Trellis Session Insight
mindfold-ai/Trellis
Reach into past AI conversation history through the trellis mem CLI.
Figure out why a prompt isn't working and fix it — diagnose the actual failure (ambiguity, missing context, wrong format, conflicting instructions) instead of randomly rewording.
Install Prompt Debugging
$ npx skills add mohitagw15856/pm-claude-skills --skill prompt-debugging -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mohitagw15856/pm-claude-skills prompt-debugging --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/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/prompt-debugging .claude/skills/prompt-debugging && 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-debugging" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/prompt-debugging into .claude/skills/prompt-debugging/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prompt-debugging", 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/mohitagw15856/pm-claude-skills/tree/main/skills/prompt-debuggingType 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 mohitagw15856/pm-claude-skills --skill prompt-debugging -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mohitagw15856/pm-claude-skills prompt-debugging --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/prompt-debugging .agents/skills/prompt-debugging && 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-debugging" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/prompt-debugging into .agents/skills/prompt-debugging/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prompt-debugging", 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 mohitagw15856/pm-claude-skills --skill prompt-debugging -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mohitagw15856/pm-claude-skills prompt-debugging --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/prompt-debugging .cursor/skills/prompt-debugging && 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-debugging" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/prompt-debugging into .cursor/skills/prompt-debugging/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prompt-debugging", 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/mohitagw15856/pm-claude-skills.git --path skills/prompt-debugging--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 mohitagw15856/pm-claude-skills --skill prompt-debugging -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mohitagw15856/pm-claude-skills prompt-debugging --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/prompt-debugging .gemini/skills/prompt-debugging && 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-debugging" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/prompt-debugging into .gemini/skills/prompt-debugging/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prompt-debugging", 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 mohitagw15856/pm-claude-skills prompt-debuggingInstalls 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 mohitagw15856/pm-claude-skills --skill prompt-debugging -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/prompt-debugging .github/skills/prompt-debugging && 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-debugging" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/prompt-debugging into .github/skills/prompt-debugging/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prompt-debugging", 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 mohitagw15856/pm-claude-skills --skill prompt-debugging -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mohitagw15856/pm-claude-skills prompt-debugging --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/prompt-debugging .opencode/skills/prompt-debugging && 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-debugging" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/prompt-debugging into .opencode/skills/prompt-debugging/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prompt-debugging", 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-debugging- GitHub stars
- 1.4k
- Token cost
- ~1.1k tokens
- SKILL.md length
- 576 words
- Files
- 1
- Skills in repo
- 1,322
- Repo updated
- First seen
- Licence
- MIT
At a glance
Figure out why a prompt isn't working and fix it — diagnose the actual failure (ambiguity, missing context, wrong format, conflicting instructions) instead of randomly rewording.
- Works in 6 steps: Name the failure mode. Match the symptom… → Fix that cause specifically. Ambiguous →… → Show, don't just tell. For format and… → …
- Asked why isnt my prompt working
- SKILL.md covers What This Skill Produces, Required Inputs, Framework: Diagnose Before You… and Output Format, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Prompt Debugging is an agent skill from mohitagw15856/pm-claude-skills. Figure out why a prompt isn't working and fix it — diagnose the actual failure (ambiguity, missing context, wrong format, conflicting instructions) instead of randomly rewording. Use when asked why isn't my prompt working, the AI keeps ignoring my instructions, my prompt gives inconsistent results, or how do I fix this prompt. Produces a diagnosis of the specific failure mode, the targeted fix for it (not a vibes rewrite), a corrected prompt, a check that it generalizes rather than fixing one case, and the…
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Development, covering Debugging. The repository describes itself as: 1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in… The licence is MIT.
When your agent uses it
- Asked why isnt my prompt working
- The AI keeps ignoring my instructions
- My prompt gives inconsistent results
- How do I fix this prompt
Example prompts
- “/prompt-debugging”
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Name the failure mode. Match the symptom to a cause — ignored instructions often mean it's buried or conflicting; inconsistent output…
- Fix that cause specifically. Ambiguous → add specificity; missing context → add it; no format → show the exact format; conflict → resolve…
- Show, don't just tell. For format and quality problems, an example of the desired output fixes more than paragraphs of description.
- Check it generalizes. Re-test on several cases — a fix that only works on your one example is overfitting, not a fix.
- Extract the principle. Name the rule behind the fix so the next prompt starts right.
- Know when to stop. If the task genuinely exceeds the model or needs tools/context it can't have, say so instead of endless rewording.
What it can do on your machine
Read from SKILL.md and the folder at commit 1cbf1f0. 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 Debugging loads about 1.1k tokens when it runs. Until then it costs about 161 tokens; SKILL.md has 576 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 mohitagw15856/pm-claude-skills at commit 1cbf1f0, republished under its MIT licence (© mohitagw15856). 576 words, ~1,146 tokens.
