Prompt Improver
severity1/claude-code-prompt-improver
This skill enriches vague prompts with targeted research and clarification before execution.
A skill your agent uses when designing, critiquing, or fixing system prompts, tool descriptions, skill definitions, or other LLM instruction text — including when a model ignores, over-applies, or…
Install Prompt Engineering
$ npx skills add WrongStack/WrongStack --skill prompt-engineering -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install WrongStack/WrongStack prompt-engineering --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/WrongStack/WrongStack.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/core/skills/prompt-engineering .claude/skills/prompt-engineering && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "prompt-engineering" agent skill from https://github.com/WrongStack/WrongStack/tree/main/packages/core/skills/prompt-engineering into .claude/skills/prompt-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prompt-engineering", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/WrongStack/WrongStack/tree/main/packages/core/skills/prompt-engineeringType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add WrongStack/WrongStack --skill prompt-engineering -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install WrongStack/WrongStack prompt-engineering --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/WrongStack/WrongStack.git skills-src && mkdir -p .agents/skills && cp -r skills-src/packages/core/skills/prompt-engineering .agents/skills/prompt-engineering && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "prompt-engineering" agent skill from https://github.com/WrongStack/WrongStack/tree/main/packages/core/skills/prompt-engineering into .agents/skills/prompt-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prompt-engineering", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add WrongStack/WrongStack --skill prompt-engineering -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install WrongStack/WrongStack prompt-engineering --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/WrongStack/WrongStack.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/packages/core/skills/prompt-engineering .cursor/skills/prompt-engineering && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "prompt-engineering" agent skill from https://github.com/WrongStack/WrongStack/tree/main/packages/core/skills/prompt-engineering into .cursor/skills/prompt-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prompt-engineering", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/WrongStack/WrongStack.git --path packages/core/skills/prompt-engineering--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add WrongStack/WrongStack --skill prompt-engineering -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install WrongStack/WrongStack prompt-engineering --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/WrongStack/WrongStack.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/packages/core/skills/prompt-engineering .gemini/skills/prompt-engineering && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "prompt-engineering" agent skill from https://github.com/WrongStack/WrongStack/tree/main/packages/core/skills/prompt-engineering into .gemini/skills/prompt-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prompt-engineering", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install WrongStack/WrongStack prompt-engineeringInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add WrongStack/WrongStack --skill prompt-engineering -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/WrongStack/WrongStack.git skills-src && mkdir -p .github/skills && cp -r skills-src/packages/core/skills/prompt-engineering .github/skills/prompt-engineering && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "prompt-engineering" agent skill from https://github.com/WrongStack/WrongStack/tree/main/packages/core/skills/prompt-engineering into .github/skills/prompt-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prompt-engineering", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add WrongStack/WrongStack --skill prompt-engineering -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install WrongStack/WrongStack prompt-engineering --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/WrongStack/WrongStack.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/packages/core/skills/prompt-engineering .opencode/skills/prompt-engineering && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "prompt-engineering" agent skill from https://github.com/WrongStack/WrongStack/tree/main/packages/core/skills/prompt-engineering into .opencode/skills/prompt-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prompt-engineering", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
prompt-engineering- GitHub stars
- 370
- Token cost
- ~1.4k tokens
- SKILL.md length
- 712 words
- Files
- 2
- Skills in repo
- 38
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when designing, critiquing, or fixing system prompts, tool descriptions, skill definitions, or other LLM instruction text — including when a model ignores, over-applies, or…
- Works in 8 steps: State the goal and the reason. A rule… → Say what good output looks like —… → Use examples deliberately. They are… → …
- Fixing system prompts
- SKILL.md covers Overview, Rules, Tool descriptions and Skill descriptions, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Prompt Engineering is an agent skill from WrongStack/WrongStack. Use this skill when designing, critiquing, or fixing system prompts, tool descriptions, skill definitions, or other LLM instruction text — including when a model ignores, over-applies, or misreads its instructions. Triggers: user mentions "prompt", "system prompt", "system instruction", "tool description", "skill description", "few-shot", "the model keeps ignoring", "eval", "usage hint".
Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `SKILL.save.md`).
It sits in AI & LLM Engineering, covering Prompt engineering. The repository describes itself as: An AI coding agent that reads your code, edits files, runs commands, and reasons through bugs — across a terminal REPL, a full-screen TUI, and a browser UI, while you keep your… The licence is MIT.
When your agent uses it
- Fixing system prompts
- Tool descriptions
- Skill definitions
- Other LLM instruction text — including when a model ignores
Example prompts
- “prompt”
- “system prompt”
- “system instruction”
- “/prompt-engineering”
Workflow steps
8 steps, taken from the first numbered list in SKILL.md.
- State the goal and the reason. A rule with its "why" generalizes to cases
- Say what good output looks like — format, length, audience, and when the
- Use examples deliberately. They are copied closely, so make them varied,
- Structure long prompts. Separate instructions, context, and data with
- Calibrate emphasis. Capitals and "CRITICAL" on every line make a model
- Remove filler and resolve contradictions. Every sentence should change
- Order for caching: stable content (identity, tools, standing rules) first,
- Test against a fixed set of inputs, including edge cases and inputs the
What it can do on your machine
Read from SKILL.md and the folder at commit 57f6018. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Prompt Engineering loads about 1.4k tokens when it runs. Until then it costs about 102 tokens; SKILL.md has 712 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from WrongStack/WrongStack at commit 57f6018, republished under its MIT licence (© WrongStack). 712 words, ~1,426 tokens.
Download SKILL.mdSave it as
.claude/skills/prompt-engineering/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- prompt-engineering
- description
- Use this skill when designing, critiquing, or fixing system prompts, tool descriptions, skill definitions, or other LLM instruction text — including when a model ignores, over-applies, or misreads its instructions. Triggers: user mentions "prompt", "system prompt", "system instruction", "tool description", "skill description", "few-shot", "the model keeps ignoring", "eval", "usage hint".
- version
- 2.0.0
- required-capabilities
- filesystem.read, filesystem.write
- optional-capabilities
- verification.run
Prompt Engineering
Overview
Current models follow instructions closely, so most prompt failures are failures of clarity, not of emphasis: a missing reason, a buried or contradictory rule, an example that teaches the wrong thing, or a tool whose purpose overlaps another. Write prompts the way you would brief a capable new colleague who has none of your context, then check them against real inputs.
Rules
- State the goal and the reason. A rule with its "why" generalizes to cases the rule didn't list; a bare rule gets applied literally.
- Say what good output looks like — format, length, audience, and when the task is done. Prefer "do X" over a list of things not to do.
- Use examples deliberately. They are copied closely, so make them varied, representative, and consistent with the written rules.
- Structure long prompts. Separate instructions, context, and data with headings or XML-style tags; put long reference material before the question that uses it.
- Calibrate emphasis. Capitals and "CRITICAL" on every line make a model over-apply rules to cases they were never meant for; reserve strong wording for genuine hard constraints.
- Remove filler and resolve contradictions. Every sentence should change behaviour; when two instructions can conflict, state which wins.
- Order for caching: stable content (identity, tools, standing rules) first, volatile content (session state, recent errors) last.
- Test against a fixed set of inputs, including edge cases and inputs the prompt should decline. Change one thing at a time and read the outputs, not just a score.
Tool descriptions
A model picks tools from their names and descriptions alone. Each description answers:
- When to use it — and when not. Name the neighbouring tool to prefer instead ("for exact text use grep; for symbols use this").
- Inputs. Required versus optional, formats, units, limits, and one concrete example value for anything non-obvious.
- Output. The shape of what comes back, so the next step can be planned.
- Failure. What errors look like and what to do about them.
✅ Search indexed code symbols by name or concept and return ranked definitions
with file and line. Use before broad grep when locating a function, type, or
module; use grep for exact strings or regexes. `kind` narrows to functions,
classes, or interfaces. If the index is empty, build it first.
