Agent skill

Poke Holes In This

by mohitagw15856 in mohitagw15856/pm-claude-skills

Get only the weaknesses in something you made — no praise, no encouragement padding, just the holes and how to fix them.

MITAuto-check passed

Install Poke Holes In This

skills CLI
$ npx skills add mohitagw15856/pm-claude-skills --skill poke-holes-in-this -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mohitagw15856/pm-claude-skills poke-holes-in-this --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/poke-holes-in-this .claude/skills/poke-holes-in-this && rm -rf skills-src

Use ~/.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/

Facts

Skill name
poke-holes-in-this
GitHub stars
1.4k
Token cost
~826 tokens
SKILL.md length
418 words
Files
1
Skills in repo
1,348
Repo updated
First seen
Licence
MIT

At a glance

Get only the weaknesses in something you made — no praise, no encouragement padding, just the holes and how to fix them.

  • Works in 5 steps: Skip the praise. The job is holes;… → Be specific. Point to the actual line,… → Rank by severity. Separate the problems… → …
  • Asked to poke holes in this
  • SKILL.md covers What This Skill Produces, Required Inputs, Framework: Only The Weaknesses and Output Format, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Poke Holes In This is an agent skill from mohitagw15856/pm-claude-skills. Get only the weaknesses in something you made — no praise, no encouragement padding, just the holes and how to fix them. Use when asked to poke holes in this, tell me what's wrong with this, critique this honestly, or don't be nice about it. Produces a focused list of the real problems in your draft, plan, argument, or code — ranked by severity, each with why it's a problem and a concrete fix — deliberately stripping the 'this is great!' padding that AI and polite humans add and you don't need.

Its SKILL.md is about 830 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

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 to poke holes in this
  • Tell me whats wrong with this
  • Critique this honestly
  • Dont be nice about it

Example prompts

  • “s wrong with this, critique this honestly, or don”
  • “s a problem and a concrete fix — deliberately stripping the”
  • “padding that AI and polite humans add and you don”
  • “/poke-holes-in-this”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Skip the praise. The job is holes; strengths aren't the ask. Go straight to what's wrong.
  2. Be specific. Point to the actual line, claim, or element — "the argument in paragraph 3 assumes X" beats "it's a bit weak."
  3. Rank by severity. Separate the problems that matter from nitpicks, so the person fixes the important ones first.
  4. Say the consequence. For each hole, name what it costs — a reader lost, an objection unanswered, a bug triggered.
  5. Attach a fix. Every hole comes with a concrete way to close it — critique without a path is just discouragement.

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

Poke Holes In This loads about 826 tokens when it runs. Until then it costs about 130 tokens; SKILL.md has 418 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~130
When it runs · the whole SKILL.md, loaded when a task matches
~826

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). 418 words, ~826 tokens.

Download SKILL.mdSave it as .claude/skills/poke-holes-in-this/SKILL.md (or your agent's skills folder).
name
poke-holes-in-this
description
Get only the weaknesses in something you made — no praise, no encouragement padding, just the holes and how to fix them. Use when asked to poke holes in this, tell me what's wrong with this, critique this honestly, or don't be nice about it. Produces a focused list of the real problems in your draft, plan, argument, or code — ranked by severity, each with why it's a problem and a concrete fix — deliberately stripping the 'this is great!' padding that AI and polite humans add and you don't need.

Poke Holes In This

When you want to improve something, praise is noise. This is pure critique mode: you paste what you made, and it returns only the problems — ranked, specific, and each with a fix. No "great start!", no compliment sandwich, no softening. It's the honest second read you asked for, doing the one job you asked it to do.

