Enable parallel agent execution for multi-domain features with git worktree isolation
Analisa um projeto de forma read-only e gera um README_GENERATED.md de alta qualidade.
Automatically analyze and tag untagged [Gorgias](https://composio.dev/toolkits/gorgias) tickets based on content.
Scan the System Backlog for stale items, enforce lifecycle timeouts, auto-archive completed items, and produce a hygiene report. Use as a scheduled maintenance task or on demand.
Auto-classify a new or existing System Backlog item as NOVEL, DUPLICATE, OVERLAP, or DEFERRED. Use when a new idea is added to the backlog or when the user asks to triage an…
Autonomously work multiple Project #9 board items in one bounded loop. Each tick dispatches a worktree-isolated sub-agent to implement ONE item and open a PR, autonomously…
Plan implementation by breaking work into one epic GitHub issue + child sub-issues. Use when: (1) User says '/big-plan', (2) User wants to plan an implementation before coding,…
Use when managing worktree lifecycle. Triggers on "/bonsai", "worktree opruimen", "ik ben hier klaar", "nieuwe worktree", "nieuwe branch", "prune".
Scaffolds a GitHub Actions workflow — a YAML file under `.github/workflows/` — with top-level least-priv `permissions:`, SHA-pinned `uses:`, per-job `timeout-minutes`,…
Scaffold a root-level RESOLVER.md — a dual routing table (filing for writes, context for reads) plus an AGENTS.md pointer and a trigger-eval sidecar at `.resolver/evals.yml`.
Build the Observable Framework dashboard for a code-diligence target's warehouse, honoring the privacy gate on the working-pattern card.
Watch a PR through CI and review feedback. Auto-fix high-confidence failures and address review comments. Use when the user says 'babysit
' or 'respond to PR comments'.
Use when the user wants to "audit a help skill", "review my plugin index", or "verify my help-skill is up to date".
Audit a root-level resolver — verify AGENTS.md pointer, managed-region integrity, filing-table coverage against disk, context-table actionability, and trigger-eval pass rate.
**DEFAULT for ROUTING AMBIGUITY — interactive picker that surfaces top skill candidates + 2 LLM-rewritten prompt variants via AskUserQuestion with previews, then dispatches the…
Recommends the right UI pattern from Tidwell's "Designing Interfaces" catalog for a given interaction problem — navigation, layout, lists/data, forms, controls, mobile.
Monitor Claude Code releases and auto-generate GitHub issues for each new version
Manage Claude Code sessions — search by topic or ID, resume crashed sessions, spawn interactive or headless sessions, monitor live sessions, auto-summarize, and bootstrap new…
Iterative review-fix loop: reviews code, auto-fixes issues, repeats until clean or stuck. Finishes with reorganize (for large changes), simplify + test consolidation.
This skill should be used when capturing solved problems as categorized documentation with YAML frontmatter for fast lookup.
AUTO-TRIGGER: Apply this skill when the user is preparing to present findings, recommendations, or results to a consulting client.
Credit Maximizer v8.4.0 — 5D router (model×effort×version×context×dispatch) + auto-dispatch to specialized agents/skills + cross-provider session bridge.
Use after craft-review in the craft pipeline. Applies auto-fixes from review findings, batches remaining findings for human triage, and re-runs a narrow review on fix deltas when…
This skill creates a Dapr workflow application with .NET Aspire. Use this skill when the user asks to "create a workflow with Aspire", "write an Aspire workflow application" or…
Create a workflow command that orchestrates multi-step execution through sub-agents with file-based task prompts
Operating philosophy for autonomous memex curator tending — orientation protocol, signal triage, bounded work units, initiative thresholds, logging conventions.
Autonomously close out a phase — tag, push, open a PR with auto-merge enabled. Invoked by /autopilot at phase completion; rarely invoked by humans directly.
Auto-invoke when the user wants to transfer saved dataset state to a remote, publish a dataset, upload annexed content to a sibling, share changes with collaborators, or push to…
Register a defect (BUG-NNN) and auto-generate the fix TASK so the bug enters the normal implement/review flow.
