Business & Operations

Mix a small fraction of plain baseline responses into an adversarial submission to preserve cross-row score variance

Greedy local search that removes one element from a fixed position and re-inserts it at every possible index, keeping the best improvement per round

Hierarchical binary search over entity space by asking category, region, then first-letter questions to narrow candidates before guessing

Dynamically reduce max_tokens and batch size as wall-clock time approaches a cutoff to ensure all inputs get processed

Extracts calibrated yes/no probabilities from a VQA model by masking all logits except yes/no token variants and renormalizing via softmax.

Assembles N extracted tiles into a sqrt(N) x sqrt(N) mosaic image for single-forward-pass CNN inference on whole slide images.

Normalize raw stroke coordinates to 0-255 range, resample at uniform arc-length spacing, then apply Ramer-Douglas-Peucker simplification

Test-time augmentation via 4 rotation angles (0/90/180/270), applying inverse rotation to each prediction before averaging

Single CNN backbone with one shallow Dense neck per organ and mixed sigmoid (binary) + softmax (multi-class severity) heads, trained with a dict of losses so each organ is calibrated independently while sharing visual features

Subtracts a Gaussian-blurred version of the image from itself to normalize local illumination and enhance fine structural details.

Overlay real hair PNGs (masked via threshold) onto dermoscopy images to simulate body-hair occlusion as a domain-specific augmentation

Fix pixel overflow artifacts in 12-bit unsigned DICOM files where values wrap around at 4096

**Resource**: Internal Communications Skill Module **Repository**: [ComposioHQ/awesome-codex-skills/internal-comms](https://github.com/ComposioHQ/awesome-codex-skills/tree/master/internal-comms) **License**: Apache License 2.0 **Latest Update**: 2026-05-07

**Research Date**: 2026-05-10 **Source URL**: <https://github.com/Jamie-BitFlight/claude_skills/blob/main/.claude/skills/gh/SKILL.md> **GitHub Repository**: <https://github.com/cli/cli> **Version at Research**: 2.87.2 (released 2026-02-20) **License**: MIT (GitHub CLI project) ---

Use when the primary outcome is creating a new portable Agent Skill directory from one local documentation file, documentation directory, or Git repository, including mixed text and capability-gated binary sources that require exhaustive source-to-output accounting.

Optimize processes in a file or directory by converting prose/bullet workflows to Mermaid diagrams — delegates to the process-siren:process-siren agent. Use when given a single SKILL.md, agent file, CLAUDE.md, or rules file to convert, or a directory containing any of those. Supports --dry-run or --report for read-only planning mode.

Autonomous feature research and gap analysis. Use when starting /add-new-feature or analyzing existing architecture documents. Explores codebase patterns, identifies ambiguities, and produces feature-context-{slug}.md for orchestrator RT-ICA phase. Does NOT make technical decisions.

Evaluate a single skill's quality against its stated purpose. Classifies the skill's purpose type, then scores applicable quality categories — universal dimensions always apply; structural dimensions (scripts, references, assets) are scored only when warranted by the skill's purpose. A focused 20-line behavioral skill with no bundled resources scores fully on all applicable categories. Use when auditing skill quality, checking marketplace readiness, evaluating skill completeness, performing p...

Format and score completed plugin assessment findings without starting another assessment workflow. Use when a plugin assessment needs the standard report structure, scoring criteria, severity breakdown, or marketplace-readiness result.

Spawn and manage persistent interactive Claude Code CLI sessions with bidirectional communication via tmux. Provides spawn, send, read, status, list, and kill subcommands for orchestrating parallel peer sessions. Uses built-in --worktree and --tmux flags. Sessions stay alive for multi-turn steering. Triggers on "spawn claude session", "launch separate claude", "peer session", "inter-session communication", "shadow clone", "kage bunshin".

Use when the PLAN artifact from SAM Stage 2 needs contextualization against actual codebase state — grounds the design plan in reality by performing scope analysis (NEW/MODIFY/COMPLETE classification), conflict detection between plan assumptions and codebase patterns, and resource mapping to concrete file paths and integration points. Produces an updated ARTIFACT:PLAN registered via MCP with a Contextualization section appended.

Reviews CLI application code for correctness and quality. Use when reviewing tools that use argparse, click, typer, commander.js, or similar argument parsers — covers exit codes, help flags, stdin/stdout/stderr separation, non-interactive operation, signal handling, argument validation, ANSI color safety, and dry-run support for destructive operations.

Bash 5.3 release features and improvements with practical examples. Use when working with Bash 5.3 features, new command substitution, GLOBSORT, loadable builtins, or when user asks about Bash 5.3 changes, new features, or version-specific capabilities.

Bash 5.1 release features and improvements with practical examples. Use when working with Bash 5.1 features, epoch time variables, redirection enhancements, or when user asks about Bash 5.1 changes, new features, or version-specific capabilities.