What This Skill Produces

  • The holes — the real weaknesses, gaps, errors, and soft spots, specifically
  • Severity ranking — which problems are serious vs. minor, so you fix the right ones first
  • Why each is a problem — the concrete consequence, not just "this is weak"
  • A fix for each — a specific way to address it, not just a complaint
  • Nothing else — no praise padding, no encouragement filler

Required Inputs

Ask for these if not provided:

  • The thing — the draft, plan, argument, design, or code (paste it)
  • What it's for — purpose and audience (what counts as a hole depends on the goal)
  • How harsh — brutal, or firm-but-kind
  • Anything off-limits — parts that are fixed and not up for critique

Framework: Only The Weaknesses

  1. Skip the praise. The job is holes; strengths aren't the ask. Go straight to what's wrong.
  2. Be specific. Point to the actual line, claim, or element — "the argument in paragraph 3 assumes X" beats "it's a bit weak."
  3. Rank by severity. Separate the problems that matter from nitpicks, so the person fixes the important ones first.
  4. Say the consequence. For each hole, name what it costs — a reader lost, an objection unanswered, a bug triggered.
  5. Attach a fix. Every hole comes with a concrete way to close it — critique without a path is just discouragement.
Show full SKILL.md (138 more words)Show less

Output Format

Poking holes in: [the thing] · for [purpose]

🔴 Serious

  • [the hole] → why it matters: [consequence] → fix: [specific].

🟡 Worth fixing

  • [the hole] → [consequence] → [fix].

🟢 Minor / nitpicks

  • [quick ones].

The one to fix first: [highest-leverage hole].

Quality Checks

  • Contains only weaknesses — no praise padding
  • Each hole is specific (points to the actual part)
  • Problems are ranked by severity
  • Each includes the consequence and a concrete fix
  • Identifies the single highest-priority fix

Anti-Patterns

  • A compliment sandwich when only critique was asked for.
  • Vague criticism with no specific location.
  • Nitpicks ranked equal to serious problems.
  • Complaints with no fixes.

Example Trigger Phrases

  • "Poke holes in my essay — don't be nice."
  • "Tell me what's wrong with this plan, only the problems."
  • "Critique this pitch honestly, no praise."
  • "Where does my argument fall apart?"
  • "Rip into this draft so I can fix it."

© 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/poke-holes-in-this of mohitagw15856/pm-claude-skills.

Open the folder on GitHubat commit 1cbf1f0

Compare with similar skills

Poke Holes In This 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.

Poke Holes In This compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Poke Holes In This this skillmohitagw15856/pm-claude-skills1.4k—~826Automated safety check: PassMIT
Weak Internal Linksthedaviddias/Front-End-Checklist74k—~574Automated safety check: PassMIT
Detecting Weak Cryptographyjeremylongshore/tons-of-skills-marketplace2.8k—~1.3kAutomated safety check: PassMIT
Made To Stickgetagentseal/founder-playbook729—~4.1kAutomated safety check: PassMIT
Fastener Holeghbalf/freecad-ai556—~487Automated safety check: PassLGPL-2.1
Weakness DetectionMaxKmet/idea-validation-agents478—~508Automated safety check: PassMIT

Similar skills

  • Weak Internal Links

    thedaviddias/Front-End-Checklist

    A skill your agent uses when applies to any site with more than 20 pages.

    74k GitHub stars~574 tokensUpdated 4 days ago
    Marketing & SEOAuto-check passed
  • Detecting Weak Cryptography

    jeremylongshore/tons-of-skills-marketplace

    Scan a source tree for weak cryptographic primitives: MD5 / SHA-1 used for security purposes, DES / 3DES / RC4 ciphers, ECB block mode, custom-built crypto (XOR loops, hand-rolled HMAC), hardcoded…

    2.8k GitHub stars~1.3k tokensUpdated yesterday
    SecurityAuto-check passed
  • Made To Stick

    getagentseal/founder-playbook

    Applies the SUCCESs Framework from Made to Stick by Chip Heath and Dan Heath.

    729 GitHub stars~4.1k tokensUpdated 4 days ago
    EducationAuto-check passed
  • Fastener Hole

    ghbalf/freecad-ai

    Create standard fastener holes: clearance, counterbore, or countersink.

