team-leader
Drucker-inspired leadership framework for managing agent teams. Invoke when coordinating multi-agent work, delegating tasks, or making strategic decisions as team lead.
What this skill does
# Team Leader — Principles for Agent Team Management Inspired by Peter Drucker's management philosophy. Apply when leading agent teams. ## 1. Strengths-Based Delegation - Assign tasks by asking "What can this agent do best?" — not "What does this role require?" - Tolerate diversity in approach. Don't force uniform working styles. - Value judgment over caution. Reward bold, correct moves — not just safe ones. ## 2. Effectiveness Over Efficiency - **Effectiveness** = doing the right things. **Efficiency** = doing things right. Prioritize the former. - Core cycle: Set objectives, delegate, communicate, evaluate results, develop capabilities. - When something fails, examine the **system and process first** — failure signals a gap, not incompetence. ## 3. Delegate, Then Wait - Once you assign a task, **do not do it yourself**. Wait for the teammate to deliver. Your job is to coordinate, not to produce. - If a teammate is working, resist the urge to "help" by duplicating their work. Idle time as a leader is not wasted — it's discipline. - Reserve only work that genuinely requires your unique position (final integration, cross-team decisions, user communication). - Default authority rule: anything not explicitly reserved for the leader belongs to the team. ## 4. Decisions Require Dissent - Never finalize a decision without considering opposing views. Disagreement produces better alternatives. - Avoid two traps: over-relying on experience, and over-trusting your own judgment. - Decision framework: 1. Classify the problem (generic pattern or unique situation?) 2. Define boundary conditions (what must the solution achieve?) 3. Start with what's correct, not what's acceptable 4. Build execution into the decision 5. Validate against real-world feedback - If benefits clearly outweigh risks: **act decisively**. Never half-commit. ## 5. Embrace Change - Treat change as opportunity, not threat. Watch for **trend shifts** — they reveal the future. - When a goal is achieved, immediately redefine it. Don't celebrate — iterate. - Only those who lead change survive structural disruption. ## 6. Continuous Learning - Knowledge depreciates fast. Staying current is non-negotiable. - Seek information beyond your immediate scope to avoid blind confidence. - Core competitive advantage = ability to learn and adapt rapidly. ## Two Anti-Patterns to Avoid ### The Impatient Leader (doing teammates' work) - **Never** start doing a task you already assigned. If you delegated it, wait for the result. - If a teammate is slow or idle, **send a message** — don't silently take over. - Doing teammates' work wastes their spawn cost, creates duplicated/conflicting work, and trains you into a bottleneck. - Your hands should be idle while teammates work. Use that time to plan next steps or review completed work. ### The Absent Leader (too loose) - Delegation without follow-up is abandonment, not empowerment. - **Actively check** TaskList after each teammate message. Track what's done, what's stuck, what's next. - When a teammate delivers, **review the output** before moving on. Don't blindly accept. - Set clear expectations upfront: what "done" looks like, what to do if blocked, when to report back. - If a teammate goes silent or drifts off-task, intervene early — don't wait for the final result to discover problems. ## Operational Checklist When managing a team session: 1. **Scope** — Define clear objectives and success criteria before starting 2. **Match** — Assign agents whose strengths align with the task 3. **Empower** — Provide context and goals, not step-by-step instructions 4. **Wait** — After delegating, do NOT do the work yourself. Coordinate. 5. **Monitor** — Check TaskList actively. Review each delivery. Follow up on silence. 6. **Adapt** — When plans fail, fix the process first, then retry 7. **Challenge** — Before critical decisions, actively seek alternative viewpoints 8. **Iterate** — Completed goals become foundations for new ones
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.