agents, including instructions for an AI developer. Not for coding execution, image-generation prompts or marketing copy. Developed by the dondego.com team.",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "PromptingCraft.com",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "code",
"short_description": "Source-backed agent prompts"
},
"name": "promptingcraft",
"plugin_release_skill_id": "pluginrsk_6ae2788d927881919cbafac14bc010e9"
}
]changed /release/version
"0.3.0"
"0.4.0"
Full snapshot data
{
"canonical_app_id": "asdk_app_6acde71d1ddc81918d6095dba60b6023",
"connector_id": "asdk_app_6acde71d1ddc81918d6095dba60b6023",
"created_at": "2026-10-13T10:05:44.423150Z",
"discoverability": "LISTED",
"id": "plugin_asdk_app_6acde71d1ddc81918d6095dba60b6023",
"is_template": false,
"is_template_instance": false,
"is_v2_template": false,
"name": "promptingcraft",
"release": {
"app_ids": [
"asdk_app_6acde71d1ddc81918d6095dba60b6023"
],
"app_manifest": {
"apps": {
"promptingcraft-guidance": {
"id": "asdk_app_6acde71d1ddc81918d6095dba60b6023",
"required": true
}
}
},
"app_templates": [],
"description": "Write, improve and review execution-ready prompts and task handoffs for coding agents such as Codex, Claude Code and Cursor, using source-backed guidance. Developed by the dondego.com team.",
"display_name": "PromptingCraft.com",
"id": "pluginrel_2f10a485c3d0819189595242b768b786",
"interface": {
"brand_color": "#15191F",
"capabilities": [
"Turns a development discussion into one execution-ready coding-agent prompt",
"Reviews an existing prompt and flags scope changes and unnecessary instructions",
"Leaves an already suitable prompt unchanged",
"Preserves requirements, decisions, permissions and unresolved choices",
"Checks applicable official AI-developer guidance and labels its freshness",
"Checks whether official sources changed since they were verified",
"Separates official guidance, project methodology and optional suggestions"
],
"category": "Developer Tools",
"composer_icon_dark_url": "https://files.openai.com/content?id=file_000000003ec081f4bfca69ae885aa941",
"composer_icon_url": "https://files.openai.com/content?id=file_000000006b4081f48e3253ecd1fb3b81",
"default_prompt": "Write a Codex prompt to fix this bug without changing the API.",
"default_prompts": [
"Write a Codex prompt to fix this bug without changing the API.",
"Help me tell Claude Code what to implement from our discussion.",
"Review my Cursor agent prompt for missing requirements."
],
"developer_name": "Aleksandr Prokofyev",
"logo_url": "https://files.openai.com/content?id=file_0000000059f8820a85c3cfc45ff99a3b",
"logo_url_dark": "https://files.openai.com/content?id=file_00000000791081f4af3d476dcf1e319f",
"long_description": "PromptingCraft.com helps you write, review and improve prompts for coding agents such as Codex, Claude Code and Cursor. Turn a development discussion into clear, execution-ready instructions for an AI developer.\n\nIt identifies the task contract (requirements, decisions already made, permissions and open questions), checks applicable official guidance from AI developers, writes a draft, critiques it against the contract, and returns one final copyable prompt. Optional ideas stay optional, unresolved choices stay open, and no new permissions are added.\n\nIt can also review an existing prompt: it points out unnecessary instructions and changes in scope, and when a prompt is already suitable it says so and leaves it unchanged.\n\nBundled model-specific records include official OpenAI and Anthropic guidance and scoped DeepSeek and Kimi API tool-use guidance; Cursor behavior comes from Cursor documentation. A public source registry records where each recommendation comes from, and the project's own methodology is labeled separately from official guidance.\n\nThe skill works on its own. The optional PromptingCraft.com guidance server (mcp.promptingcraft.com) adds read-only access to its deployed guidance ledger: it lists official guidance for a target agent, model family and topic, returns a record with its source, limits and verification date, and checks whether an official source page changed since it was verified. Its tools take only fixed categories and identifiers as input and do not ask for task text.\n\nChecking current guidance depends on the tools and access available in the conversation. When the server or live retrieval is unavailable, PromptingCraft.com says so and states whether it used other official sources, dated cached guidance or none.\n\nPromptingCraft.com writes and reviews prompts only. It does not run the development task, edit code or grant permissions, and it does not guarantee better downstream results. It needs no PromptingCraft.com account or credentials; installation and connection availability depend on the host. The guidance tools take only fixed categories and identifiers, and no PromptingCraft.com service receives your prompts. Evaluation methods, results and limits are published at promptingcraft.com/benchmarks.\n\nPromptingCraft.com is developed independently and is not affiliated with or endorsed by OpenAI, Anthropic or Cursor.\n\nDeveloped by the dondego.com team.",
"plugin_category_id": "developer tools",
"privacy_policy_url": "https://promptingcraft.com/privacy",
"screenshot_urls": [],
"short_description": "Source-backed agent prompts",
"terms_of_service_url": "https://promptingcraft.com/terms",
"website_url": "https://promptingcraft.com"
},
"keywords": [
"agent-skills",
"prompt-engineering",
"coding-agents",
"codex",
"claude-code",
"cursor",
"agent-prompts",
"prompt-review",
"task-contracts",
"official-guidance",
"open-source"
],
"mcp_servers": [
{
"key": "promptingcraft-guidance",
"metadata": {
"headers": {},
"type": "streamable-http",
"url": "https://mcp.promptingcraft.com/mcp"
}
}
],
"onboarding_skill_name": null,
"requires_local_executor": false,
"skills": [
{
"description": "Write, improve or review prompts and task handoffs for coding agents, including instructions for an AI developer. Not for coding execution, image-generation prompts or marketing copy. Developed by the dondego.com team.",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "PromptingCraft.com",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "code",
"short_description": "Source-backed agent prompts"
},
"name": "promptingcraft",
"plugin_release_skill_id": "pluginrsk_6ae2788d927881919cbafac14bc010e9"
}
],
"version": "0.4.0"
},
"scope": "GLOBAL",
"share_url": "https://chatgpt.com/plugins/plugin_asdk_app_6acde71d1ddc81918d6095dba60b6023?open_in_app",
"status": "ENABLED"
}SHA-256 of public snapshot: 678a839288fb67371553d46c0d30983a4bafa952319614e520ccabcc8d3a20e1