delegate-deepseek
Delegate well-scoped coding/verification subtasks to deepseek-v4-flash via the Claude Code CLI in a lightweight, permission-free, context-free mode.
Skill by mattdanielmurphy
Chalk Labs
Need help deploying delegate-deepseek?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/mattdanielmurphy-delegate-deepseek
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: testing, writing, research, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/delegate-deepseek
What's inside
- Skill name
delegate-deepseek- Description
- Delegate well-scoped coding/verification subtasks to deepseek-v4-flash via the Claude Code CLI in a lightweight, permission-free, context-free mode. Use this to act as an orchestrator and conserve premium-model tokens for tasks like running scripts, writing throwaway test/verification code, mechanical edits, or research grunt work.
- License
- unknown
- Instructions
- 96 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from mattdanielmurphy/ai-os
- 0.567score
hermes-gateway-api
mattdanielmurphy
Configure and troubleshoot the Hermes Gateway HTTP API server — enabling port 8642, setting API_SERVER_KEY, and connecting external tools (Studio, dashboards…
SkillAFreshness: AClaude Code +9 - 0.561score
hermes-database-internals
mattdanielmurphy
Hermes Agent's SQLite database architecture — schema layout, FTS5 dual-tokenizer search, trigger-based index sync, and the pattern for safely ingesting…
SkillAFreshness: AClaude Code +9 - 0.559score
agy
mattdanielmurphy
Delegate through the agymcp MCP bridge by default; use the agy CLI only as a documented fallback.
SkillAFreshness: AClaude Code +9 - 0.558score
hermes-to-agy
mattdanielmurphy
Delegate to agy with full Hermes system context (SOUL + memory) for free Antigravity quota.
SkillAFreshness: AClaude Code +9 - 0.552score
agy-extreme-delegation
mattdanielmurphy
Configure agy to delegate EVERYTHING possible — editing, research, context-gathering — to Claude Code or subagent.py.
SkillAFreshness: AClaude Code +9 - 0.552score
_plan-with-gemini
mattdanielmurphy
Initiate high-reasoning implementation planning by spawning a planning subagent with Gemini 3.7 High without requiring GitHub repo sync.
SkillAFreshness: AClaude Code +9 - 0.552score
_plan-with-subagent
mattdanielmurphy
Initiate high-reasoning implementation planning by spawning a native subagent with Gemini 3.7 High without requiring GitHub repo sync.
SkillAFreshness: AClaude Code +9 - 0.551score
hermes-agent-skill-authoring
mattdanielmurphy
Author in-repo SKILL.md files: frontmatter and structure.
SkillAFreshness: AClaude Code +9 - 0.550score
hermes-desktop-plugins
mattdanielmurphy
Write desktop app plugins that add UI panes and commands.
SkillAFreshness: AClaude Code +9 - 0.549score
_manage-memory
mattdanielmurphy
Store, search, and prefetch durable memories via the battle-tested Mem0 engine.
SkillAFreshness: AClaude Code +9 - 0.549score
_plan-with-ai-os
mattdanielmurphy
Initiate high-reasoning planning via ai-os (Gemini) when explicitly requested by user.
SkillAFreshness: AClaude Code +9 - 0.516score
ai-os-audit
mattdanielmurphy
Run token waste audits on agent conversation transcripts using agy's audit_transcripts.py.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 17, 2026 (18 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/mattdanielmurphy/ai-os
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from mattdanielmurphy
- 0.567score
hermes-gateway-api
mattdanielmurphy
Configure and troubleshoot the Hermes Gateway HTTP API server — enabling port 8642, setting API_SERVER_KEY, and connecting external tools (Studio, dashboards…
SkillAFreshness: AClaude Code +9 - 0.561score
hermes-database-internals
mattdanielmurphy
Hermes Agent's SQLite database architecture — schema layout, FTS5 dual-tokenizer search, trigger-based index sync, and the pattern for safely ingesting…
SkillAFreshness: AClaude Code +9 - 0.559score
agy
mattdanielmurphy
Delegate through the agymcp MCP bridge by default; use the agy CLI only as a documented fallback.
SkillAFreshness: AClaude Code +9 - 0.558score
hermes-to-agy
mattdanielmurphy
Delegate to agy with full Hermes system context (SOUL + memory) for free Antigravity quota.
SkillAFreshness: AClaude Code +9 - 0.552score
agy-extreme-delegation
mattdanielmurphy
Configure agy to delegate EVERYTHING possible — editing, research, context-gathering — to Claude Code or subagent.py.
SkillAFreshness: AClaude Code +9 - 0.552score
_plan-with-gemini
mattdanielmurphy
Initiate high-reasoning implementation planning by spawning a planning subagent with Gemini 3.7 High without requiring GitHub repo sync.
SkillAFreshness: AClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get delegate-deepseek running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
delegate-deepseek skill. Agent Mart. https://agentmart.dev/skills/mattdanielmurphy-delegate-deepseek (last updated 2026-10-24)