New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Ijfw Critique

by FerroxLabs in FerroxLabs/ijfw

Challenge decisions, surface counter-arguments, flag assumptions.

MITAuto-check passed

Install Ijfw Critique

skills CLI
$ npx skills add FerroxLabs/ijfw --skill ijfw-critique -a claude-code

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

GitHub CLI
$ gh skill install FerroxLabs/ijfw ijfw-critique --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/FerroxLabs/ijfw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/codex/skills/ijfw-critique .claude/skills/ijfw-critique && 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
ijfw-critique
GitHub stars
212
Token cost
~1.2k tokens
SKILL.md length
424 words
Files
1
Skills in repo
38
Repo updated
First seen
Licence
MIT

At a glance

Challenge decisions, surface counter-arguments, flag assumptions.

  • Works in 4 steps: Steelman first. In one sentence, state… → Surface the assumptions. Name 2-3… → Three concrete counter-arguments. Each… → …
  • SKILL.md covers Four-step critique, Refactor reframe (single-line…, When NOT to critique and Output shape, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Ijfw Critique is an agent skill from FerroxLabs/ijfw. Challenge decisions, surface counter-arguments, flag assumptions. Trigger: 'should I', 'is this right', 'critique', 'poke holes', 'second opinion', 'devil's advocate'. Auto-fired by ijfw-intent-router.

Its SKILL.md is about 1.2k 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: IJFW — It Just Fcking Works. Ferrox Labs' local-first infrastructure for AI coding agents: shared memory, smart routing, multi-AI cross-audits, disciplined workflow. The licence is MIT.

Example prompts

  • “should I”
  • “is this right”
  • “critique”
  • “/ijfw-critique”

Workflow steps

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

  1. Steelman first. In one sentence, state the strongest version of the
  2. Surface the assumptions. Name 2-3 assumptions the plan rests on.
  3. Three concrete counter-arguments. Each should be
  4. State your verdict briefly. After laying out the counters, give a

What it can do on your machine

Read from SKILL.md and the folder at commit eda62f3. 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

Ijfw Critique loads about 1.2k tokens when it runs. Until then it costs about 54 tokens; SKILL.md has 424 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~54
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

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 FerroxLabs/ijfw at commit eda62f3, republished under its MIT licence (© FerroxLabs). 424 words, ~1,184 tokens.

Download SKILL.mdSave it as .claude/skills/ijfw-critique/SKILL.md (or your agent's skills folder).
name
ijfw-critique
description
Challenge decisions, surface counter-arguments, flag assumptions. Trigger: 'should I', 'is this right', 'critique', 'poke holes', 'second opinion', 'devil's advocate'. Auto-fired by ijfw-intent-router.

Before you agree, disagree. Before you advise, stress-test.

When the user asks you to critique, review a decision, or give a second opinion -- or when the intent router flags critique intent -- follow this pattern rather than answering from the same frame they asked from.

Four-step critique

  1. Steelman first. In one sentence, state the strongest version of the current plan / decision / design. Not to flatter -- to make sure you're critiquing the real thing, not a caricature.

  2. Surface the assumptions. Name 2-3 assumptions the plan rests on. These are the load-bearing beliefs that, if wrong, collapse the argument. Be specific: "assumes traffic stays under 10k qps", not "assumes scale".

  3. Three concrete counter-arguments. Each should be:

    • Non-obvious (if the user already considered it, skip)
    • Bounded (state when it applies; rarely are counter-arguments universal)
    • Actionable (each comes with a "watch for X" or "test by Y")

    Prefer counter-arguments that come from different angles: operational, social/organizational, economic, correctness. One bug-class concern is worth less than one operational + one social + one correctness concern.

  4. State your verdict briefly. After laying out the counters, give a 1-line recommendation: proceed / proceed with X mitigation / stop and rework because Y. Own the verdict -- don't just hedge.

Show full SKILL.md (224 more words)Show less

Refactor reframe (single-line trigger)

When the user is mid-refactor and a fix feels hacky, or you catch yourself patching around a smell rather than removing it, run this prompt out loud:

Knowing everything I know now, what would the elegant solution look like?

Answer it briefly (3-5 lines). If the elegant version costs less than the hack you're about to ship, replace the hack. If it costs more than 2x, log the elegant version as a follow-up and proceed with the pragmatic fix -- but only after you've named the debt explicitly.