[UDS] Guide for mapping software development phases to UDS commands and features
Enriches dbt source and model YAML descriptions for AI-driven query generation. Profiles BigQuery tables for schema metadata, sparse_ratio, and enum values so documentation uses…
Import one or more Google Drive folders as private repos into the local Forgejo dev-hub. Wraps the kei-drive-import bash wizard.
Review a PR — analyze code, present findings, optionally post comments and patches to ADO. Also supports standalone posting of saved findings (for automation pipelines).
Auto-review skill for expert agents. After coding, expert applies elicitation techniques to self-correct before sniper validation. Inspired by BMAD-METHOD.
Use when the user asks to "design a welcome flow", "set up an abandoned-cart sequence", "build a light re-engagement branch inside a lifecycle flow", or "plan a cold-outbound…
Analyze TRD complexity and auto-configure team roles, agent assignments, and marketplace plugins (Codex skill for /ensemble:configure-team)
ONLY when user explicitly types /exe-plan. Never auto-trigger on execute, run, or implement.
Background-dispatch variant of execute-phase. Spawns one `claude --bg --agent maxv-executor` session per plan (with auto-worktree) instead of running waves of in-process Agent…
This skill should be used when the user wants expert reviews on a document, plan, or deliverable. Trigger on "expert-review", "전문가 리뷰", "리뷰 부탁", "expert review", "페르소나 리뷰", "전문가…
Extract recurring failure patterns from breezing orchestration logs and Judgment Ledger, emit failure-rule.v1 proposals with confidence scores.
Auto-tag tests that flaked >N times in M runs, move them to a quarantine suite, and cap how long they stay there
Use when the user wants to manually flush a deferred-commit queue from a prior or interrupted chain. Reads .hyperflow/commits-queue/manifest.json, fast-forwards the staging branch…
Full Self Driving — autonomous release loop that processes all auto-dev-eligible GitHub issues until none remain, by repeatedly running /pipeline auto-dev then /homework.
Fully automated end-to-end demo of the team-tile bootstrap pattern — zero user args, runs all 12 steps front-to-back, auto-cleans up at the end.
One-gesture external-document ingestion into the Brain knowledge layer. Fetches a URL, local file, or stdin paste, auto-infers slug and tags, writes provenance-stamped markdown…
Context-sensitive help with project-state-aware routing (greenfield / brownfield / post-update / healthy).
Analyze and fix failing PR checks. Use when the user asks to fix the PR, resolve failing CI checks, diagnose red GitHub Actions runs, auto-fix lint/type/test failures on a pull…
Triage open GitHub issues and PRs in one sweep. Scans the codebase and merged PRs for evidence of issue completion, evaluates PR CI state, merge readiness, and review decision,…
Git 통합 워크플로우 허브 — autopilot, collab (팀 온보딩), conflict (충돌 해결), guide (초보자 가이드), safe (안전망), strategy (브랜치 전략), sync (동기화), workflow (커밋·브랜치·PR), worktree (병렬 브랜치) 9개 서브툴을 통합.
Audit GitHub repo health, auto-fix safe issues, run quality gates, deploy, and record decisions across runs.
Apply Agile linkage controls in GitHub using issue types, sub-issues, dependencies, issue-branch/PR linkage, project fields, and built-in automations.
Use when: activating LLM coding behavioral rules, ensuring code stays minimal/surgical/verified, preventing over-engineering.
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…
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…
AUTO-TRIGGER: Apply this skill when the user is working with intent data signals from ZoomInfo, Bombora, G2, 6sense, Demandbase, or any similar platform, and needs to…
Create GitHub Actions auto-deploy workflow for a Kaggle notebook directory. Use when wiring up a new or existing notebook directory to automated Kaggle kernel push on git push.
Audit / curate KB-vault hygiene — surfaces mechanical drift (broken [[wikilinks]], dangling §-pointers, status-enum violations, status-drift, index-row bloat) the librarian's…
Retrieve claudit knowledge cache domains (ecosystem, core-config, optimization). Checks freshness and auto-refreshes stale domains.
Create a draft pull request targeting develop. Auto-generates PR body from design files, GitHub issues, and/or commit history. Use when opening a PR.
Link the current Claude Code session to a ticket (Linear, Jira, GitHub Issues, or GitHub Pull Requests) and cache its title/status in karma.