challenge
Skill4 starsChanged 7 months agoMITView on GitHub
Challenge a plan, design, or approach in two structured passes — scope/necessity, then correctness/completeness. Use before executing any plan.
33 other projects use a version of this.
Adopted by
Most recently taken up by
- SylphxAI/skillstheir own version, first seen Nov 8, 2026
- seankoji-com/.agentstheir own version, first seen Nov 8, 2026
- pedrohcgs/claude-code-my-workflowtheir own version, first seen Nov 7, 2026
- pche-broken-artist/forge-of-thoughttheir own version, first seen Nov 6, 2026
- bas1l/claude-skillstheir own version, first seen Nov 3, 2026
- grainulation/grainulatortheir own version, first seen Nov 3, 2026
Used with
Projects with it also use prove-it, ingest and 10 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-LabsSkillprove-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
JaimeGBASkillingest
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
MetaSkillroadmap
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
GoogleSkillcritique
Expertise in auditing and fixing repository scripts and GitHub Actions workflows to ensure technical robustness and security.
Also in 3 projects that use this
genomewalkerSkilllearn
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
AnthropicSkillstart
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
Other versions33 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 33
- pedrohcgs/claude-code-my-workflow★ 1.7ksame name
- me2resh/apexyard★ 542same name
- nudgebee/nudgebee★ 520same name
- The01Geek/prflow★ 99same name
- grainulation/grainulator★ 86same name
- BULDEE/ai-craftsman-superpowers★ 35same name
- TakaGoto/rag-learning-academy★ 24same name
- Hassaan146/claude-skills★ 18same name
- lenar-amirov/product-pipeline-public★ 13same name
- pche-broken-artist/forge-of-thought★ 12same name
23 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- user-level-reference/CLAUDE.mdCLAUDE.md
- commitSkill
- contribute-upstreamSkill
- jevSkill
- karpathy-guidelinesSkill
- mcp-usageSkill
- retro-reviewSkill
- sprintSkill
- sync-templateSkill
The file
We split this skill into the rules it gives an agent
12 rules. 0 are common, 10 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 29 edited versions we read keep these.
10
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
- Very specific: line 19
If $ARGUMENTS is provided, use it as the challenge target
- Distinctive: line 20
If omitted, identify the most recent plan, design, or proposed approach in the conversation
- Distinctive: line 21
If no clear target exists, ASK the user what to challenge
- Very specific: line 24
If an architect agent is available (team context with AGENT_TEAM.md), spawn the architect to perform both challenges
- Distinctive: line 25
If no architect is available (solo session), perform both challenges directly
- Distinctive: line 47
If no changes result from a pass, state: "Challenged — no changes needed"
- Distinctive: line 52
MUST perform exactly two challenge passes — never skip the second
- Distinctive: line 53
MUST challenge substance, not style — focus on correctness, scope, and completeness
- Distinctive: line 54
MUST preserve the original intent while cutting scope or simplifying
- Distinctive: line 55
MUST NOT rubber-stamp — if you can't find issues, look harder at assumptions and edge cases
- Distinctive: line 56
If the architect agent is available, MUST delegate to it rather than self-challenging
- Distinctive: line 57
After both passes, present the final revised version for user approval
“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.
Files
Challenge a Plan or Design
Challenge the current plan, approach, or design with two structured passes. Catches over-engineering, missing requirements, YAGNI violations, and implementation flaws early.
Arguments
$ARGUMENTS— (Optional) Description of what to challenge. If omitted, challenge the current plan or approach in the conversation context.
Workflow
- Identify the target
- If
$ARGUMENTSis provided, use it as the challenge target - If omitted, identify the most recent plan, design, or proposed approach in the conversation
- If no clear target exists, ASK the user what to challenge
- If
- Attempt architect delegation
- If an architect agent is available (team context with AGENT_TEAM.md), spawn the architect to perform both challenges
- If no architect is available (solo session), perform both challenges directly
- Challenge 1 — Scope & Necessity
- Is every component/feature actually needed? (YAGNI check)
- Are there simpler approaches that were dismissed too quickly?
- Are edge cases identified but deferred appropriately?
- Does the design solve the stated problem without gold-plating?
- Is the tier assignment (if applicable) correct for the scope?
- Could any pieces be cut without losing the core value?
- Challenge 2 — Correctness & Completeness
- Does the plan match the stated requirements faithfully?
- Are there missing steps, untested paths, or incorrect assumptions?
- Are error handling and validation covered at every layer?
- Will the proposed changes pass CI (formatting, linting, type checks)?
- Are there batches or tasks that should be cut or reordered?
- Does the team configuration (if applicable) match the assigned tier?
- Present results
- For each challenge pass, output a numbered list of:
- Changes made (cuts, additions, corrections)
- Rationale for each change
- If no changes result from a pass, state: "Challenged — no changes needed"
- Present the revised plan/approach incorporating all changes
- For each challenge pass, output a numbered list of:
Rules
- MUST perform exactly two challenge passes — never skip the second
- MUST challenge substance, not style — focus on correctness, scope, and completeness
- MUST preserve the original intent while cutting scope or simplifying
- MUST NOT rubber-stamp — if you can't find issues, look harder at assumptions and edge cases
- If the architect agent is available, MUST delegate to it rather than self-challenging
- After both passes, present the final revised version for user approval
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

