agentic-assistant

Generate throughput and quality reports from coordinator audit data and episodic memory

Execute roadmap items iteratively with policy-aware vendor routing and learning feedback

Orchestrate the full plan-review-implement-validate-PR lifecycle with multi-vendor review convergence

Merge approved PR, migrate open tasks, archive OpenSpec proposal, and cleanup branches

Ingest raw session transcripts from coding-agent harnesses via vendor-specific adapters, normalize to a common event schema, triage for struggle signals, and write structured findings to episodic memory

HTTP fallback bridge for coordinator when MCP transport is unavailable

Analyze capability-gap failure patterns from episodic memory and generate improvement reports with OpenSpec proposal stubs

Triage, review, and merge open pull requests from multiple sources (OpenSpec, Jules, Codex, Dependabot, manual)

Shared parallel execution infrastructure: DAG scheduling, review dispatch, consensus synthesis, scope checking

Create OpenSpec proposal with tiered execution (coordinated / local-parallel / sequential)

Decompose a proposal into prioritized OpenSpec change candidates with a dependency DAG. Scaffolds a proposal first if none exists.

Drive a deployed frontend via Playwright using OpenSpec WHEN/THEN scenarios; emit behavioral_failure findings.

Analyze active OpenSpec proposals and produce a prioritized "what to do next" report

Open the artifacts relevant to a review (OpenSpec proposal, branch changes, or explicit paths) in VS Code, in a curated read-order, in the right worktree.

Shared roadmap artifact validation, checkpointing, learning-log helpers, and context assembly

Cloud environment bootstrap (setup script + verify hook) and coordinator lifecycle hooks

Structured decision records for session logs and merge logs at phase boundaries

Configure and verify coordinator access for CLI MCP and Web/Cloud HTTP runtimes

Deploy locally, run security scans and behavioral tests, check CI/CD, and verify OpenSpec spec compliance

Validation scripts for work packages, parallel zones, and work results

Worktree lifecycle management scripts — setup, teardown, heartbeat, pin, GC, merge

Archive a completed roadmap workspace to openspec/roadmaps/archive/<date>-<id>/

OpenBao/Vault credential seeding and management scripts

Comprehensive project health diagnostic — collects signals from CI tools, existing reports, deferred issues, and code markers into a prioritized finding report

Generate changelog entries and suggest semantic version bumps from git history

Curates the right context for an agent at the right time. Loaded by orchestrator skills (plan-feature, implement-feature, validate-feature) when a worker is about to start a task and needs to decide which rules, specs, source files, errors, and conversation history to surface. Covers the 5-level context hierarchy, named packing strategies, and the most common failure modes (starvation, flooding, stale context, missing examples, implicit knowledge, silent confusion). Tied to this repo's coordinator, work-packages.yaml scope rules, worktree branching, and OPENSPEC_BRANCH_OVERRIDE handoff conventions.

Render and seed coordinator-owned task status block in OpenSpec tasks.md

Write durable documentation that captures *why* a system is the way it is. Use when making a significant architectural decision, adding or changing a public API, shipping user-facing behavior, onboarding new humans or agents, or any time you find yourself explaining the same thing twice. Covers the ADR template (Status / Context / Decision / Consequences), ADR lifecycle (PROPOSED → ACCEPTED → SUPERSEDED → DEPRECATED), sequential numbering, the "comment intent not mechanics" rule, and a README skeleton (quick-start / commands / architecture). Localized to this repo's `docs/decisions/` capability-timeline format and OpenSpec workflow.

Readiness gate for sync-point operations — inspect validation, rework, and active-agent state before merge

Identify high-value next features using architecture artifacts, code signals, and active OpenSpec context

Implement approved OpenSpec proposal with tiered execution (coordinated / local-parallel / sequential)

Iteratively refine a feature implementation by identifying and fixing bugs, edge cases, and improvements

Iteratively refine an OpenSpec proposal by identifying and fixing completeness, clarity, feasibility, scope, consistency, testability, parallelizability, and assumptions issues

One front door for Langfuse — combines the Langfuse Agent Skill (best practices + docs), the Langfuse CLI (full API surface via npx), and the Langfuse MCP server (native prompt-management tool calls). Use when instrumenting an app, querying or modifying Langfuse data (traces, prompts, datasets, scores, sessions, evals), looking up Langfuse documentation, or configuring Langfuse for a new repo. Routes between Skill knowledge / CLI / MCP based on intent.

Per-package implementation review producing structured findings per review-findings.schema.json

Independent plan review producing structured findings per review-findings.schema.json

Dispatch N parallel variant agents to produce competing working skeletons from an approved proposal, score them via cheap validation phases, and capture human pick-and-choose feedback for convergence-aware refinement

Delegate small ad-hoc tasks to any configured vendor without OpenSpec ceremony

Refresh architecture analysis artifacts (docs/architecture-analysis/) from the codebase

Run reusable cross-project security review with profile detection, OWASP Dependency-Check, ZAP container scanning, and risk-gated reporting