Count features marked as @failing and write to status JSON file. Used to determine when the autonomous coding loop should end.

Stop asking "How long will this take?" and start asking "How much is this worth to us?" By setting a fixed budget (an appetite) rather than a variable estimate, you force teams to find the simplest, m

forward-derivation

foundations

fractal-docs

The **GAM Researcher Agent** automates retrieval and synthesis of context from your Transmission Packet archive. It eliminates manual context pasting by implementing an iterative research loop that se

gas-clasp-ops

**Purpose:** Strategic enhancement and functional evolution of agent skills

Creates a new GitHub issue. Use when a new task, bug, or feature request needs to be tracked.

**Goal:** Stage a single, cohesive set of related file changes for an

Create, switch, and manage git branches with proper handling of uncommitted changes. Use when creating feature branches, switching contexts, or cleaning up after merges.

**`GOAL`**: present the git status in a visually appealing and

Manage Gitea wiki pages. Use when working with wiki content, creating documentation, or updating wiki pages.

GitHub 代码提交与推送 - 完整的 git commit 和 push 工作流，包含远程仓库配置、冲突处理和 SSH 推送。

Creates well-structured GitHub issues for the MCPSpy project using the gh CLI tool. Use when asked to create issues, report bugs, or document features. Follows conventional naming with feat/chore/fix prefixes and maintains appropriate detail levels.

GitHub issue lifecycle management with worktree isolation

Spawn and coordinate parallel Claude Code sub-agents using git worktrees. Use this skill when you need to parallelize work across multiple independent tasks, delegate subtasks to sub-agents, or orchestrate complex multi-part implementations.

Tracks micro-sprint completion state and progress for Google Sheets operations

Use when starting a session (resume previous work) or ending a session (create handover for next). Automatically detects mode based on conversation state. Cascades through completed handovers via Haiku subagents until finding incomplete work.

Automated quality check loops with escalation and fix sub-agents

View and analyze Hawk evaluation results. Use when the user wants to see eval-set results, check evaluation status, list samples, view transcripts, or analyze agent behavior from a completed evaluation run.

hcom

hecras_compute_plans

hecras_compute_remote

hecras_parse_compute-messages

Claude Code Hook system reference for capabilities, possibilities, and limitations. Use when you want to know what hooks can do.

>

<objective>

Use when analyzing Claude Code conversation logs to find patterns in repeated user instructions that could become skills. Ask for date range first.

'Query and manage feature implementation task status. Provides CLI tools to list features, check task status, find ready tasks, and validate task files. Used by /implement-feature orchestrator to track progress. Automatically updates task timestamps via hooks on /start-task.'

Design, organize, and operate Deepnote projects as the InsightPulseAI Data Lab workspace for exploration, jobs, and Superset-ready summary tables.

Install skills from github.com/oaustegard/claude-skills to `/mnt/skills/user`, making them available in the current and future conversations.

Enables GitHub repository operations (read/write/commit/PR) for Claude.ai chat environments. Use when users request GitHub commits, repository updates, DEVLOG persistence, or cross-session state management via GitHub branches. Not needed in Claude Code (has native git access).

>

Spawn a Claude worker to handle a GitHub issue. Fetches issue details, creates a feature branch, and works autonomously. Use when you want to delegate an issue to a worker.

Progressive context retrieval pattern for understanding unfamiliar codebases through iterative refinement

JaxLife open-ended agentic simulator for emergent behavior, tool use,

Proactively captures significant work into the journal for future reference

Daily journaling prompts and frameworks for reflection, growth, and clarity

Ultrathink LLM-as-Judge validation of completed work. Uses extended thinking by DEFAULT for thorough evaluation.

Feature Justice Matrix items for storytelling and content creation

Core coding patterns and conventions for Kalahari project. MUST be used by all code-related agents.

Use this skill when you are creating documentation for an existing Connect feature or updating existing docs

lfs

Intelligent, conversational interface for managing Linear workspace operations (issues, projects, teams, reporting)

literature-retrieval

Route AI requests to different LLM providers using SwiftOpenAI-CLI's agent mode. This skill automatically configures the CLI to use the requested provider (OpenAI, Grok, Groq, DeepSeek, or OpenRouter)

>