行動開發
3314 skills in 開發 > 行動開發
llm-inference-batching-scheduler
Guidance for optimizing LLM inference request batching and scheduling problems. This skill applies when designing batch schedulers that minimize cost while meeting latency and padding constraints, involving trade-offs between batch count, shape selection, and padding ratios. Use when the task involves grouping requests by sequence lengths, managing shape compilation costs, or optimizing multi-objective scheduling with hard constraints.
vulnerable-secret
This skill provides guidance for extracting secrets from vulnerable executables. It should be used when tasks involve binary analysis, reverse engineering executables to find hidden flags/secrets, or exploiting buffer overflows and other vulnerabilities to extract protected data. Applicable to CTF challenges, security research, and authorized penetration testing scenarios.
code-from-image
Extracting code or pseudocode from images using OCR, then interpreting and implementing it. This skill should be used when tasks involve reading code, pseudocode, or algorithms from image files (PNG, JPG, screenshots) and converting them to executable code. Applies to OCR-based code extraction, image-to-code conversion, and implementing algorithms shown in visual formats.
tam-calculator
Calculate Total Addressable Market (TAM), Serviceable Addressable Market (SAM), and Serviceable Obtainable Market (SOM) using top-down, bottom-up, and value-theory approaches with credible data sources and VC-ready presentation.
AILANG Sprint Executor
Execute approved sprint plans with test-driven development, continuous linting, progress tracking, and pause points. Use when user says "execute sprint", "start sprint", or wants to implement an approved sprint plan.
ln-333-task-rework
Fixes tasks in To Rework and returns them to To Review. Applies reviewer feedback only for the selected task.
constraints-scheduling
Provides systematic approaches for solving constraint-based scheduling problems, such as finding meeting times that satisfy multiple participant availability windows, preferences, and existing calendar conflicts. This skill should be used when tasks involve scheduling with constraints, calendar conflict resolution, time slot optimization, or finding valid time windows across multiple inputs with hard and soft constraints.
sqlite-db-truncate
This skill should be used when recovering data from corrupted or truncated SQLite databases. Apply this skill when a .db file cannot be opened with standard SQLite tools, when binary truncation has occurred, or when manual parsing of the SQLite binary format is needed to extract recoverable data.
gcode-to-text
Decode and interpret text content from G-code files by analyzing toolpath geometry and coordinate patterns. This skill should be used when extracting text, letters, or symbols that are encoded as movement commands in G-code files (e.g., 3D printing, CNC engraving, laser cutting). Applies to tasks like identifying what text a G-code file will print/engrave, reverse-engineering embossed or engraved text from toolpaths, or visualizing G-code geometry to reveal hidden content.
protein-assembly
Guidance for designing and assembling multi-component fusion protein sequences, particularly for FRET biosensors and tagged constructs. This skill applies when tasks involve identifying proteins by spectral properties (excitation/emission wavelengths), assembling fusion proteins from multiple domains, codon optimization with GC content constraints, working with PDB sequences and fluorescent protein databases, or generating gBlock sequences for gene synthesis.
multi-source-data-merger
This skill provides guidance for merging data from multiple heterogeneous sources (JSON, CSV, Parquet, XML, etc.) into a unified dataset. Use this skill when tasks involve combining records from different file formats, applying field mappings, resolving conflicts based on priority rules, or generating merged outputs with conflict reports. Applicable to ETL pipelines, data consolidation, and record deduplication scenarios.
ln-312-task-replanner
Updates ALL task types (implementation/refactoring/test). Compares IDEAL plan vs existing tasks, categorizes KEEP/UPDATE/OBSOLETE/CREATE, applies changes in Linear and kanban.
ipsw
Apple firmware and binary reverse engineering with the ipsw CLI tool. Use when analyzing iOS/macOS binaries, disassembling functions in dyld_shared_cache, dumping Objective-C headers from private frameworks, downloading IPSWs or kernelcaches, extracting entitlements, analyzing Mach-O files, or researching Apple security. Triggers on requests involving Apple RE, iOS internals, kernel analysis, KEXT extraction, or vulnerability research on Apple platforms.
app-standards
All modes that write scripts or code follow these app standards for communication, modularization, simplification, naming conventions
app-knowledge
When any part of the application needs to be found or understood.
anyway-config-coder
Implement type-safe configuration with anyway_config gem. Use when creating configuration classes, replacing ENV access, or managing application settings. Triggers on configuration, environment variables, settings, secrets, or ENV patterns.
industry-research
Research a market, pinpoint an underserved customer pain, and design a venture that can capture the opportunity within 12 months. Comprehensive 10-step workflow from market mapping to 90-day action plan.
design-language-system
Apply the professional Navy Blue colour scheme and design tokens. Use when styling components, charts, or ensuring colour consistency across the application.
useful-discoveries-check
For finding solutions, patterns, and workarounds to issues when encountering unexpected behavior, or when stuck after trying initial approaches
sam-cell-seg
Guidance for SAM-based cell segmentation and mask conversion tasks involving MobileSAM, mask-to-polygon conversion, CSV processing, and command-line interface design. This skill applies when working with Segment Anything Model (SAM) for biological image segmentation, converting binary masks to polygon coordinates, processing microscopy data, or building CLI tools that interface with deep learning models. (project)