talon-ai-tools

Use when user wants help choosing an approach or isn't sure where to start — presents bar-based options.

Use when user wants bar to automatically shape every response — detects and applies bar structuring without being asked.

Use when user asks which token fits an intent — looks up bar tokens by intent phrase and returns ranked matches. token matches a user's intent, when you need the full metadata for a specific token, or when you need all tokens on an axis.

Use when user wants to learn bar commands or build prompts manually — guides bar CLI usage step by step.

bar CLI — structured prompting tool. Use when the user wants to run bar build, apply bar tokens, build a workflow, or get help with bar commands. Covers autopilot, workflow, suggest, manual, dictionary, and all bar token usage.

Use when user wants to chain multiple steps or build a sequence — constructs and runs multi-step bar command workflows.

Set up a tmp scenario from ADR-0239, run a haiku agent through it using the craft pack (bar build make witness ground gate falsify atomic), score the transcript against the 20-frame battery, and output a filled round-result block for the work-log.

Reference for all GrepAI MCP tools. Use this skill to understand available MCP tools and their parameters.

Advanced search options in GrepAI. Use this skill for JSON output, compact mode, and AI agent integration.

Find function callees with GrepAI trace. Use this skill to discover what functions a specific function calls.

Find function callers with GrepAI trace. Use this skill to discover what code calls a specific function.

Build complete call graphs with GrepAI trace. Use this skill for recursive dependency analysis.

Declarative workflow for running churn × complexity Concordance analysis and landing a numbered ADR with bundled scripts.

Applies when tasks involve structural or textual edits with supported grammars; documents the repository expectations for ast-grep workflows, diagnostics, and fallbacks.

Loads when bootstrap detection or harness detector configuration changes; outlines required refresh and validation workflow.

Activates when a task references Concordance ADRs 0107, 0118, 0119, 0120, 0123, or 0126; captures backlog assumptions, delivery expectations, and successor ADR guidance.

Triggers when work touches property harness guardrails, analytics probes, or hydration telemetry; documents required probe usage and verification steps.