Download SKILL.mdSave it as
.claude/skills/prompt-debugging/SKILL.md (or your agent's skills folder).- name
- prompt-debugging
- description
- Figure out why a prompt isn't working and fix it — diagnose the actual failure (ambiguity, missing context, wrong format, conflicting instructions) instead of randomly rewording. Use when asked why isn't my prompt working, the AI keeps ignoring my instructions, my prompt gives inconsistent results, or how do I fix this prompt. Produces a diagnosis of the specific failure mode, the targeted fix for it (not a vibes rewrite), a corrected prompt, a check that it generalizes rather than fixing one case, and the principle behind the fix so you stop hitting it — turning prompt frustration into a debuggable, repeatable process.
Prompt Debugging
When a prompt misbehaves, most people randomly reword it until something sticks — slow, and it doesn't teach you anything. Prompts fail in diagnosable ways: ambiguity, missing context, a format the model can't follow, or instructions that contradict each other. This finds the actual failure, applies the targeted fix, and names the principle — so you fix it once and stop hitting the same wall.
What This Skill Produces
- A diagnosis — the specific failure mode: ambiguous ask, missing context, unspecified output format, conflicting instructions, buried key instruction, or too much at once
- The targeted fix — the change that addresses that failure, not a superstitious reword
- A corrected prompt — rewritten to fix the diagnosed problem, with the change explained
- A generalization check — testing that the fix works across cases, not just the one example (the trap of overfitting to a single output)
- The principle — the underlying rule (be specific, show the format, resolve conflicts, front-load the key instruction) so you recognize it next time
- When it's the model, not the prompt — the honest call when the task is beyond what prompting fixes
Required Inputs
Ask for these if not provided:
- The prompt — the actual text that's misbehaving
- What it's doing wrong — ignoring an instruction, wrong format, inconsistent, off-topic
- What you want — the correct output, ideally with an example
- The pattern — does it fail always or sometimes (points at ambiguity vs. a hard miss)
Framework: Diagnose Before You Reword
- Name the failure mode. Match the symptom to a cause — ignored instructions often mean it's buried or conflicting; inconsistent output usually means ambiguity; wrong shape means the format wasn't specified.
- Fix that cause specifically. Ambiguous → add specificity; missing context → add it; no format → show the exact format; conflict → resolve it; buried → move the key instruction up front.
- Show, don't just tell. For format and quality problems, an example of the desired output fixes more than paragraphs of description.
- Check it generalizes. Re-test on several cases — a fix that only works on your one example is overfitting, not a fix.
- Extract the principle. Name the rule behind the fix so the next prompt starts right.
- Know when to stop. If the task genuinely exceeds the model or needs tools/context it can't have, say so instead of endless rewording.
Show full SKILL.md (196 more words)Show less
Output Format
Prompt debug: [what's failing]
Diagnosis: [the specific failure mode — ambiguity / missing context / no format / conflict / buried / overloaded]. The fix: [the targeted change for that cause]. Corrected prompt:
[rewritten prompt].
Generalization check: [test across cases, not just the one example]. Principle: [the rule — so you avoid it next time]. If it's not the prompt: [when the task exceeds prompting → what's actually needed].
Quality Checks
- Diagnoses a specific failure mode before rewriting
- Applies the fix that matches the cause
- Uses an example where the problem is format/quality
- Checks the fix generalizes beyond one case
- Names the principle; flags when it's a model limit, not a prompt one
Anti-Patterns
- Randomly rewording until something works, learning nothing.
- Fixing to one example and overfitting.
- Adding more words when the issue is a conflict or buried instruction.
- Describing the format instead of showing it.
- Blaming the model when the prompt is fixable — or the reverse.
Example Trigger Phrases
- "Why isn't my prompt working?"
- "The AI keeps ignoring one of my instructions — why?"
- "My prompt gives me different results every time."
- "Help me fix this prompt, it's not doing what I want."
- "How do I get consistent output from this prompt?"
© mohitagw15856, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/prompt-debugging of mohitagw15856/pm-claude-skills.
Open the folder on GitHubat commit 1cbf1f0
Compare with similar skills
Prompt Debugging 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 Debugging this skillmohitagw15856/pm-claude-skills | 1.4k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Trellis Session Insightmindfold-ai/Trellis | 15k | 4 repos | ~1.7k | Automated safety check: Pass | AGPL-3.0 | |
| Native Data FetchingCherryHQ/cherry-studio-app | 4k | 6 repos | ~2.9k | Automated safety check: Notes | MIT | |
| Debugging Executionsn8n-io/n8n | 207k | — | ~2.6k | Automated safety check: Pass | Custom licence | |
| Aoti Debugpytorch/pytorch | 104k | 1 repos | ~1.7k | Automated safety check: Pass | Custom licence | |
| Herdr Throwaway Reproductionherdrdev/herdr | 43k | — | ~2.4k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Native Data Fetching
CherryHQ/cherry-studio-app
A skill your agent uses when implementing or debugging ANY network request, API call, or data fetching.
