agentleFS
seankoji-comseankoji-com/.agents/skills/challenge/SKILL.md

challenge

Skill2 starsChanged 10 days agoMITView on GitHub

Pressure-test an idea, design or proposal with an independent cross-lineage reviewer. Use when the user asks for an adversarial second opinion, asks "are you sure", or wants to challenge assumptions; return findings without implementation.

33 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use prove-it, ingest and 8 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

  • JaimeGBASkill

    ingest

    Digest an external source (article, paper, transcript, URL, book chapter) and integrate its content into the knowledge base

    Also in 4 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

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 29 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check each consequential finding against the sources or reproduction.

    line 43
  2. Distinctive:

    Default to one pass. Add one fresh, targeted second opinion only for a concrete unresolved consequential risk or disagreement.

    line 48
  3. Distinctive:

    Use readable text when native HTML is unavailable or the result is brief.

    line 57

“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

Challenge a proposal

Frame the problem, proposal, constraints and decision to be made from the user's request and available evidence. Ask only about material missing intent. Keep this workflow read-only apart from task-owned probes and presentation; no source edits, publication or external mutations. Observe host permissions and sharing limits.

Triggers such as "are you sure?", "challenge this" or a request for an adversarial second opinion select this workflow; implementation and repair requests do not.

Independent challenge

Apply review for cross-lineage eligibility, reviewer selection, dispatch and evidence. Use one fresh reviewer and require it to read and apply review in the assigned-reviewer role. Follow review's rule for named models, settings and conflicts.

Give the reviewer the problem, constraints, proposal, source/version and raw evidence. Do not prime it with the parent's preferred conclusion or earlier reviewer verdicts. Ask it to:

  • Identify assumptions that could invalidate the proposal.
  • Offer the strongest simpler alternative and its tradeoff.
  • Name evidence or a bounded probe that distinguishes the approaches.
  • Separate demonstrated failures, static evidence, plausible risks and unknowns.

Require a complete plain-text final report with stable finding IDs, severity, source locations, evidence, assumptions, alternative and discriminating next check. The delegate must not use html_render or return only a child-thread presentation. A timeout, missing report or completion status alone is not a completed challenge.

Allow safe, bounded probes only in task-owned isolated artifacts, with no live system changes or source edits. No findings is acceptable. Do not demand scores, consensus or a predetermined objection.

Assess and report

Check each consequential finding against the sources or reproduction. Retain statically demonstrated defects and clearly label risks that cannot safely be reproduced. Preserve disagreement with evidence; do not automatically accept or discard a finding because of its reviewer or rarity.

Default to one pass. Add one fresh, targeted second opinion only for a concrete unresolved consequential risk or disagreement. Unless explicitly named, choose the next eligible unused reviewer lineage in review's ordered list; report unavailable choices. Report unresolved decisions after that; do not loop to unanimity. Follow explicit user limits and stop task-owned work when complete or cancelled.

Return the recommendation, assumptions, supported findings, simpler alternative, discriminating next check, reviewer identity and material gaps. In T3 Code, the coordinator checks user-facing substantive reports with html_preview, inspects them and shows with html_render. Use readable text when native HTML is unavailable or the result is brief. Pressure testing alone does not authorize implementation.

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.