Skip this for trivial or obvious fixes; the point is to break frame on non-trivial decisions, not to over-engineer.

When NOT to critique

  • The user is midway through implementing and needs help, not a critique.
  • The decision is reversible and cheap (just do it and see).
  • You lack the domain facts to form an opinion -- say so instead of guessing.
  • The question is "how" not "whether". How-to questions deserve how-to answers, not a rehash of whether to do it at all.

Output shape

Steelman: <one-line strongest version>

Assumptions:
  1. <load-bearing belief>
  2. <load-bearing belief>

Counter-arguments:
  1. <non-obvious objection> -- applies when <condition>; watch for <signal>.
  2. <different angle> -- applies when <condition>; test with <method>.
  3. <third angle> -- applies when <condition>; mitigate via <approach>.

Verdict: <proceed|mitigate|rework> -- <one-line reason>

Audit: stress-tested <N> assumptions, <N> angles (<angle-1> + <angle-2> + <angle-3>). Confidence: <low|med|high>.
Worked example
Steelman: Rewriting the auth layer in Rust eliminates the class of memory bugs that caused last quarter's outages.

Assumptions:
  1. The team has enough Rust fluency to maintain the new code without slowdown.
  2. The outages trace to memory bugs, not logic or config errors.

Counter-arguments:
  1. Operationally: Rust compile times and borrow-checker friction could double review cycles -- applies when the team has <3 months Rust experience; watch for PR cycle time increasing past 2 days.
  2. Socially: the auth team may resist a full rewrite when incremental hardening (address-sanitiser + fuzzing) could close the same risk at 20% of the effort -- applies when management is measuring velocity; test by asking the team to estimate both approaches.
  3. Correctness: auth logic bugs (e.g. missing token expiry checks) are language-agnostic -- applies if the root-cause analysis is incomplete; mitigate by running a postmortem before deciding on the rewrite.

Verdict: mitigate -- commission a 2-week root-cause analysis first; if the cause is confirmed memory-safety, Rust is the right call.

Audit: stress-tested 2 assumptions, 3 angles (operational + social + correctness). Confidence: high.

Tone

Direct, not hedging. The user asked for a critique; they don't need "this is just my opinion". State the counter clearly. If they push back, that's the signal to update or yield -- but make them do the work of pushing back, not you.

Resume normal mode after.

© FerroxLabs, 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 codex/skills/ijfw-critique of FerroxLabs/ijfw.

Open the folder on GitHubat commit eda62f3

Compare with similar skills

Ijfw Critique 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.

Ijfw Critique compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ijfw Critique this skillFerroxLabs/ijfw212—~1.2kAutomated safety check: PassMIT
Flagsvercel/next.js143k—~746Automated safety check: PassMIT
Design Critiquepaperclipai/paperclip99k—~1.2kAutomated safety check: PassMIT
Agent Challengesruvnet/ruflo74k2 repos~995Automated safety check: PassMIT
Critique Theaternexu-io/open-design100k—~640Automated safety check: PassApache-2.0
Challengealirezarezvani/claude-skills28k1 repos~1.7kAutomated safety check: PassMIT

Similar skills

  • Flags

    vercel/next.js

    Official

    How to add or modify Next.js experimental feature flags end-to-end.

    143k GitHub stars~746 tokensUpdated today
    DevelopmentAuto-check passed

  • Design Critique

    paperclipai/paperclip

    Give a structured product design critique — user job clarity, hierarchy, affordance, error states, accessibility, and consistency — focused on what to change, in what order, and why.

    99k GitHub stars~1.2k tokensUpdated today
    Media & CreativeAuto-check passed

  • Agent Challenges

    ruvnet/ruflo

    Agent skill for challenges - invoke with $agent-challenges. An agent skill from ruvnet/ruflo.

    74k GitHub starsUsed in 2 repos~995 tokens
    Auto-check passed

  • Critique Theater

    nexu-io/open-design

    Five-dimension design quality review — score the artifact against craft, brand, accessibility, and copy, then fix what falls short before handing it over.

    100k GitHub stars~640 tokensUpdated today
    Frontend & DesignAuto-check passed

  • Challenge

    alirezarezvani/claude-skills

    Pre-mortem plan analysis. An agent skill from alirezarezvani/claude-skills.

