Review and resolve PR comments from GitHub. Validates each comment, fixes legitimate issues.
Apply Agile linkage controls in GitHub using issue types, sub-issues, dependencies, issue-branch/PR linkage, project fields, and built-in automations.
Govern release readiness and incident response flow in GitHub with rollback evidence, hotfix linkage, and follow-up controls.
Extract and score leads from GitHub repositories by analyzing stars, forks, issues, PRs, comments, and contributions.
Enforce review and merge administration gates with required checks, approvals, conversation resolution, rulesets, and merge queue readiness.
Naming conventions and phase protocol for GitHub ticket lifecycle. Baton workflow in manager-ticket-lifecycle.
Initialize a repository so global skills are always loaded first through repository instructions, local hooks, and governance presence checks.
Classify tasks into free, fleet, or premium lanes and persist an escalation rationale for the active session.
Iterate on content until it passes eval — driven by CTO conversion, not score-chasing
Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR.
Draft a single net-new *good first issue* on the configured `` repo from one supplied candidate such as a known gap or a small maintainer-named task.
Build a Google Ads Performance Max campaign — asset groups, audience signals, and asset specs ready for production.
Build a Google Ads Search campaign — ad group structure, responsive search ads, and bid strategy.
Versão lite da skill mapear-nicho da Accelera 360. Mapeia ICP, dores, mecanismo proprietário, oferta, GTM, eventos gatilho e linguagem do nicho preenchendo nichos/{slug}/ com 9…
Pesquisa de mercado para escolha de nicho. Modo A — Top 10 nichos pra montar empresa de IA agora (com score 1-10 em 4 critérios).
ALWAYS invoke when the user wants to install or update the governance policy in CLAUDE.md. Triggers:"gov init","install governance policy","set up governance".
Design GPU orchestration on EKS using Karpenter v1.2+ NodePools, KEDA scale-to-zero, and DRA 1.35 GA for multi-instance GPU (MIG) partitioning.
Optimize Gradle build speed with Configuration Cache, parallel execution, and AGP 9 tuning
Recreate grainient.supply's 16 dark-mode visual effects as single-file HTML pages: WebGL shader gradients, vignette overlays, 9-layer box shadows, smooth scroll, spring…
Compile Graphviz diagrams (.dot files) to SVG in-place. Use when working with .dot files or markdown with Graphviz code blocks, or when user says "compile diagrams", "generate SVG…
Vernile the Great - Opus excellence. The envy of the agent world. Human devs are in awe.
Creates new email templates for Greenhouse EO. Handles React Email components, template registration, type updates, preview metadata, and delivery integration.
Review, prune, and suggest notes in notes.toml. Cleans stale notes and proposes new ones from recent changes.
Anchor claims to evidence from authoritative sources. Use when validating assertions, establishing provenance, verifying facts, or ensuring claims are supported by evidence.
Use when grounding exactly ONE target assertion against library evidence — retrieves via MCP tools, widens context as needed, synthesizes across all retrieved evidence with…
Use when assigning backlog items to a GitHub milestone. Args: {milestone-number} [P0|P1|P2|title-filter].
Query and interpret the new Google Search Console AI Performance Report (AI Overviews + AI Mode impressions/pages/countries/devices/dates).
Analyze codebase with parallel mapper agents to produce structured documentation
Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR.
Code review a PR using great-tables-specific standards. Use when reviewing pull requests on this repo.
Create or audit a GTM container with the core baseline configured ready for ongoing tag management.
Create or audit GTM tags, triggers, and variables for a specific tracking need with ready-to-publish config.
Interactive guide and tutorial for brewcode plugin suite. Teaches all features step-by-step with progress tracking.
Use when: activating LLM coding behavioral rules, ensuring code stays minimal/surgical/verified, preventing over-engineering.
Schedule meetings between people using the `gws` CLI (Google Calendar). Use when the user wants to find a meeting time, schedule a meeting, check availability, or book time with…
Use when the user mentions habits, saved prompts, reusable workflows, repeated commands, or their prompt inventory. Triggers on: browsing, searching, listing, or selecting habits.
Stack new habits onto existing routines using cue/reward design, accountability tricks, and an 8-week ramp. Outputs a stack diagram, tracker spec, and failure-mode plan.
Coverage / readability scanner of the haipipe-insight family. Reads the project's probes/ and existing insights/ folders; reports which probes are CONFIRMED and ready for…
individual-query task-folder build specialist. Scaffolds {NN}_/ task-folders under E-series task-groups that query / visualize ONE individual's data (CGM trace, meal…
Citation-grounding verifier — for each claim in an LLM response, confirm support in the retrieved context, report ungrounded claims
This command should be used to run the Kimchi self-improvement system. Observes execution outcomes, proposes incremental improvements to skills/validators/personas, validates…
Load the most recent save-to-md session log into a fresh session and brief the new agent on where the prior session left off.
Workflow for picking up and implementing GitHub issues in this repo. Use when the user asks to work on an issue, pick up a ticket, implement a feature from GitHub, or start work…
Generate Connect-RPC handler implementations backed by sqlc stores. Use when the user wants to scaffold or implement CRUD handlers for their proto services.
Reflect on the improvement loop itself. Examine the trail, surface recurring findings, blind spots, methodology effectiveness, and what the loop has been ignoring.
Use when `/harness-auto-setup` is invoked to bootstrap and configure a project-shaped harness, expand an existing harness without refreshing its foundation, or migrate an existing…
Runs interactive brainstorming to capture intent and produce a design spec, then hands off to harness-plan to generate Plans.md.
하네스(Harness) 통합 관리 스킬 - 에이전트/지식/엔진 워크플로우의 생성, 사용, 평가를 하나로 통합. 이 스킬은 자동 트리거하지 않는다. 반드시 /harness-kakashi-creator 명령으로만 활성화할 것.
싱글 에이전트 하네스 루프. 간단한 작업이나 단일 Stage 작업 시 사용. 멀티에이전트 조율이 필요한 경우 /orchestrate를 대신 사용할 것. Use for simple single-stage work. For multi-stage or parallel work, use /orchestrate instead.
Iterates a fresh ralph-worker subagent per attempt in a persistent worktree until
tag and verify command both confirm success.
Manages version bumps, CHANGELOG, git tags, and GitHub Releases. Use when cutting a release or updating version metadata.
Manages SSOT memory — decisions.md, patterns.md, and cross-session learnings. Use when recording decisions, searching memory, or promoting learnings.
Runs Plans.md tasks in a long-running autonomous loop with ScheduleWakeup, sprint contracts, and plateau detection. Use when running tasks overnight or on a scheduled cadence.
HAR: Project init, tool setup, agent config, memory setup, skill mirror sync. Trigger: setup, init, new project, CI/Codex setup, harness-mem, mirror.
Harnessダッシュボードを表示。現状を一目で把握できる司令塔。Use when user mentions '/harness-ui', dashboard, monitoring, or UI display.
Executes Plans.md tasks — solo, parallel, or breezing team mode. Use when implementing tasks or running the work loop.
Hash-anchored line edits — refuse the edit if the target line content changed since the read
Unified health conversation entry point - automatically loads all health data for each conversation, supports natural language queries, and intelligently routes to appropriate…
Pair Claude and Codex as collaborating peer agents inside herdr. Use whenever the user invokes /herdr-pair, asks to "pair", "team up", "collaborate with codex", "collaborate with…
Rédiger et poster un message BBCode sur le topic Redface 2 de forum.hardware.fr (cat=23, post=35395) en respectant les règles BBCode HFR et l'attribution IA.