Build Coherence

AI multi-path reasoning coherence using bee democracy — independent evaluation of competing approaches, waggle dance as reasoning-out-loud, quorum sensing for confidence thresholds, and deadlock resolution. Use when forage-solutions has identified multiple valid approaches and a selection must be made, when oscillating between options without committing, when justifying an architecture or tool choice with structured reasoning, or before an irreversible action where the cost of the wrong choice is high.

45 stars 4 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add pjt222/agent-almanac --skill build-coherence
Manual install
git clone --depth 1 https://github.com/pjt222/agent-almanac.git /tmp/agent-almanac
mkdir -p ~/.claude/skills
cp -r /tmp/agent-almanac/i18n/caveman-lite/skills/build-coherence ~/.claude/skills/build-coherence

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Build Coherence

Evaluate competing approaches through independent assessment, explicit reasoning-out-loud advocacy, confidence-calibrated commitment thresholds, and structured deadlock resolution — producing coherent decisions from multiple reasoning paths.

## When to Use

- `forage-solutions` has identified multiple valid approaches and a selection must be made
- Oscillating between two approaches without committing to either
- Needing to justify a decision with structured reasoning (architecture choice, tool selection, implementation strategy)
- When a previous decision was made by gut feeling and needs evidence-based validation
- When internal reasoning is producing contradictory conclusions and coherence must be restored
- Before an irreversible action (merging, deploying, deleting) where the cost of the wrong choice is high

## Inputs

- **Required**: Two or more competing approaches to evaluate
- **Optional**: Quality assessments from prior scouting (see `forage-solutions`)
- **Optional**: Decision stakes (reversible, moderate, irreversible) for threshold calibration
- **Optional**: Time budget for the decision
- **Optional**: Known failure mode (oscillation, premature commitment, groupthink)

## Procedure

### Step 1: Independent Evaluation

Assess each approach on its own merits before comparing them. The critical rule: do not let the assessment of approach A bias the assessment of approach B.

For each approach, evaluate independently:
Read the full skill on GitHub

Details

Skill name
build-coherence
Path
i18n/caveman-lite/skills/build-coherence/SKILL.md
License
MIT
Repo updated
18 November 2026

FAQ

What does the Build Coherence skill do?

AI multi-path reasoning coherence using bee democracy — independent evaluation of competing approaches, waggle dance as reasoning-out-loud, quorum sensing for confidence thresholds, and deadlock resolution. Use when forage-solutions has identified multiple valid approaches and a selection must be made, when oscillating between options without committing, when justifying an architecture or tool choice with structured reasoning, or before an irreversible action where the cost of the wrong choice is high.

How do I install the Build Coherence skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add pjt222/agent-almanac --skill build-coherence. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Build Coherence popular?

It lives in pjt222/agent-almanac, which has 45 GitHub stars and 4 forks, and is included in 1 curated skill list.

Related skills

Adapt Architecture

45

pjt222/agent-almanac

Execute structural metamorphosis using strangler fig migration, chrysalis phases, and interface preservation. Covers transformation planning, parallel running, progressive cutover, rollback design, and post-metamorphosis stabilization for system architecture evolution. Use when assess-form has classified the system as READY for transformation, when migrating from monolith to microservices, when replacing a core subsystem while dependents continue operating, or when any architectural change must be gradual rather than big-bang.

Software DevelopmentIn 1 list

Adaptic

45

pjt222/agent-almanac

Master skill composing the 5-step synoptic cycle for panoramic synthesis across multiple domains. Orchestrates meditate, expand-awareness, observe, awareness, integrate-gestalt, and express-insight into a coherent process that produces unified understanding rather than sequential compromise. Use when a problem genuinely spans 3+ domains and the interactions between domains matter more than depth in any one, when sequential analysis feels like compromise rather than integration, or before major architectural decisions affecting multiple stakeholders.

OtherIn 1 list

Add Puzzle Type

45

pjt222/agent-almanac

Scaffold a new puzzle type across all 10+ pipeline integration points in jigsawR. Creates the core puzzle module, wires it into the unified pipeline (generation, positioning, rendering, adjacency), adds ggpuzzle geom/stat layers, updates DESCRIPTION and config.yml, extends the Shiny app, and creates a comprehensive test suite. Use when adding a completely new puzzle type to the package or following the 10-point integration checklist to ensure nothing is missed end-to-end.

Testing & QAIn 1 list

Build Consensus

45

pjt222/agent-almanac

Achieve distributed agreement without central authority using bee democracy, threshold voting, and quorum sensing. Covers proposal generation, advocacy dynamics, commitment thresholds, deadlock resolution, and consensus quality assessment. Use when a group must decide between options without a designated leader, when centralized decision-making is a bottleneck, when stakeholders have different perspectives to integrate, or when designing automated systems that must reach consensus such as distributed databases or multi-agent AI.

AI, LLMs & AgentsIn 1 list

Bootstrap Agent Identity

45

pjt222/agent-almanac

Consistent agent behavior after restart — progressive identity loading, working context reconstruction from persistent artifacts, fresh-vs-continuation detection, calibration through centering and attunement, and identity verification for coherence. Addresses the cold-start problem where an agent must reconstruct who it is and what it was doing from evidence rather than memory. Use at the start of every new session, after a session interruption or crash, when agent behavior feels inconsistent with prior sessions, or when persistent memory and current context appear contradictory.

AI, LLMs & AgentsIn 1 list

Build Custom MCP Server

45

pjt222/agent-almanac

Build a custom MCP (Model Context Protocol) server that exposes domain-specific tools to AI assistants. Covers server implementation in Node.js or R, tool definitions, transport configuration, and testing with Claude Code. Use when you need to expose custom functionality beyond what mcptools provides, when building specialized domain-specific AI integrations, or when wrapping existing APIs or services as MCP tools.

AI, LLMs & AgentsIn 1 list

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.