harness-kit

Audit the fable roadmap (docs/fable_roadmap/) — verify claimed progress with proof, write a short report, update RESUME state + BACKLOG rank. Use at wave close or whenever the user asks how roadmap development is going. Triggers on - 'fable audit', 'roadmap audit', 'how is the roadmap going', 'audit progress', or /fable-audit.

Run a scout wave over outside sources (links, blogs, trending repos) into a progressive-disclosure research wiki in the current project, then distill findings into the project's ideas/backlog file. Generic across projects. Use when the user shares links/blogs to research, asks to "scout", "build a wiki from these", or wants outside ideas funneled into planning. Triggers on - 'scout wave', 'wiki scout', 'research these links', 'update the wiki', or /hk-scout-wiki.

Create and maintain a shift-handover HTML changelog artifact — a page the returning human reads in two minutes to know everything that happened while they were away. Generic across projects. Use when working autonomously for an away user, when asked for a changelog/progress page/catch-up artifact, or at every meaningful transition once one exists. Triggers on - 'changelog artifact', 'progress page', 'what happened while I was away', 'keep me posted in html', or /hk-shift-changelog.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. Triggers on: 'create a skill', 'new skill', 'make a skill for', 'improve this skill', 'test this skill', 'skill eval', 'optimize skill description', or /hk-skill-creator.

Run comprehensive agent-native architecture review with scored principles. Audits a codebase against 8 agent-native architecture principles (Action Parity, Tools as Primitives, Context Injection, Shared Workspace, CRUD Completeness, UI Integration, Capability Discovery, Prompt-Native Features) by launching parallel sub-agents and producing a scored report. Use when the user wants to evaluate how agent-friendly their architecture is, or audit specific principles. Triggers on: 'agent native audit', 'architecture review', 'how agent-friendly is this', or /hk-arch-audit.

Audit whether an AI agent can autonomously close the loop on problems in a given area — from discovering a symptom to verifying a fix — without human intervention. Evaluates documentation, diagnostic tools, commands, logs, and flows for completeness and actionability. Generates a gap-focused report with ratings. Use this skill whenever someone wants to assess debugging readiness, check if docs are agent-sufficient, audit a workflow for autonomous solvability, evaluate operational tooling coverage, or wants to know 'could an agent fix this on its own?' Triggers on: 'loop audit', 'audit this flow', 'is this debuggable', 'agent readiness', 'can an agent solve this', 'autonomous debugging check', or /hk-autonomy-audit.

Traces a workflow end-to-end through the harness-kit monorepo and creates a breadcrumb analysis doc in docs/breadcrumb_analysis/. Use this skill whenever the user wants to document a flow, trace a workflow, understand how a feature works across layers (frontend → backend → worker → CLI), or create debugging guides for a specific flow. Also use when the user mentions 'breadcrumb', 'trace this flow', 'how does X work end to end', 'document this workflow', or /hk-breadcrumb-creator.

Generate changelog entries from git diffs, prepend to CHANGELOG.md, and optionally commit + PR. Use when the user wants to update the changelog.

Compound a learning into a reusable pattern. Use after solving a non-trivial problem, discovering a principle worth reusing, or hitting a gotcha that would bite someone else. Triggers on: 'document this', 'capture this learning', 'that was tricky', 'let's compound this', 'compound this', or /hk-compound.

Consults existing breadcrumb analysis docs before exploring the codebase. Use this skill whenever the user asks about how a flow works, where something happens in the code, how to debug or test a specific area, what files are involved in a feature, or needs to understand the path data takes through the system. Also trigger when the user mentions 'where does X happen', 'how does Y work', 'trace this', 'what files handle Z', 'how to test this flow', 'debug this area', or when you're about to spawn multiple exploration subagents to understand a cross-cutting flow. Even if the user doesn't explicitly ask — if the task requires understanding how multiple layers connect (frontend → backend → worker → CLI), check breadcrumbs first. This is cheaper and more accurate than re-discovering the same information through code search.

Run diagnostic scripts on tasks, specs, boards, or reflections. Wraps testing_tools/ with proper working directory and output mode selection. Use this skill whenever the user wants to inspect, debug, or check the state of a task, spec, board, or reflection — even if they don't say 'inspect' explicitly. Triggers on: 'why did task X fail', 'show me spec Y', 'what's on the board', 'check task', 'inspect', 'diagnose', or /hk-local-diagnose.

Inspect and debug errors via logs across the harness-kit monorepo. Reads the right log file based on the error layer — backend, frontend, celery, odin CLI, or odin task execution. Use this skill whenever someone mentions a 500 error, a stack trace, a crash, 'check the logs', 'what went wrong', a service not starting, celery task failures, or any runtime error. Also triggers on: 'getting 500', 'backend error', 'celery error', 'odin failed', 'check logs', 'tail logs', 'debug this error', or /hk-local-logs.

Plan and execute an odin spec. Handles working directory, auth, nested-session detection, and post-run diagnostics. Use whenever the user wants to run a spec, test a spec, or do a smoke test. Triggers on: 'run this spec', 'test this spec', 'odin plan', 'smoke test', or /hk-local-run-spec.

Resolve merge conflicts in the current branch. Only invoke when the user explicitly runs /hk-merge-resolve. Do NOT auto-trigger on mentions of merge conflicts, conflict markers, or similar keywords.

Mock-first, layer-by-layer feature development. Instead of building a feature end-to-end and hoping the interface works, start by mocking at the user-facing surface with realistic data, get user acceptance on the experience, then deepen one complexity layer at a time with TDD. Everything is anchored on disk so work survives across sessions. Use whenever building a new feature, adding significant UI, planning a multi-layer change, or when the user mentions 'mock first', 'let me see it first', 'prototype this', 'simulate this feature', 'build this layer by layer', or /hk-mock-first.

Interactive Root Cause Analysis enforcer. Guides you through the 7-step RCA protocol: Reproduce, Locate, Hypothesis, Failing Test, Fix, Verify Live, Document. Use when debugging a bug, investigating a failure, or when something unexpected happened. This skill gates each step — it won't let you skip to a fix without stating a hypothesis first. Triggers on: 'something is broken', 'debug this', 'why is this failing', 'RCA', 'root cause', or /hk-rca.

Iteratively improve any output by running a structured observe-hypothesize-change-rerun loop. Uses an organized scratch directory to prevent context blowup — the conversation stays thin while iterations accumulate on disk. Use when an output (reflection, plan, prompt, pipeline result) isn't good enough and needs systematic refinement. Triggers on: 'close the loop', 'this output isn't good enough', 'iterate on this', 'refine this output', 'improve this reflection', or /hk-refine.

Run a codebase hygiene audit. Scans for misplaced files, dead code, temp files, security issues, structural problems, dependency slop, and git slop. Outputs a prioritized report with P0-P4 findings. Use periodically or before releases. Triggers on: 'audit the codebase', 'find slop', 'hygiene check', 'clean up', or /hk-slop-audit.