agent-intercom

Browser automation skill. Drives agent-browser through structured navigate→snapshot→interact→re-snapshot flows with authentication support, form automation, visual verification, and explicit human checkpoints for external flows.

Autonomous iterative experimentation loop. Defines a measurable goal, establishes a baseline, then iterates modify→commit→measure→keep/revert until the goal is met or the budget is exhausted. Persists a TSV experiment log under the configured results directory.

GI/GR reconciliation gate for shipment manifests — verifies every manifest item exists in queue (pre-mode) or archive (post-mode) with the expected status before or after backlogit_ship_shipment runs.

On-demand harness health diagnostic. Checks manifest presence, version drift, file integrity, cross-reference validity, MCP tool availability, and template variable residue. Produces a per-category graded health report.

Multi-phase security audit skill. Scans agentic config surfaces and application source for OWASP Top 10 vulnerabilities, STRIDE threats, and config hygiene issues. Produces a scored, graded report persisted to the configured security docs directory (default: docs/security).

Scaffolds compilable but failing test harnesses for feature and chore tasks

Decomposes a reviewed implementation plan into backlog feature/task/subtask hierarchy

Multi-persona review gate for implementation plans. Validates architectural soundness, scope boundaries, and coding standards compliance before the harvest skill decomposes a plan into work items.

Manages the full PR lifecycle: creation, review comment handling, CI remediation, and user-approved merge

Structured code review using tiered persona subagents, confidence-gated findings, and a merge/dedup pipeline. Use when reviewing code changes before creating a PR, as a build gate, or for standalone review.

Explore requirements and approaches through collaborative dialogue before writing a right-sized requirements document. Use for feature ideas, problem framing, or when the user says 'brainstorm', 'explore', 'what should we build', or 'help me think through'.

Transform feature descriptions or requirements into structured implementation plans grounded in repo patterns and research. Use when the user says 'plan this', 'create a plan', 'how should we build', 'break this down', or when a brainstorm requirements document is ready for technical planning.

Usage: Run HITL tests. Executes human-in-the-loop test scenarios against a live agent-intercom server with real Slack integration.

Usage: Run automated tests. Executes Rust API coverage and a self-seeding Playwright UX suite so routine validation does not require the manual HITL skill.

Usage: Build feature {spec-name} phase {phase-number}. Implements a single phase from the spec's task plan, iterating build-test cycles until the phase passes its constitution gate, then records memory, logs decisions, and commits.

Usage: Fix CI. Detects CI pipeline failures on the current branch's PR, reproduces and fixes errors locally, runs all CI gates, then pushes and polls until the pipeline passes.

Usage: Compact context. Captures the current session state into a structured checkpoint file, then compacts the conversation history to reclaim context window space.