- Official
Debugging Executions
n8n-io/n8n
Debug failed or wrong-output workflow executions using executions tools.
Aoti Debug
pytorch/pytorch
Debug AOTInductor (AOTI) errors and crashes. An agent skill from pytorch/pytorch.
Herdr Throwaway Reproduction
herdrdev/herdr
Runs a disposable, uniquely named Herdr session inside an existing one so runtime, pane, terminal or API bugs can be reproduced without touching the main session.
Systematic Debugging
ultralisp/ultralisp
A skill your agent uses when encountering any bug, test failure, or unexpected behavior, before proposing fixes
More from mohitagw15856/pm-claude-skills
All 1,322 skills in this repoExit Waterfall
mohitagw15856/pm-claude-skills
Compute who gets what at each exit price from a cap table — liquidation preferences, conversion points, and where the founders' share collapses.
Feature Prioritisation
mohitagw15856/pm-claude-skills
Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.
Freelance Rate
mohitagw15856/pm-claude-skills
Derive a freelance day/hourly rate backwards from target income, honest billable utilization, overhead, and the self-employment tax premium — the arithmetic that proves a rate is not salary÷2000.
Offer Comparison
mohitagw15856/pm-claude-skills
Compare two or more job offers as total-comp curves over four years — vesting cliffs, bonuses, 401(k) match, and the crossover year computed, not vibed.
Refinance Breakeven
mohitagw15856/pm-claude-skills
Compute the month a refinance actually starts saving money — payment delta, breakeven month, and total interest on both paths including the term-reset trap.
Rent Vs Buy
mohitagw15856/pm-claude-skills
Model rent-vs-buy honestly — year-by-year net position for both paths including the assumption everyone drops (the renter invests the difference), with a breakeven horizon instead of a verdict.
Related
Categories
Questions about Prompt Debugging
What does Prompt Debugging do?
Figure out why a prompt isn't working and fix it — diagnose the actual failure (ambiguity, missing context, wrong format, conflicting instructions) instead of randomly rewording. Prompt Debugging is an agent skill from mohitagw15856/pm-claude-skills. Figure out why a prompt isn't working and fix it — diagnose the actual failure (ambiguity, missing context, wrong format, conflicting instructions) instead of randomly rewording.
When should I use Prompt Debugging?
Prompt Debugging fits situations like: asked why isnt my prompt working; the AI keeps ignoring my instructions; my prompt gives inconsistent results; how do I fix this prompt.
How do I install Prompt Debugging in Claude Code?
Run `npx skills add mohitagw15856/pm-claude-skills --skill prompt-debugging -a claude-code`. Or copy the skill folder (skills/prompt-debugging in mohitagw15856/pm-claude-skills) into .claude/skills/prompt-debugging in your project. Claude Code loads it when a task matches its description.
How do I install Prompt Debugging in Codex?
Run `npx skills add mohitagw15856/pm-claude-skills --skill prompt-debugging -a codex`. Or copy the skill folder (skills/prompt-debugging in mohitagw15856/pm-claude-skills) into .agents/skills/prompt-debugging in your project. Codex loads it when a task matches its description.
Can I use Prompt Debugging 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 mohitagw15856/pm-claude-skills --skill prompt-debugging -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-debugging, .gemini/skills/prompt-debugging, .github/skills/prompt-debugging and .opencode/skills/prompt-debugging in your project.
What does Prompt Debugging need to run?
SKILL.md names no scripts, command-line tools or credentials: Prompt Debugging is instructions for the agent only.
Does Prompt Debugging 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 Debugging 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 Debugging use?
Prompt Debugging 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 Debugging use?
About 1.1k tokens (SKILL.md is roughly 4.6k 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 Debugging?
Skills that share tags, products or a category with Prompt Debugging: Trellis Session Insight (mindfold-ai/Trellis, 15k stars), Native Data Fetching (CherryHQ/cherry-studio-app, 4k stars), Debugging Executions (n8n-io/n8n, 207k stars) and Aoti Debug (pytorch/pytorch, 104k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Prompt Debugging?
mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,431 GitHub stars. The repository holds 1,322 skills in this directory. The repository was last updated on October 7, 2026.
Source: mohitagw15856/pm-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.