cherrypicking-pr-to-v3
Backports (cherry-picks) a merged PR from main (v4) to the v3 branch of buildkite/agent, translating v4 code back to v3 conventions. Use when asked to…
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-09 00:13
25,952 results
Backports (cherry-picks) a merged PR from main (v4) to the v3 branch of buildkite/agent, translating v4 code back to v3 conventions. Use when asked to…
Prepare a release for buildkite-agent-metrics.
Read, cross-reference, or update construction records through connected MCP tools. Use for project-system capability discovery, RFIs, submittals, change…
Analyze Buildr financial forecasts through the Buildr MCP server. Use when the user asks for the account-wide revenue or profit forecast, a project's forecast…
Keep asking the user questions about a plan or design proposal until both sides reach consensus, resolving each branch of the decision tree one by one. Use when the user wants to stress-test a plan, wants the design to be interrogated, or mentions "grill me". Not for ordinary technical Q&A, code review, or directly implementing code changes.
Synchronously maintain the consistency of the "AI Capability Model" across multiple files. Triggered when an AI capability model needs to be added, modified, or deleted, ensuring changes are synchronized to all associated files.
n8n-to-skill is a workflow migration Skill developed by buluslan (WeChat Official Account: 新西楼.AI). It will rewrite any of your existing n8n workflows into a standalone, runnable Agent Skill with an equivalent goal—after conversion, n8n can retire with honor, the business goals are achieved exactly as before, the implementation is left to the Agent's native optimal solution, and there is no longer any dependence on the original workflow. More cross-border e-commerce AI…
Influencer/creator marketing command desk (Busabase App-in-Skill) — the agent sweeps and fit-scores creator candidates, drafts outreach and briefs, and gates…
Busabase-backed App-in-Skill CRM operator for contacts, companies, deals, and agent-drafted follow-ups in a reviewable follow-up queue. Use when the user…
Lightweight R&D desk that coding agents keep current — products, projects, tasks, a plain-language changelog, delivery acceptance and a weekly R&D report. Use…
Create, improve, and evaluate reusable agent skills. Use when the user wants to create a skill, revise its instructions or resources, measure its performance,…
Pursue a long-running goal in a single session by co-ordinating subagents.
Turn a loose idea into a sequenced map of investigation tickets, then drive them to resolution one at a time.
Cross-examines an irreversible plan with a fresh-context adversarial reviewer before the plan reaches the user. Use before presenting, asking approval for, or…
Agent Skill design knowledge base — mechanisms, philosophy, patterns, pitfalls. Use when: designing new skills, reviewing skill quality, or deciding whether…
Session handoff — compress current context into a structured prompt for seamless continuation in a new session. Use when: switching sessions, running low on…
Banini contrarian indicator analysis. Trigger timing: When the user requests tracking Banini, analyzing the contrarian indicator, fetching social media posts, and pushing to Telegram. Capability scope: Fetching Facebook posts via CLI, contrarian indicator logic analysis, chain effect derivation, Telegram push. Goal: Claude acts as the analysis engine, producing a straightforward Chinese contrarian indicator analysis report.
Parse the jsonl conversation record from a Claude Code Session and continue executing the task
Write or update a handoff document so that the next Agent with a fresh context can continue the work
Process interview records, including interview outline planning, question extraction and error correction, summarization, and knowledge graph storage
General file/object storage, such as for images, videos, files, documents and other bulk data. Perfect fit for image galleries, video galleries, and other file…
Place one consent-first CALL-E callback after a local safety gate has already blocked an extreme-risk developer action, so a known project owner can say stop…
Turn Google Form lead or callback responses into safe one-off AI-agent phone calls with template-driven goals, scheduled runs, and result writeback.
Use this project-local skill when the user asks Codex to start, spawn, launch, or use an agent/subagent to review current code changes, implementation, diff,…