❌ Searches the codebase.Skill descriptions
The description decides whether a skill is ever loaded, so it is written for selection, not for documentation:
- The first sentence is the trigger shown in the skill manifest — a concrete situation ("when writing or fixing tests in any project"), not a topic ("this skill is about tests").
- Follow with the phrases users actually type, including symptoms ("flaky", "keeps failing"), not only the formal names.
- Scope it honestly. An over-broad trigger crowds out better skills; one that
says "in
<product>" may never fire for the user's own project. - In WrongStack skill bodies, a tool name wrapped in backticks, or "use/run/call" followed by a backticked name, is treated as a required tool — the skill is dropped where that tool is absent. Write optional tool names in plain text.
Show full SKILL.md (249 more words)Show less
Diagnosing a misbehaving prompt
| Symptom | Likely cause | Fix |
|---|---|---|
| Ignores an instruction | Buried in a long block, or contradicted elsewhere | Move it near the task, remove the conflict, give the reason |
| Applies a rule where it doesn't fit | Absolute or shouted wording | State the scope and the exception; drop the capitals |
| Output format drifts | No example or schema | Show one exact example, or require a schema |
| Too verbose or too terse | No length or audience guidance | State the reader and the expected length |
| Calls the wrong tool | Overlapping tool descriptions | Add "use X instead when…" to both |
| Invents facts | No permission to say "unknown" | Tell it what to do when information is missing |
Anti-patterns
- Identity filler ("You are a helpful assistant") and politeness padding — they cost tokens and change nothing.
- Rules without reasons, so edge cases are guessed.
- Examples that contradict the rules — the example wins.
- Fixing one bad output by adding one more rule, until the prompt is a pile of patches; find the underlying ambiguity instead.
- Judging a prompt change from a single run.
Before returning
- Goal, reasons, and success criteria stated
- No contradictions; precedence stated where rules can conflict
- Examples consistent with the rules and varied
- Emphasis reserved for real hard constraints
- Tool and skill descriptions say when to use, inputs, outputs, and alternatives
- Checked against representative and edge-case inputs
Skills in scope
skill-creator— for the WrongStack SKILL.md format and authoring workflowoutput-standards— for WrongStack's final-message and<nextsteps>conventionstesting— for turning prompt checks into repeatable evaluations
© WrongStack, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in packages/core/skills/prompt-engineering of WrongStack/WrongStack.
- SKILL.md
- SKILL.save.md
Open the folder on GitHubat commit 57f6018
Compare with similar skills
Prompt Engineering next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Prompt Engineering this skillWrongStack/WrongStack | 370 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Prompt Improverseverity1/claude-code-prompt-improver | 1.9k | 2 repos | ~1.7k | Automated safety check: Pass | MIT | |
| Prompt Engineering Patternsynulihao/AgentSkillOS | 617 | 15 repos | ~1.7k | Automated safety check: Pass | None | |
| Patch CreationPiebald-AI/tweakcc | 2.5k | — | ~1.6k | Automated safety check: Pass | MIT | |
| LLM Application DevMoizIbnYousaf/ai-agent-skills | 1.1k | 2 repos | ~1.3k | Automated safety check: Pass | MIT | |
| Senior Prompt Engineermaslennikov-ig/claude-code-orchestrator-kit | 260 | 4 repos | ~1.4k | Automated safety check: Pass | Custom licence |
Similar skills
Prompt Engineering Patterns
ynulihao/AgentSkillOS
Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production.
Patch Creation
Piebald-AI/tweakcc
Create and register new patches for tweakcc. An agent skill from Piebald-AI/tweakcc.
LLM Application Dev
MoizIbnYousaf/ai-agent-skills
Building applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration.
Senior Prompt Engineer
maslennikov-ig/claude-code-orchestrator-kit
Provides reference guides and Python scripts for prompt optimization, RAG evaluation, and agent orchestration when building or tuning LLM systems.
