PromptingCraft Guidance

Source-backed prompting and agent guidance for coding agents, with dated official references and freshness checks.

View on promptingcraft.com

Hosted MCP Server

npx add-mcp 'https://mcp.promptingcraft.com/mcp'

Installs into Claude Code, Codex, Cursor and more

Documentation

We’re live in ChatGPT and the official MCP Registry →

Official guidance.Zero prompt folklore.

One task, six stages.

Write a Claude Code handoff: add CSV export to the existing report view; reuse current columns, no backend change. Edits, tests and an MR are authorized; merge and deployment aren't.

Target agent named in the request: Claude Code. Executor model: not stated.

  • EXPLICIT_REQUIREDAdd CSV export to the existing report view add CSV export to the existing report view
  • EXPLICIT_REQUIREDUse the current columns reuse current columns
  • FORBIDDENBackend changes no backend change
  • EXPLICIT_REQUIREDAuthority granted: edits, tests, an MR Edits, tests and an MR are authorized
  • FORBIDDENMerge and deployment merge and deployment aren't
  • UNRESOLVEDEmpty-result behaviour was never discussedleft open — not invented

Methodology Classification is PromptingCraft.com’s own method, not a provider recommendation.

Official · AnthropicApplied

State output and constraints clearly; request above-and-beyond behavior explicitly rather than relying on inference.

Prompting best practices · retrieved 2026-10-12 · record claude-clear

Official · AnthropicApplied

Choose the simplest workflow that solves the task and add orchestration only when its quality benefit justifies latency and cost.

Building effective agents · retrieved 2026-10-12 · record claude-workflow-complexity

Official · AnthropicNot applied

If unsolicited additions occur, instruct the model to finish requested work and checks, then report helpful extras as suggestions.

Why not: this record applies to “Claude Sonnet 5.5 only”. The executor model was never established, so model-specific tuning is not transferred.

Implement CSV export, then ship it.

"Ship" invents merge/deploy authority. Missing column and backend constraints.

  • ship grants merge and deployment the user withheld.
  • Dropped: reuse current columns.
  • Dropped: no backend change.
Add CSV export to the existing report view using its current columns. Make no backend changes. Edits, tests and an MR are authorized; merge and deployment are not. Verify the export represents the chosen columns as valid CSV.

Optional suggestion: consult nearby export patterns; retain existing empty-result conventions if applicable rather than choosing a new one in this handoff.
  • Every required item is present; nothing forbidden is granted.
  • The unresolved empty-result choice stays an optional suggestion, not a gate.

A prompt can quietly change the task.

Rewrites tend to add authority, drop constraints and promote suggestions into requirements. PromptingCraft.com checks for exactly that.

Common driftWhat PromptingCraft.com checks
“Ship it” appears where only an MR was allowedGranted and withheld permissions are carried over exactly — no new merge, deploy or publish rights.
A constraint from the discussion disappearsEach required and forbidden item is traced from the original into the final prompt.
A nice idea becomes an acceptance gateNew ideas stay under “Optional suggestion”, never as completion criteria.
An open question gets silently decidedUnresolved choices remain open, or one focused question is asked.
A good prompt gets rewritten anyway“No material revision is necessary” is a valid outcome.

Promising results in a small, transparent evaluation.

The same model wrote prompts with and without PromptingCraft.com for five synthetic tasks. A blinded grader checked each one against what the user actually asked for.

One model configuration, ten outputs per condition, model grading and one disclosed scoring correction. It measures prompt fidelity, not better code.

Passing with PromptingCraft.com

8/103 defects

Passing without it

3/1016 defects

Prompt requests that loaded the skill

30/300/30 unrelated requests did

Every recommendation points back to its source.

The knowledge ledger holds 19 official recommendations from OpenAI, Anthropic, DeepSeek, and Kimi documentation, each with its applicable model, limits and retrieval date.

Curated 2026-10-12. Shown from commit 1edbc120. Dated snapshot — not live.

  • State the desired result and relevant supplied context; separate instructions from examples/reference data. Applies to: OpenAI text and reasoning models Prompt engineering · ledger line 14
  • For large document inputs, place long documents first and the query later; identify document sources and ground answers in relevant passages. Applies to: Current Claude families covered by the living page Prompting best practices · ledger line 185
  • Use simple direct outcome instructions and explicit constraints; try zero-shot before adding examples; omit generic step-by-step reasoning requests. Applies to: Documented OpenAI reasoning models; historical o-series particulars stay model-specific Reasoning best practices · ledger line 52

You can always tell where an instruction came from.

Your requirements

What you asked for

Your words outrank everything else. They are preserved, not paraphrased away.

Official

Provider guidance

Model-specific advice must be supported by applicable official provider documentation; see the dated source ledger.

Methodology

PromptingCraft.com’s method

Contract classes, provenance tracing and the critique rubric are our own and labelled as such.

Research

Design & SEO research

Used to build this website. Never used as evidence for how to prompt a model.

Install in a minute. Use it in any discussion.

Install the skill into a project, then ask your assistant for a prompt — “Prepare a Codex prompt for this task.”

Codex uses $promptingcraft. It works as a standalone skill; the optional guidance MCP server adds structured access to official guidance. Plugin packaging and removal are covered in the documentation.

git clone https://gitlab.com/revanalex/promptingcraft-skill.git
cd promptingcraft-skill
python3 scripts/install_skill.py --host claude --project-dir /path/to/your/project
# then, in Claude Code:
/promptingcraft

It writes prompts, not code.

PromptingCraft.com composes the handoff. It never executes the development task or grants permissions.

No proven superiority.

We publish our evaluations, but do not claim prompts written this way always produce better results.

Guidance ages.

Sources are revalidated when your agent can fetch them. Offline, the ledger is labelled as dated.