Borrowing it
Nothing to install: this file belongs to archcore-ai/cli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/archcore-ai/cli/main/.claude/skills/review-prompts-quality/SKILL.mdgit clone --depth 1 https://github.com/archcore-ai/cliWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/archcore-ai/cli/review-prompts-quality)<a href="https://agentmods.dev/skills/archcore-ai/cli/review-prompts-quality"><img src="https://agentmods.dev/badge/skills/archcore-ai/cli/review-prompts-quality/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/archcore-ai/cli/review-prompts-quality"><img src="https://agentmods.dev/badge/skills/archcore-ai/cli/review-prompts-quality.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00691 |
| Opus 5 | $0.00000 | $0.00345 |
| Sonnet 5 | $0.00000 | $0.00138 |
| Haiku 4.5 | $0.00000 | $0.00069 |
Grade A, and why
review-prompts-quality scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Prompts Quality
Prompt Locations in This Project
| File pattern | What it contains |
|---|---|
internal/mcp/tools/*.go |
MCP tool descriptions (mcp.WithDescription(...)) and parameter descriptions |
internal/mcp/server.go |
mcpServerInstructions — system context served to all AI agents |
templates/templates.go |
Document templates with section guidance for human authors |
Workflow
Step 1: Find changed prompt files
Run both commands to capture staged and unstaged changes:
git diff --cached --name-only
git diff --name-only
Filter the results to files matching these patterns:
internal/mcp/tools/*.gointernal/mcp/server.gotemplates/templates.go
If no matching files are found, report: "No prompt-related files changed." and stop.
Step 2: Extract changed prompt content
For each matched file, read the current content of that file. Focus on:
internal/mcp/tools/*.go: Allmcp.WithDescription(...)call arguments and parameter description stringsinternal/mcp/server.go: ThemcpServerInstructionsvariable andbuildInstructions()functiontemplates/templates.go: Thegenerate*Template()functions
Also run git diff HEAD -- <file> (or git diff --cached -- <file>) to see exactly what changed.
Step 3: Delegate to prompt-engineer agent
Launch the ai-kit:prompt-engineer agent with all extracted prompt content and diffs. Ask it to review each changed prompt on these four axes:
-
Effectiveness — Does the prompt clearly communicate intent? Are instructions unambiguous and actionable? Would an AI agent follow them correctly without guessing?
-
Best practices — For MCP tool descriptions: does it specify when to call the tool, what inputs are expected, and what the output looks like? For system instructions: is there a logical hierarchy, no contradictions, clear scope? For templates: do sections guide the author toward complete, useful content?
-
Token cost — Is the prompt unnecessarily verbose? Identify: repeated information, overly long examples, content that could be condensed without loss. Estimate rough token impact for significant issues.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago Changed 08dbd51a9837
- 9d ago First seen · 62 lines · 0 tokens per session scan A dd8ccac8e436
review-prompts-quality is a skill published in the GitHub repository archcore-ai/cli (64 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 691 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
refine
Transform a brief or prompt into a structured, production-ready prompt via prompt-optimizer. File or text mode.
prompt-writer
Write maximally terse agent prompts from scratch. Use when creating agent specs, command prompts, or instruction sets with constitutional governance.
tersify-prompt
Rewrites agent-instruction prompts to be maximally terse while preserving full intent.
shipkit-prompt-audit
Audit LLM prompt pipeline architecture — decomposition, parallelization, chain integrity, schema validation, fallback paths. Finds structural issues no linter catches.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.