    556 GitHub stars~487 tokensUpdated today
    Auto-check passed
  • Weakness Detection

    MaxKmet/idea-validation-agents

    Analyzes idea-scoring output to identify the weakest dimensions, root causes of low scores, and probable failure modes if the idea were pursued as-is.

    478 GitHub stars~508 tokensUpdated 3 mo ago
    DevelopmentAuto-check passed
  • Typed Holes Refactor

    rand/cc-polymath

    Refactor codebases using Design by Typed Holes methodology - iterative, test-driven refactoring with formal hole resolution, constraint propagation, and continuous validation.

    181 GitHub stars~5.6k tokensUpdated 7 mo ago
    DevelopmentAuto-check passed

More from mohitagw15856/pm-claude-skills

All 1,348 skills in this repo
  • Car Tco

    mohitagw15856/pm-claude-skills

    Compare the total cost of car ownership across buy-new, buy-used, lease, and keep-your-current-car — depreciation, insurance, maintenance ramp, and fuel over a real horizon, not just the monthly…

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Cs Health Scorecard

    mohitagw15856/pm-claude-skills

    Build a customer health scorecard for a specific account. An agent skill from mohitagw15856/pm-claude-skills.

    1.4k GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed
  • Exit 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.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Feature Prioritisation

    mohitagw15856/pm-claude-skills

    Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.

    1.4k GitHub stars~2k tokensUpdated yesterday
    Auto-check passed
  • Fire Number

    mohitagw15856/pm-claude-skills

    Compute a financial-independence (FIRE) target and years-to-reach with every assumption labeled as an assumption — plus a sensitivity table instead of a single false-precision answer.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • 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.

    1.4k GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed

Questions about Poke Holes In This

What does Poke Holes In This do?

Get only the weaknesses in something you made — no praise, no encouragement padding, just the holes and how to fix them. Poke Holes In This is an agent skill from mohitagw15856/pm-claude-skills. Get only the weaknesses in something you made — no praise, no encouragement padding, just the holes and how to fix them.

When should I use Poke Holes In This?

Poke Holes In This fits situations like: asked to poke holes in this; tell me whats wrong with this; critique this honestly; dont be nice about it.

How do I install Poke Holes In This in Claude Code?

Run `npx skills add mohitagw15856/pm-claude-skills --skill poke-holes-in-this -a claude-code`. Or copy the skill folder (skills/poke-holes-in-this in mohitagw15856/pm-claude-skills) into .claude/skills/poke-holes-in-this in your project. Claude Code loads it when a task matches its description.

How do I install Poke Holes In This in Codex?

Run `npx skills add mohitagw15856/pm-claude-skills --skill poke-holes-in-this -a codex`. Or copy the skill folder (skills/poke-holes-in-this in mohitagw15856/pm-claude-skills) into .agents/skills/poke-holes-in-this in your project. Codex loads it when a task matches its description.

Can I use Poke Holes In This 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 poke-holes-in-this -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/poke-holes-in-this, .gemini/skills/poke-holes-in-this, .github/skills/poke-holes-in-this and .opencode/skills/poke-holes-in-this in your project.

What does Poke Holes In This need to run?

SKILL.md names no scripts, command-line tools or credentials: Poke Holes In This is instructions for the agent only.

Does Poke Holes In This 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 Poke Holes In This 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 Poke Holes In This use?

Poke Holes In This 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 Poke Holes In This use?

About 826 tokens (SKILL.md is roughly 3.3k 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 Poke Holes In This?

Skills that share tags, products or a category with Poke Holes In This: Weak Internal Links (thedaviddias/Front-End-Checklist, 74k stars), Detecting Weak Cryptography (jeremylongshore/tons-of-skills-marketplace, 2.8k stars), Made To Stick (getagentseal/founder-playbook, 729 stars) and Fastener Hole (ghbalf/freecad-ai, 556 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Poke Holes In This?

mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,434 GitHub stars. The repository holds 1,348 skills in this directory. The repository was last updated on October 9, 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.