a5c-ai/babysitter

adversarial-proof-audit

Audit immutable mathematical artifacts through isolated evidence-focused review lenses

原文の言語: 英語

mathematical-artifact-validation

Run fail-closed deterministic validation for mathematical and LaTeX artifacts

原文の言語: 英語

proof-obligation-registry

Maintain durable proof-obligation registries with profile coverage and semantic ledgers

原文の言語: 英語

six-dimension-code-review

Structured pull-request review across six fixed dimensions — correctness, clarity, consistency, coverage, complexity, and change-scope — producing a per-dimension verdict plus severity-tagged findings. Use when reviewing a PR diff or running the collaboration…

原文の言語: 英語

generative-media-prompting

The shared brief-to-prompt convention behind the media point tasks — parse the brief, select the model or tool, construct the prompt, then QA the output against the brief. Use when prompting for image, video, speech, or music generation or editing.

原文の言語: 英語

kip-librarian

Canonical kip knowledge-store patterns for any process or agent: recall prior facts before work, assert decisions/gate outcomes/rejections as structured facts after work, resolve entities with explicit --model sonnet, and invoke the CLI Windows-safely via…

原文の言語: 英語

atlas-graph-query

Reference for querying the Atlas knowledge graph through its MCP tools — the SECONDARY enrichment/comparison layer that adds best-practice context to systems you have ALREADY scanned from your real sources (`az`, repos, dirs). Use when you need to look up…

原文の言語: 英語

atlas

Atlas turns your STATED NEED into a real systems atlas by SCANNING your actual sources (Azure via `az`, git repos, local dirs) and process/data mining them, THEN enriching against the Atlas knowledge graph. Use this skill when asked to inventory/map your real…

原文の言語: 英語

assimilate-popular-workflows

This skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md files in repos", "research external skills", "find workflow patterns", "survey the skill landscape", "what skills exist out there",…

原文の言語: 英語

jsdoc-tsdoc

JavaScript and TypeScript documentation generation using JSDoc and TSDoc. Parse source code, generate API documentation, validate coverage, and integrate with TypeDoc for comprehensive developer documentation.

原文の言語: 英語

systematic-debugging

Structured debugging methodology using hypothesis-driven investigation, log analysis, and bisection to isolate and resolve defects.

原文の言語: 英語

zk-circuits

Zero-knowledge circuit development using Circom and Noir languages. Supports constraint optimization, ZK-friendly cryptographic primitives, proof generation (Groth16, PLONK), and Merkle tree implementations.

原文の言語: 英語

timing-constraints

Expert skill for developing and validating timing constraints. Writes SDC (Synopsys Design Constraints) and XDC files for FPGA timing closure.

原文の言語: 英語

integrate-harness

Use when adding a new agent harness (CLI-based coding agent) adapter to adapters. Covers capability audit, adapter scaffold, session parsing, auth detection, hooks/plugins wiring, tests, and docs.

原文の言語: 英語

storybook-docs

Storybook integration for UI component documentation. Configure docs addon, generate component documentation from stories, write MDX documentation, and integrate with design systems.

原文の言語: 英語

greet

Greet the user with a friendly message

原文の言語: 英語

test

A test skill for the compiler

原文の言語: 英語

process-builder

Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.

原文の言語: 英語

accomplish-status

Report babysitter orchestration run status to Accomplish AI desktop app via file-based IPC

原文の言語: 英語

babysit

Execute via @babysitter. Use this skill when asked to babysit a task, do anything that is structured process-driven (even a loop) or whenever it is called explicitly. (babysit, babysitter, with a process, orchestrate, orchestrate a run, workflow, loop until,…

原文の言語: 英語

architecture-patterns

System and API design guidance covering component boundaries, data flow, integration patterns, and scalability considerations.

原文の言語: 英語

code-generation

Minimal, pattern-matching code output. Write the least code that satisfies requirements. Match existing project patterns. Use Write/Edit tools only.

原文の言語: 英語

code-review-patterns

Multi-dimensional code assessment across security, quality, performance, and maintainability with confidence-gated reporting (>=80%) and Router Contract generation.

原文の言語: 英語

debugging-patterns

Root cause analysis frameworks including log-first investigation, git bisect correlation, and pattern-based diagnosis with confidence scoring.

原文の言語: 英語

planning-patterns

Structured planning methodology with research, brainstorming, phased plan creation, risk assessment, and plan-to-build continuity.

原文の言語: 英語

session-memory

Mandatory memory persistence system across session resets using three markdown surfaces in .claude/cc10x/. Iron law - every workflow must load at start and update at end.

原文の言語: 英語

test-driven-development

Strict RED-GREEN-REFACTOR cycle enforcement. Tests are never skipped or deferred. Run mode only, never watch mode. Exit code evidence mandatory.

原文の言語: 英語

verification-before-completion

Evidence requirement enforcement ensuring all claims are backed by logs, test results, or exit codes. Zero = success, non-zero = failure. No guessing allowed.

原文の言語: 英語

checkpoint-management

Git-backed state management for safe rollback. Create and restore checkpoints with tagged commits and metadata tracking.

原文の言語: 英語

code-review-orchestration

6-agent parallel code review orchestration covering architecture, security, performance, testing, quality, and documentation dimensions with weighted scoring.

原文の言語: 英語

codebase-mapping

Automatic codebase indexing for invisible context injection. Catalogs project structure, file types, entry points, dependencies, and test layout.

原文の言語: 英語

file-guard

PreToolUse protection blocking sensitive file access across 195+ patterns in 12 categories with bash pipeline analysis and multi-tool ignore support.

原文の言語: 英語

hook-management

Session-scoped hook lifecycle management with enable/disable/status controls, execution profiling, and color-coded performance alerts.

原文の言語: 英語

research-orchestration

Parallel research agent orchestration dispatching 5-10 concurrent agents for comprehensive multi-source research with synthesis and validation.

原文の言語: 英語

spec-creation

Feature specification creation from codebase research. Produces requirements, acceptance criteria, architecture decisions, implementation plans, and risk analysis.

原文の言語: 英語

spec-execution

6-phase iterative specification execution workflow covering implementation, testing, review, improvement, commit, and progress tracking with quality-gated convergence.

原文の言語: 英語

cog-braindump-capture

Capture raw thoughts with automatic domain classification and vault routing

原文の言語: 英語

cog-daily-intelligence

Generate personalized verified news briefs with 7-day freshness and 95%+ source accuracy

原文の言語: 英語

cog-knowledge-consolidation

Build structured knowledge frameworks from scattered vault notes with source attribution

原文の言語: 英語

cog-meeting-processing

Process meeting recordings and transcripts into decisions, action items, and team dynamics

原文の言語: 英語