Agent skills for DeepSeek Harness

Context agent for continuity between sessions.

Progressive disclosure architecture for organizing project context as a DAG (directed acyclic graph).

Use when conversation context is too long, hitting token limits, or responses are degrading.

This skill SHOULD be used for structured extraction or batch queries against JSON (use jq), YAML (use yq), or Markdown (use mq), and for…

Use when designing agent system prompts, optimizing RAG retrieval, or when context is too expensive or slow.

Show how much context window context-mode saved this session.

Generate a compact first-pass repository briefing with context-pack.

Show current context status and session health.

Fetches current, version-specific library documentation and code examples through the Context7 MCP server.

Add or evolve ContextOS runtime contracts across TypeScript types, JSON Schemas, canonical examples, documentation, and drift tests.

Audit a ContextOS proof-carrying run using RunContext, CompiledContext, ToolEnvelope, DecisionRecord, trace, scorecard, and ReplayPacket…

Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into…

Validates and normalizes heterogeneous CSV and XLSX tables against explicit data contracts with deterministic mapping and quality gates.

Review contracts against your organization's negotiation playbook, flagging deviations and generating redline suggestions.

Analyzes contractor engagements against standard classification factors to assess operational exposure and evaluate remediation options.

Use when turning results into an explicit contribution statement for a Journal of Marketing Research (JMR) manuscript — clearing JMR's…

Review a contribution PR for safety, quality, and readiness.

Community and contributions command center -- manage GitHub Discussions, moderate community interactions, track contributor health…

Audit, disable, and restore selected Windows AI features through reviewable registry and policy changes with explicit elevation and…

Use when: (1) a new submission scores worse than baseline and the reason is unclear, (2) multiple changes were made simultaneously (new…