work-contract-portability
Use when designing agent work contracts, handoffs, evidence, and role boundaries across runtimes. Triggers:
What this skill does
# Work Contract Portability ## Purpose Make agent work transferable. Any qualified agent should be able to continue, review, validate, or replace another agent's work without relying on private memory, hidden assumptions, or personality-specific habits. Portable work is not created by making agents identical. It is created by shaping the task so continuation depends on explicit contracts, recorded evidence, concise handoffs, durable context, and clear role boundaries. ## Core Rule Prefer portable work products over personal continuity. A task is portable when another agent can answer these questions from the artifacts alone: - What outcome is required? - What constraints are binding? - What evidence proves the current state? - What decisions have already been made, and why? - What role is this agent playing now? - What remains open, blocked, risky, or intentionally deferred? ## Operating Principles ### Clear Contracts Define the work as a contract before optimizing execution. A useful contract states the requested outcome, accepted inputs, forbidden moves, ownership boundary, output shape, and validation criteria. If the contract is fuzzy, the next agent inherits ambiguity instead of progress. ### Evidence Evidence is the shared memory of the work. Prefer concrete artifacts: command output, tests, diffs, citations, logs, screenshots, decision records, and verdicts. Claims without evidence force the next agent to re-investigate the same ground. ### Handoffs A handoff should compress state without hiding uncertainty. Name what changed, what was verified, what was not verified, what failed, and what assumption the next agent must preserve or revisit. A good handoff is short enough to use and specific enough to audit. ### Durable Context Keep context portable by recording only the context needed to continue the work. Do not depend on chat history as the source of truth. Promote durable facts into repo files, issue records, generated reports, or explicit handoff notes. Remove noise, but preserve decision lineage. ### Role Boundaries State the role being played: researcher, planner, implementer, reviewer, validator, release operator, or steward. Role boundaries prevent one agent from silently changing the standard of proof. When a role changes, update the contract and evidence expectations. ## Application Checklist Use this checklist when shaping portable agent work: 1. Name the unit of work and its acceptance criteria. 2. List the artifacts another agent must inspect first. 3. Record decisions as decisions, not as incidental prose. 4. Attach evidence to every meaningful claim of completion. 5. Separate durable facts from temporary reasoning. 6. Identify the current role and the next expected role. 7. Close with a handoff that distinguishes done, pending, risky, and blocked. ## Failure Modes - Private continuity: progress exists only in one agent's memory. - Evidence debt: conclusions are present, but proof is missing. - Boundary drift: an implementer silently becomes the approver. - Context flooding: the next agent receives too much transcript and too little contract. - Handoff theater: a summary sounds complete but omits verification gaps. ## Output Return portability guidance that makes the work transferable: the contract, required evidence, handoff state, durable context to preserve, role boundaries, and any gaps that prevent another agent from safely continuing.
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.