claude-prompt-forge
Prompt-forging skill for Claude Code and long autonomous Claude sessions — the prompt analogue of grill-me-extensive. Builds orchestration, session, unit, and handoff prompts with resume-don't-restart preambles, both-states evidence contracts, AND-gate completion, hard safety bans, and unit sentinels so work survives compaction and resists false greens. Use when writing or hardening a multi-phase Claude prompt, when a prior prompt caused restarts or false completion, or when the user says forge a prompt, prompt for Claude Code, make this prompt robust, orchestration prompt, session prompt, or handoff prompt.
- License 许可
- MIT
- 最近更新
- 2026-11-02
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- claude-prompt-forge
- description
- Prompt-forging skill for Claude Code and long autonomous Claude sessions — the prompt analogue of grill-me-extensive. Builds orchestration, session, unit, and handoff prompts with resume-don't-restart preambles, both-states evidence contracts, AND-gate completion, hard safety bans, and unit sentinels so work survives compaction and resists false greens. Use when writing or hardening a multi-phase Claude prompt, when a prior prompt caused restarts or false completion, or when the user says forge a prompt, prompt for Claude Code, make this prompt robust, orchestration prompt, session prompt, or handoff prompt.
02 资源文件 1
- 参考文档references/languages.md4.7 KB
03 SKILL.md 正文
Forge prompts that drive Claude (especially Claude Code) through multi-phase autonomous work without restarting completed gates, trusting uncontrolled zeros, or claiming success from partial evidence.
This skill is the prompt analogue of grill-me-extensive. Where grill-me-extensive scopes a program by walking decisions, this skill produces the instrument that executes a decided program. Read references/prompt-anatomy.md for the full anatomy, references/failure-patterns.md for the measured failure modes each rule prevents, and references/discovery-surface.md when forging prompts that discover tools, MCPs, skills, or capacity upgrades (multi-registry + maturity flags + concrete borrow lines).
When to use
- Writing or hardening an orchestration / session / unit prompt for Claude Code
- Turning a decision log or backlog into a paste-ready Claude prompt
- Fixing a prompt that caused restart-of-completed-work, false greens, or fragment overwrites
- Producing prompts for fan-out units, harvest units, or review units
Do not use for ordinary one-shot questions, casual chat, or prompts that do not need durability across context loss.
The 8-section method
Produce prompts in this order. Omit a section only when it is genuinely inapplicable — never because it is long.
1. ROLE AND DELIVERABLE (who + what only)
State who Claude is in this turn and the single deliverable class. Ban pretence of access Claude does not have.
You are the [architect | implementer | reviewer | miner] for [program].
### 2. RESUME-DON'T-RESTART PREAMBLE
### 3. GROUND TRUTH (measured, banked)
### 4. BINDING DECISIONS (settled, do not re-litigate)
### 5. HARD SAFETY BOUNDARIES (prohibitions)
### 6. EVIDENCE AND COMPLETION CONTRACT
### 7. PHASED WORK (numbered, ordered, gated)
### 8. OUTPUT / UNIT CONTRACT
### Question policy (encode in the prompt)
### Anti-patterns to ban inside the forged prompt
### Modes (state which you are forging)
### Process
04 同仓库更多 Skills
clarify-requirements
Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.
openmm-md
Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein / protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.
visual-review
Take screenshots of web pages and UI using Playwright for visual review and iteration
status
Diagnostic status report — shows metaswarm installation state, project setup, and potential issues
start
Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work
setup
Interactive project setup — detects your project, configures metaswarm, writes project-local files