farness
Use when the user wants advice or a decision recommendation rather than direct implementation, especially for prompts like "should I", "should we", "which is better", "is it worth it", or "what would you do" about architecture, product, hiring, strategy, or career choices. Prefer the local farness MCP server when available and structure the answer around KPI, option expansion, reference class, disconfirming evidence, numeric forecasts, and a review date.
What this skill does
# Farness
Use this skill to turn vague decisions into forecastable choices.
Prefer the local `farness` MCP server when it is connected.
## Workflow
1. If the decision is not stored yet, call `create_decision`.
2. Use the `analyze_decision` or `review_decision` MCP prompts for the canonical structure.
3. Make the analysis explicit:
- KPI definition
- KPI resolution metadata
- option expansion
- reference class / base rate
- mechanism or decomposition
- disconfirming evidence
- numeric forecasts with 80% confidence intervals
- a compact forecast summary table
- review date
4. Persist the result with `save_analysis`.
- `kpis` must be a list of objects shaped like:
`{"name": "...", "description": "...", "unit": "%|$|days|...", "target": 80, "weight": 1.0, "outcome_type": "binary|count|continuous|percent|currency|score", "resolution_date": "2026-06-30", "resolution_rule": "...", "data_source": "..."}`
- `options` must be a list of objects shaped like:
`{"name": "...", "description": "...", "forecasts": [{"kpi_name": "...", "point_estimate": 75, "ci_low": 60, "ci_high": 86, "confidence_level": 0.8, "reasoning": "...", "assumptions": ["..."], "base_rate": 68, "base_rate_source": "...", "inside_view_adjustment": "..."}]}`
- Do not pass KPI or option names as bare strings.
5. If outcomes are known, call `score_decision`.
6. If the user wants to externalize a forecast into a prediction market, draft it first:
- Use `farness forecast-draft <decision-id> --output forecast-pack.json` for stored decisions.
- Use `farness forecast-draft "<forecast question>" --initial-prob <1-99> --resolution-date YYYY-MM-DD --output forecast-pack.json` for standalone policy questions.
- Treat forecast drafts as review artifacts only; do not publish questions or place bets unless the user explicitly asks.
## Working Rules
- Do not give a vague recommendation before the KPIs and forecasts are explicit.
- In the first answer, show the forecast results without waiting to be asked again. Include a compact table or bullet summary of each option on the decisive KPIs.
- After the forecast summary, explain how those forecast differences drive the recommendation or prioritization.
- Prefer KPIs that can actually resolve later; avoid labels like `fit` or `quality` unless the resolution rule makes them numeric and scoreable.
- Keep the option set broader than the user's initial framing.
- Treat disconfirming evidence as first-class, not cleanup.
- Use the MCP server for persistence instead of leaving the analysis only in chat.
## Setup
If the `farness` MCP server is not connected, add it with:
```bash
farness setup claude
```
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.