#harness-engineering
49 resources
Results
- browser-edge-cases
SOP for debugging browser automation failures on complex websites.
- vision-skills
Local vision CLIs: glance (describe/ask/OCR an image), ground (locate a target, pixel box), detect (element inventory), trace (image to SVG geometry),…
- hive.terminal-tools-foundations
Required reading whenever any shell_* tool is available.
- hive.terminal-tools-fs-search
Use terminal_rg / terminal_glob for all filesystem search — your project tree as well as system configs, /var/log, /etc, archive contents.
- hive.terminal-tools-job-control
Background jobs are how you do things that take time without blocking your conversation.
- mk:tech-graph
Generate publish-grade SVG+PNG technical diagrams — architecture, data flow, flowchart, sequence, agent-memory, class, ER, state-machine,…
- hive.browser-automation
Required before any hive-browser CLI command.
- hive.chart-creation-foundations
Required reading whenever any chart_* tool is available.
- hive.image-generation
Required before calling image_generate.
- hive.linkedin-automation
Read before automating LinkedIn with browser_* tools.
- hive.slack-notifications-setup
Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest,…
- hive.telegram-notifications-setup
Set up a Telegram notification channel (Sentinel) for a colony by driving the browser — create a bot via @BotFather in Telegram Web, store its token,…
- hive.terminal-tools-pty-sessions
PTY sessions are how you talk to interactive programs — programs that detect a terminal (isatty()) and behave differently when they don't see one.
- hive.terminal-tools-troubleshooting
Read when a terminal-tools call returned something surprising — empty stdout despite no error, exit_code is null, output_handle came back…
- hive.worker-delegation
Concrete patterns for breaking colony work into parallel worker jobs via run_playbook — when fan-out helps, how to model the goal as a…
- hive.writing-hive-skills
Author a new Agent Skill for a Hive agent that conforms to the Agent Skills specification (SKILL.md with YAML frontmatter, optional…
- hive.x-automation
Read before automating X / Twitter with browser_* tools.
- mk:confluence
Routing skill — recommends the correct mk:confluence-* leaf for any Confluence Cloud task.
- mk:cook
Orchestrates single-task implementation pipeline: plan → test → build → review.
- mk:docs-finder
Retrieve up-to-date library, framework, and project documentation using scripts + MCP tools (Context7, Context Hub) with intelligent fallback.
- mk:multimodal
Process images, video, audio, PDFs with Gemini API.
- mk:prompt-enhancer
Refine a draft user prompt using a 5-step framework — mode-select, decompose, detect, (scout if --deep), map, rewrite — grounded in 7 source docs <!-- research-citation --> (Anthropic / OpenAI Codex / FactoryAI prompting + Anthropic conte
- mk:sequential-thinking
Structured step-by-step reasoning with hypothesis generation, elimination, and revision capability.
- mk:web-to-markdown
Fetch a URL and return clean markdown.
- hive.colony-progress-tracker
Claim tasks, record step progress, and verify SOP gates in the colony SQLite queue.
- mk:qa-manual
Spec-driven manual QA testing and Playwright E2E code generation.
- dayu-harness
The publisher’s description is only a heading. Open the skill to read what it does.
- mk:agent-browser
Browser automation CLI for AI agents using agent-browser.
- hk-skill-creator
Create new skills, modify and improve existing skills, and measure skill performance.
- consulting-writing
Management-consulting writing craft — McKinsey SCR (Situation·Complication·Resolution), Minto Pyramid/MECE, BCG bold-bullet executive summary, so-what…
- encyclopedia-writing
Encyclopedic neutral-reference writing craft — NPOV (attribute facts not opinions, due weight, neutral faction labels, verdict restraint), summary style…
- guideline-writing
Guideline-authoring craft for instruction SoTs (.claude/ guides, CLAUDE.md, plan files) — operative rules vs recital, MUST/SHOULD/MAY force tiers,…
- journalism-writing
Journalism and argumentation writing craft — inverted pyramid, lede, nut graph, kicker, explainer framing, PAGE frames, Toulmin argument…
- scholarly-citation
Verifiable-attribution and citation-discipline craft — atomic claim decomposition, evidence grading (primary/analysis/forecast tiers), claimant…
- mk:angular
Angular v20+ patterns — 10 topics consolidated with progressive disclosure.
- mk:fix
Diagnoses and fixes bugs, type errors, lint failures, CI/CD issues, and runtime errors via root-cause-first investigation.
- mk:playwright-cli
Session-persistent browser automation via Playwright CLI — form filling, screenshots, data extraction, multi-step flows.
- mk:review
Multi-pass structural code review with adversarial analysis, scope-aware dispatch, adversarial persona passes, and forced-finding protocol.
- mk:ship
Ship workflow with explicit scopes: prepare stages and commits locally; release pushes and creates a PR; publish manages issues and versioning.
- mk:vue-testing-best-practices
Vue-specific test-design advisor + test-code reviewer.
- claude
OpenLoomi is an open-source AI coworker.
- mk:autobuild
mk:autobuild — Autonomous Multi-Hour Build Orchestration
- mk:bootstrap
End-to-end project orchestrator: research → design → plan → scaffold → implement → docs.
- mk:context-audit
Three concrete triggers: 1.
- mk:evaluate
Experimental behavioral evaluator.
- mk:figma
Read-first Figma gateway via Figma MCP: analyze designs, implement Figma-to-code for 1–3 screens, extract design tokens, produce a Figma…
- mk:investigate
Systematic debugging with root cause investigation.
- mk:jira
Routing skill — recommends the correct mk:jira-* leaf for any Jira task.
- mk:llms
Generate llms.txt files from project documentation following the llmstxt.org spec.
