athola/claude-night-market - Page 2

code-communities

Detects architectural clusters and coupling boundaries via community detection on the code graph. Use when identifying module groupings or refactoring targets.

Langue du texte source : anglais

data-flow

Generates a Mermaid sequence diagram showing how data moves between components. Use when tracing request flows or documenting data transformation pipelines.

Langue du texte source : anglais

dependency-graph

Generates a Mermaid dependency graph showing import relationships between modules. Use when analyzing coupling, finding circular deps, or planning refactors.

Langue du texte source : anglais

workflow-diagram

Generates a Mermaid workflow diagram showing process steps, decisions, and state transitions. Use when documenting CI/CD pipelines or lifecycle processes.

Langue du texte source : anglais

gemini-delegation

Delegates tasks to Gemini CLI implementing delegation-core for Google's models. Use when delegation-core selects Gemini or 1M+ token context is needed.

Langue du texte source : anglais

qwen-delegation

Delegates tasks to Qwen CLI via delegation-core for Alibaba's models. Use when delegation-core selects Qwen or large-context batch processing is needed.

Langue du texte source : anglais

context-map

Generates a compressed project context map to avoid expensive Read/Grep calls. Use at session start or before implementing features in an unfamiliar codebase.

Langue du texte source : anglais

challenge

Presents adaptive codebase challenge questions with multiple-choice and trace exercises. Use when testing contributor knowledge of the codebase.

Langue du texte source : anglais

curate

Adds developer-authored annotations to the gauntlet knowledge base. Use when capturing tribal knowledge or rationale not visible in code.

Langue du texte source : anglais

extract

Builds the gauntlet knowledge base from AST extraction and AI enrichment. Use when initializing or refreshing codebase knowledge for challenges.

Langue du texte source : anglais

gauntlet-curate

Audits the DSA problem bank for coverage gaps and proposes new YAML entries. Use when refreshing the problem bank during update-plugins runs.

Langue du texte source : anglais

graph-build

Builds or updates the code knowledge graph via tree-sitter AST and SQLite. Use when setting up the graph before search or blast-radius analysis.

Langue du texte source : anglais

graph-search

Searches the code knowledge graph by function, class, or type using FTS5 full-text search. Use when locating code entities by name or qualified path.

Langue du texte source : anglais

onboard

Guides a new developer through five staged challenge sets covering architecture, domain, patterns, and hardening. Use when onboarding contributors.

Langue du texte source : anglais

assisted-mastery

Makes agent reasoning visible, surfaces tradeoffs, and fades help so humans build judgment. Use when reviewing or learning from agent-written code.

Langue du texte source : anglais

dependency-verification

Verifies a package exists before install, defending against hallucination and slopsquatting. Use when adding, recommending, or installing a package.

Langue du texte source : anglais

graduated-implementation

Ramps implementation ambition a notch only after the prior increment is understood. Use when building a feature you must understand, not just ship.

Langue du texte source : anglais

justify

Audits changes for additive bias and Iron Law compliance. Use when reviewing completed work before merging or after AI-assisted implementation.

Langue du texte source : anglais

karpathy-principles

Pre-implementation gate covering think-first, simplicity, surgical edits, and verifiable goals. Use when starting implementation to verify the approach.

Langue du texte source : anglais

rigorous-reasoning

Applies anti-sycophancy checklist to override agreement bias. Use when analyzing contested claims or avoiding socially convenient but inaccurate conclusions.

Langue du texte source : anglais

vow-enforcement

Classifies and enforces constraints via soft vows, hard vows, and Nen Court layers. Use when designing or auditing enforcement mechanisms for project rules.

Langue du texte source : anglais

workflow-monitor

Detects workflow failures and inefficient patterns then files GitHub issues. Use when a workflow step repeatedly fails or produces inconsistent output.

Langue du texte source : anglais

additive-bias-defense

Inverts burden of proof for code additions. Use when reviewing PRs, planning refactors, or running unbloat to challenge every addition's necessity.

Langue du texte source : anglais

memory-clarity-probe

Probe memory/summary clarity via dual anchor questions: task progress, info gaps. Use when verifying session state or summary before handoff or compression.

Langue du texte source : anglais

dora-metrics

Computes DORA delivery-performance metrics from git and GitHub API. Use when assessing deployment frequency, lead time, or change failure rate.

Langue du texte source : anglais

github-initiative-pulse

Generates markdown digests and CSV exports for GitHub initiative health. Use when reporting on issue/PR progress across a milestone or project.

Langue du texte source : anglais

release-health-gates

Standardizes release approvals with GitHub-aware checklists and deployment gates. Use before releasing to production to verify all gates pass.

Langue du texte source : anglais

setup

Provisions the oracle ML inference daemon with onnxruntime via uv. Use when setting up local ONNX model inference for skill quality evaluation.

Langue du texte source : anglais

api-review

Evaluates API surface design, consistency, and exemplar alignment. Use when reviewing public API changes or before releasing a new API surface.

Langue du texte source : anglais

blast-radius

Analyzes code change impact with risk scoring and affected-node mapping. Use before merging to understand what a change touches and what lacks test coverage.

Langue du texte source : anglais

performance-review

Detects time and space complexity hotspots via AST scan. Use when code feels slow, before performance-sensitive merges, or to find O(n²) regressions.

Langue du texte source : anglais

safety-critical-patterns

Applies NASA Power of 10 rules for safety-critical verifiable code. Use when auditing financial, medical, or high-reliability system code.

Langue du texte source : anglais

do-issue

Implements GitHub or GitLab issues via parallel subagents with review gates between task batches. Use when resolving multi-step issues end-to-end.

Langue du texte source : anglais

doc-consolidation

Merges ephemeral report and analysis artifacts into permanent documentation. Use when LLM-generated markdown files have accumulated and need consolidation.

Langue du texte source : anglais

git-workspace-review

Verifies workspace state and staged changes as a read-only preflight. Use before commits or PRs to confirm staged set is clean and correct.

Langue du texte source : anglais

pr-prep

Prepares pull requests by running quality gates, drafting descriptions, and validating tests. Use when completing a feature and ready for review.

Langue du texte source : anglais

stack-create

Initializes a stacked branch set from an ordered plan, one branch per slice with parent-child links. Use when a plan has 2+ sequentially dependent changes.

Langue du texte source : anglais

stack-mode

Detects shared stack membership and iterates a command across all PRs in base-to-tip order. Use when a command supports --stack flag for multi-PR iteration.

Langue du texte source : anglais

stack-push

Pushes all branches in a stack and opens or updates one dependent PR per slice. Use after stack-create to publish the stack or after adding commits to a slice.

Langue du texte source : anglais

stack-rebase

Cascades a rebase through an entire PR stack after a base PR merges or upstream changes. Use when a stack needs to incorporate new base branch commits.

Langue du texte source : anglais