AI coding lifecycle
Routes software work through 25 focused lifecycle skills across 8 packs, keeps durable mutation-aware state in .fable/state.json, and requires fresh evidence before completion.
Skills 25 in the ChatGPT listing
Fable Artifact Design and author structured technical proposals, responsive artifacts, architecture diagrams, Mermaid charts, and interactive components. Fable Config Configure and audit AI agent harness settings, permissions allowlists, environment variables, editor keybindings, and lifecycle hook integrations. Fable Cowork Execute autonomous multi-step cowork sessions with silent tool chaining, outcome-first progress reporting, and strict safety boundary enforcement. Fable Dataviz Design and generate accessible, cohesive data visualizations, SVG charts, metric cards, and dashboard tiles with theme-adaptive styling and verified viewports. Fable Delegate Delegate independent subtasks to parallel workers or subagents with strict disjoint ownership, bounded scope, and explicit acceptance contracts. Fable Discover Gather the smallest set of repository, environment, documentation, and runtime evidence needed before planning or changing code. Fable Eval Evaluate changes to agent prompts, skills, routing policies, and harnesses against reproducible baselines, held-out suites, and regression benchmarks. Fable Execute Implement one accepted, bounded work card with immediate local verification, invariant preservation, and zero scope drift. Fable Handoff Compact session decisions, durable evidence, open blockers, and exact next actions into structured continuation state for cross-session resumption. Fable Loop Execute bounded recurring polling loops, CI build babysitting, interval-based status monitors, and self-paced test cycles with explicit timeouts and backoff. Fable Memory Manage persistent file-based memory, indexing cross-session user preferences, feedback, and architectural constraints in structured MEMORY.md stores. Fable Plan Convert discovery evidence into bounded, testable work cards with explicit acceptance criteria and architectural invariants. Fable Recover Diagnose repeated command failures, stale build caches, branch drift, or contradictory evidence before attempting further code edits. Fable Release Audit and certify repository merge and release readiness against required quality gates, clean git working trees, and verified distribution artifacts. Fable Research Resolve current external facts, official documentation, library behaviors, and API contracts against primary sources before implementation. Fable Review Perform an independent, evidence-grounded review of git diffs against requested specifications, architectural invariants, and code standards. Fable Run Launch, manage, and verify live applications across CLI binaries, web servers, TUIs, Electron apps, and background daemons with readiness probes and clean teardown. Fable Security Conduct threat modeling, vulnerability assessments, secret sanitization, and security reviews across trust boundaries, auth flows, and untrusted inputs. Fable Simplify Refactor and simplify settled, recently modified code to improve readability, remove dead branches, flatten deeply nested logic, and reduce duplication while preserving behavior. Fable Simulator Verify complex code changes against independent mathematical oracles, derived specifications, headless browser environments, and isolated sandbox states. Skill Creator Author, evaluate, refine, optimize, and package autonomous AI agent skills across multi-agent ecosystems with BinEval scoring and description tuning. Fable Spark Predict the smallest atomic next engineering action from current workspace state, evidence gates, and mutation freshness with situational silence. Fable TDD Drive testable behavior changes and bug fixes through disciplined red-green-refactor cycles with observable regression tests. Fable Verify Falsify software implementations and gather fresh, machine-checked acceptance proof across tests, builds, typechecks, and runtime smoke checks before completion. Get Fable Orchestrate software engineering workflows across the canonical get-fable coding lifecycle with deterministic routing and evidence precedence. 