agentleFS
lenar-amirovlenar-amirov/product-pipeline-public/.claude/skills/challenge/SKILL.md

challenge

Skill13 starsChanged 5 months agoMITView on GitHub

Adversarial gate rehearsal — a hostile stakeholder attacks the presentation against the hypothesis registry before the real gate does. Use when the PM says "завтра защита", "порепетируем гейт", "challenge my deck", "attack this presentation", "прогони как злой стейкхолдер", or before any Gate 1 / Gate 2 review.

34 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

  • BlockSkill

    plan

    Draft a TDD, PRD, or lightweight plan in the conversation without committing it.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 30 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run python3 tools/scripts/validate-evidence.py --gate <dir> — it checks three things: ≥2 hypotheses confirmed REAL, zero registry …

    line 14

“Common” is measured: kept by at least 6 in 10 of the 30 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 — /challenge [gate1|gate2|<file>]

The cheapest place to lose a gate is in rehearsal. Attack the PM's deck the way the real audience will — armed with the registry, which knows exactly where the evidence is thin.

0. Preconditions first

Run python3 tools/scripts/validate-evidence.py --gate <dir> — it checks three things: ≥2 hypotheses confirmed REAL, zero registry violations (ranges, unreconciled data_inconsistency), Frame complete (metric / baseline / target / kill criteria). If GATE BLOCKED — stop: report the blockers and the fastest way to clear each one. Rehearsing a deck built on unreconciled numbers wastes the PM's time.

1. Load the ammunition

  • The deck: output/presentation.md (Gate 1) or output/gate2-presentation.md
  • The registry: hypotheses.py show <dir> — statuses, confidences, flags, sources per hypothesis
  • CONTEXT.md — the promised metric/target
  • Last decisions.md entries — anything promised earlier and not delivered

2. Attack in three personas (in order)

CFO / sponsor — attacks the money and the sizing:

  • Where does the effect estimate come from? Which registry source backs each number on the sizing slide?
  • What's the cost of being wrong? Kill criteria defined?
  • "Why this and not the other initiative competing for the same team?"

VP Product — attacks the problem-solution link:

  • Which slide claims rest on SYNTHETIC/INFERRED evidence presented as fact? (cross-check every proof slide against the registry — this is the highest-yield attack)
  • Refuted or flagged hypotheses: does the deck quietly rely on any?
  • Segment sizes: do funnel numbers on different slides agree?

Skeptic engineer / analyst — attacks the data:

  • Metric definitions: same metric, same definition on every slide?
  • data_inconsistency flags: "these two numbers contradict — which is true?"
  • Baseline windows and seasonality; sample sizes for any test claims.

3. Report

For each hit: slide/claim → the attack question → severity (fatal / painful / cosmetic) → how to fix before the gate (patch the slide, move to speaker notes, reconcile the number, downgrade the claim). Fatal = presentation should not go out; list fatals first. End with the 3 questions most likely to actually be asked, and suggested answers backed by registry sources.

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.