agentleFS
slogsdonslogsdon/skills-vault-knowledge/skills/challenge/SKILL.md

challenge

Skill0 starsChanged 3 months agoMITView on GitHub

Use when Shane wants to pressure-test a belief, steelman an opposing view, or invoke /challenge. Do NOT use for confirming or validating a position.

33 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use prove-it, roadmap and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Neko-Catpital-LabsSkill

    prove-it

    Shared evidence rule for investigating, diagnosing, debugging, proving, or explaining what happened or why for any problem or situation: do not assert something is fixed, working, passing, merged, or running unless you personally observed it this turn and can show what you saw; do not assert it was caused by X until a repro and controlled isolation prove that cause.

    Also in 3 projects that use this

  • MetaSkill

    roadmap

    Build, continue, inspect, or visualize a source-grounded mathematical roadmap and theorem DAG in an existing Autoform Markdown blueprint. Use for source research, repository-wide inventories of existing and planned mathematics, scope, coverage, milestones, and roadmap articles; do not create repository infrastructure or prove Lean declarations.

    Also in 3 projects that use this

  • GoogleSkill

    critique

    Expertise in auditing and fixing repository scripts and GitHub Actions workflows to ensure technical robustness and security.

    Also in 3 projects that use this

  • genomewalkerSkill

    learn

    Learn from web sources, generate SKILL.md, and store key patterns in soul memory. Trigger keywords: learn, skill-gen, web-learn, documentation, tutorial.

    Also in 4 projects that use this

  • AnthropicSkill

    start

    Set up your bio-research environment and explore available tools. Use when first getting oriented with the plugin, checking which literature, drug-discovery, or visualization MCP servers are connected, or surveying available analysis skills before starting a new project.

    Also in 3 projects that use this

  • Hugging FaceSkill

    implement

    Make tests pass. Invoke after /write-tests produces failing tests.

    Also in 5 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 29 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Follow Qwen Protocol with:

    line 15
  2. Distinctive:

    If Qwen is unavailable:

    line 22
  3. Very specific:

    Run obsidian search query='[argument]' limit=10 via bash to find notes related to the topic

    line 24
  4. Very specific:

    Read the relevant notes by running obsidian read file='[note name]' via bash for each — look especially for where Shane states the position …

    line 25
  5. Distinctive:

    Search the vault for any counterevidence — places where Shane's own notes undermine the position

    line 29
  6. Distinctive:

    Don't soften it — the value is in the discomfort

    line 34

“Common” is measured: kept by at least 6 in 10 of the 29 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Skill: /challenge [argument]

Steelman the strongest opposition to a belief using vault evidence — the value is in the rigour of the challenge, not in protecting the position.

Don't: soften the opposition to protect Shane's self-image. Don't look for confirming evidence — look for what challenges the position.

Steps

  1. Parse the argument/topic from Shane's request.
  2. Follow Qwen Protocol with:
    • task: "Vault access (bash only, no MCP tools): obsidian search query='TERM' limit=10, obsidian read file='Note Name' (no .md). Steelman the strongest opposition to '[argument]'. Identify the most vulnerable assumptions, surface counterevidence from the vault, and pressure-test the position rigorously."
    • skill: "challenge"
  3. Review Qwen's result, synthesize if needed, and present to Shane.

Fallback

If Qwen is unavailable:

  1. Run obsidian search query='[argument]' limit=10 via bash to find notes related to the topic
  2. Read the relevant notes by running obsidian read file='[note name]' via bash for each — look especially for where Shane states the position most confidently
  3. Steelman the opposition:
    • Build the strongest possible case against [argument] — not a strawman, the actual best version
    • Find the most vulnerable assumptions underlying [argument]; name them explicitly
    • Search the vault for any counterevidence — places where Shane's own notes undermine the position
  4. Pressure-test the position:
    • What would have to be true for [argument] to be wrong?
    • What's the most common smart objection to this position?
    • What would a rigorous critic say?
  5. Don't soften it — the value is in the discomfort
  6. Present the challenge to Shane as: the strongest opposition case, the most vulnerable assumptions, and the counterevidence found in his own vault

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.