Codex Fable5
baskduf/FableCodex
Apply a Claude Fable 5 inspired operating style inside Codex.
More from WrongStack/WrongStack
All 38 skills in this repoDesign Craft
WrongStack/WrongStack
Design or substantially improve user-facing interfaces with a product-specific visual direction, content hierarchy, and rendered critique.
Design Critique
WrongStack/WrongStack
A skill your agent uses to audit an interface that already exists and say precisely why it looks generated, templated, or unfinished — a scored rubric across composition, typography, color, states…
Mailbox Bridge
WrongStack/WrongStack
A skill your agent uses when external coding agents (Claude Code, Aider, custom scripts) need to participate in the project's shared WrongStack mailbox, or when a user asks to "expose the mailbox"…
Multi Agent
WrongStack/WrongStack
A skill your agent uses whenever work can be split across multiple AI agents running in parallel, or when orchestrating leader/worker patterns in WrongStack.
Web Platform Baseline
WrongStack/WrongStack
Use this skill before asserting that a CSS, HTML or accessibility capability is available, unavailable, or the right tool — it carries dated, refreshable platform facts and refuses to let stale…
Wrongstack Mailbox
WrongStack/WrongStack
A skill your agent uses when the user wants to communicate with WrongStack's shared project mailbox from outside WrongStack — read messages sent by WrongStack agents, send replies, broadcast to all…
Related
Categories
Questions about Prompt Engineering
What does Prompt Engineering do?
A skill your agent uses when designing, critiquing, or fixing system prompts, tool descriptions, skill definitions, or other LLM instruction text — including when a model ignores, over-applies, or…. Prompt Engineering is an agent skill from WrongStack/WrongStack. Use this skill when designing, critiquing, or fixing system prompts, tool descriptions, skill definitions, or other LLM instruction text — including when a model ignores, over-applies, or misreads its instructions.
When should I use Prompt Engineering?
Prompt Engineering fits situations like: fixing system prompts; tool descriptions; skill definitions; other LLM instruction text — including when a model ignores.
How do I install Prompt Engineering in Claude Code?
Run `npx skills add WrongStack/WrongStack --skill prompt-engineering -a claude-code`. Or copy the skill folder (packages/core/skills/prompt-engineering in WrongStack/WrongStack) into .claude/skills/prompt-engineering in your project. Claude Code loads it when a task matches its description.
How do I install Prompt Engineering in Codex?
Run `npx skills add WrongStack/WrongStack --skill prompt-engineering -a codex`. Or copy the skill folder (packages/core/skills/prompt-engineering in WrongStack/WrongStack) into .agents/skills/prompt-engineering in your project. Codex loads it when a task matches its description.
Can I use Prompt Engineering in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add WrongStack/WrongStack --skill prompt-engineering -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/prompt-engineering, .gemini/skills/prompt-engineering, .github/skills/prompt-engineering and .opencode/skills/prompt-engineering in your project.
What does Prompt Engineering need to run?
SKILL.md names no scripts, command-line tools or credentials: Prompt Engineering is instructions for the agent only.
Does Prompt Engineering access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Prompt Engineering safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Prompt Engineering use?
Prompt Engineering is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Prompt Engineering use?
About 1.4k tokens (SKILL.md is roughly 5.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Prompt Engineering?
Skills that share tags, products or a category with Prompt Engineering: Prompt Improver (severity1/claude-code-prompt-improver, 1.9k stars), Prompt Engineering Patterns (ynulihao/AgentSkillOS, 617 stars), Patch Creation (Piebald-AI/tweakcc, 2.5k stars) and LLM Application Dev (MoizIbnYousaf/ai-agent-skills, 1.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Prompt Engineering?
WrongStack (a GitHub organization) maintains it in WrongStack/WrongStack, which has 370 GitHub stars. The repository holds 38 skills in this directory. The repository was last updated on October 7, 2026.
Source: WrongStack/WrongStack on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.