    28k GitHub starsUsed in 1 repo~1.7k tokens
    Business, Finance & HRAuto-check passed

  • Workspace Surface Audit

    affaan-m/ECC

    Audit the active repo, MCP servers, plugins, connectors, env surfaces, and harness setup, then recommend the highest-value ECC-native skills, hooks, agents, and operator workflows.

    276k GitHub starsUsed in 3 repos~1.3k tokens
    Agent WorkflowsAuto-check: notes

More from FerroxLabs/ijfw

All 38 skills in this repo

  • Ijfw Agents Md

    FerroxLabs/ijfw

    Maintain canonical AGENTS.md (open spec). An agent skill from FerroxLabs/ijfw.

    212 GitHub stars~2.7k tokensUpdated 5 days ago
    Auto-check passed

  • Ijfw Design

    FerroxLabs/ijfw

    A skill your agent uses when the user says: 'design', 'redesign', 'UI', 'UX', 'dashboard', 'page', 'component', 'make it look better', 'polish', 'pretty', 'professional', 'user experience'…

    212 GitHub stars~2.2k tokensUpdated 5 days ago
    Auto-check passed

  • Ijfw Complete Milestone

    FerroxLabs/ijfw

    A skill your agent uses when a milestone is shipping and you need to archive its artifacts, generate a summary, and seed the next milestone.

    212 GitHub stars~1.5k tokensUpdated 5 days ago
    Auto-check passed

  • Ijfw Cross Audit

    FerroxLabs/ijfw

    Generate a cross-platform multi-model audit (Trident) on a diff, brief, or artifact.

    212 GitHub stars~594 tokensUpdated 5 days ago
    Auto-check passed

  • Ijfw Debug

    FerroxLabs/ijfw

    Root-cause analysis with hypothesis tracking. An agent skill from FerroxLabs/ijfw.

    212 GitHub stars~578 tokensUpdated 5 days ago
    Auto-check passed

  • Ijfw Milestone Summary

    FerroxLabs/ijfw

    A skill your agent uses when the user asks for a milestone summary, milestone recap, or to summarize a milestone -- or runs /ijfw-milestone-summary.

    212 GitHub stars~1.5k tokensUpdated 5 days ago
    Auto-check passed

Questions about Ijfw Critique

What does Ijfw Critique do?

Challenge decisions, surface counter-arguments, flag assumptions. Ijfw Critique is an agent skill from FerroxLabs/ijfw. Challenge decisions, surface counter-arguments, flag assumptions.

How do I install Ijfw Critique in Claude Code?

Run `npx skills add FerroxLabs/ijfw --skill ijfw-critique -a claude-code`. Or copy the skill folder (codex/skills/ijfw-critique in FerroxLabs/ijfw) into .claude/skills/ijfw-critique in your project. Claude Code loads it when a task matches its description.

How do I install Ijfw Critique in Codex?

Run `npx skills add FerroxLabs/ijfw --skill ijfw-critique -a codex`. Or copy the skill folder (codex/skills/ijfw-critique in FerroxLabs/ijfw) into .agents/skills/ijfw-critique in your project. Codex loads it when a task matches its description.

Can I use Ijfw Critique 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 FerroxLabs/ijfw --skill ijfw-critique -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ijfw-critique, .gemini/skills/ijfw-critique, .github/skills/ijfw-critique and .opencode/skills/ijfw-critique in your project.

What does Ijfw Critique need to run?

SKILL.md names no scripts, command-line tools or credentials: Ijfw Critique is instructions for the agent only.

Does Ijfw Critique 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 Ijfw Critique 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 Ijfw Critique use?

Ijfw Critique 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 Ijfw Critique use?

About 1.2k tokens (SKILL.md is roughly 4.7k 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 Ijfw Critique?

Skills that share tags, products or a category with Ijfw Critique: Flags (vercel/next.js, 143k stars), Design Critique (paperclipai/paperclip, 99k stars), Agent Challenges (ruvnet/ruflo, 74k stars) and Critique Theater (nexu-io/open-design, 100k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ijfw Critique?

FerroxLabs (a GitHub user) maintains it in FerroxLabs/ijfw, which has 212 GitHub stars. The repository holds 38 skills in this directory. The repository was last updated on October 5, 2026.

Source: FerroxLabs/ijfw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.