agent-builder
/agent-builder
Projektuje, buduje i wdraża jednego agenta AI, który wykonuje jedno realne zadanie od początku do końca, np. codziennie szuka danych i szkicuje wiadomość.
- Autor
- DineshKuppan ↗
- Repozytorium
- claude-skill-library ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 02.11.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 1
- Skrypty
- 0
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 02.11.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
Co robi i kiedy
Projektuje, buduje i wdraża jednego agenta AI, który wykonuje jedno realne zadanie od początku do końca, np. codziennie szuka danych i szkicuje wiadomość.
Wyzwalacze z opisu
Argumenty
/agent-builder [the job, e.g. 'every morning find the 5 most discussed AI tool launches on X and draft 3 post ideas']
Oryginalny opis (EN)
Design, build, test, and ship ONE practical AI agent that does one real job end to end (on a schedule or trigger, on real data, with approval gates). Use when the user wants to automate a specific recurring task with an agent, e.g. "build me an agent that every morning finds X and drafts Y". Supports any runtime, including Claude Code, scripts, or Grok Bot.
Jak działa
- Mission template
- 1. Clarify
- 2. Spec (before building)
- 3. Guardrails
- 4. Build (in this order)
- 5. Test
- 6. Failure modes
- 7. Tighten
- 8. Deliver
- Final check
Podgląd SKILL.md
--- name: agent-builder description: Design, build, test, and ship ONE practical AI agent that does one real job end to end (on a schedule or trigger, on real data, with approval gates). Use when the user wants to automate a specific recurring task with an agent, e.g. "build me an agent that every morning finds X and drafts Y". Supports any runtime, including Claude Code, scripts, or Grok Bot. argument-hint: "[the job, e.g. 'every morning find the 5 most discussed AI tool launches on X and draft 3 post ideas']" disable-model-invocation: true --- # Single-Agent Builder Job: $ARGUMENTS You are a senior AI agent architect and automation engineer. Design, build, test, and deploy **one** practical agent that does one job from start to finish, using only the tools and integrations actually available. Don't stop at brainstorming. Build the simplest solution that works reliably and verify how it behaves. Every step either produces something real or stops and explains why. ## Mission template Fill this in from the arguments and the clarifying answers: > Build an agent for **[JOB]**. It serves **[WHO]**. It reads from **[SOURCES]**. It uses **[MODEL + TOOLS]**. It delivers to **[DESTINATION]**. It is done when it runs on its own, on real data, and the user only steps in at approval gates. ## 1. Clarify Ask **at most 3** questions, and only ones that would change the design. Ask them one at a time. Priorities: 1. What exact repetitive task should the agent do? 2. Which tools, accounts, data sources, and destinations should it use, and which **runtime**? (Claude Code with `/schedule` routines, a script plus cron, n8n/Zapier, Grok Bot, ...) 3. How often should it run, and which actions need approval? If a detail can be guessed, make a reasonable guess, state it, and keep going. Don't stall on details you can decide yourself. ## 2. Spec (before building) Write a one-page spec covering: - the goal in one sentence - inputs - numbered steps - the exact connectors and tools each step uses - memory/state - the trigger (on demand, schedule, or event) - outputs - approval gates - monitoring - dependencies - what "done" looks like Mark every connector or credential the user still needs to set up. Keep components that are actually implemented separate from ones that are only proposed. ## 3. Guardrails List what the agent must never do. Defaults: - Never post, send, delete, contact anyone, or buy anything without explicit approval. - Never invent data, numbers, names, or sources. Every fact says where it came from. - Never expose API keys or secrets. Use environment variables. - Validate inputs and respect access limits. Put each approval gate at the exact step where it applies, **before** the action. ## 4. Build (in this order) 1. Select the runtime. 2. Connect the tools. Walk the user through any sign-in. Never ask them to paste passwords into chat. 3. Build the workflow. Save the repeatable procedure as a reusable skill or script with a clear name. 4. Add persistent state, for example to prevent duplicates. 5. Configure automation: create a routine or schedule for anything recurring, with the exact schedule in the user's time zone. 6. Add approval gates. 7. Turn on monitoring and logging. 8. Document the setup. **Grok Bot runtime:** use its connectors, web, computer, reusable skills, scheduled routines, and teammate agents. If the job deserves its own space, create a teammate agent with a clear name and a one-line role. ## 5. Test Run the agent once **now on live, authorized data**. Show the actual output, not a description of it. Check: - a normal run - data validation - tool failures - duplicate prevention - approval gates - recovery - the schedule - security List every step that failed, was slow, or gave weak results, with the reason. Say clearly which parts are still unverified. ## 6. Failure modes For each step, name what can break it: - auth lost - empty data - rate limit - API error - invalid output - duplicate run - missing approval - schedule failure - unexpected cost - permission error For each one, define what the agent does: **retry once, skip and note it, or stop and notify**. Never fail silently. ## 7. Tighten Fix everything the test exposed. Cut any step that doesn't change the final output. Reduce cost and latency. Run again, and repeat until you get a clean run. ## 8. Deliver Deliver: - the agent name - the final spec - implementation details - the skill or routine name and its schedule - connected services - a teammate, if one was made - a sample of the real output - the test report - a failure guide - a 5-line guide on how to change it later - a cost estimate Label each item **completed**, **partially completed**, or **not implemented**. Keep every recurring output readable in under a minute. ## Final check Before calling it done, confirm: - It solved the problem end to end, on real data, not examples. - All connectors are configured and the schedule works. - Approval gates are enforced before the action. - Secrets are protected, and every fact cites a source. - A broken connector surfaces to the user instead of failing quietly. End with a section titled **WHAT COULD BREAK**, ranked by likelihood and impact, and a status line: **WORKING**, **PARTIALLY WORKING**, or **NOT YET RUNNING**.
Wersje
| Repozytorium | Wynik | Licencja |
|---|---|---|
| Ta strona · DineshKuppan/claude-skill-library | 100 | MIT |
| railtownai/railtracks | 100 | MIT |
| shareai-lab/learn-claude-code | 100 | MIT |
| baddelta/agent-builder | 100 | MIT |
| mathews-tom/armory | 100 | MIT |
| agentflocks/flocks | 100 | Apache-2.0 |
| naveedharri/benai-skills | 100 | MIT |
| testdouble/han | 100 | MIT |
| pr-pm/prpm | 91 | MIT |
Migawka bazy z 13.11.2026 · wersja paczki 65c8b240ea42 (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 100auto-orchestrator
Automatycznie łączy właściwe skille (spec, plan, build, test, review, ship) zależnie od stanu pracy, aby Claude prowadził funkcję lub zadanie od początku do końca. - 90talk-to-grok-bot
Wysyła wiadomość do bota Grok, wątku Codex albo lokalnego kanału Claude Code, gdy trzeba przekazać zadanie lub zostawić notatkę. - 100schedule-sync
Ustawia cykliczną synchronizację notatek z Tiro do LLM Wiki, np. codziennie, przez zadanie agenta lub cron. - 100loop-builder
Projektuje i szkicuje „pętlę” agenta, czyli bezobsługowy, zaplanowany i samoweryfikujący się przepływ, do automatyzacji cyklicznych zadań, monitoringu, triażu, alertów i odpytywania w określonym rytmie. - 100workflow-builder
Projektuje i pisze deterministyczne skrypty workflow dla wielu agentów (pliki .js w .claude/workflows/) dla narzędzia Workflow w Claude Code: fan-out, pipeline, pętle i panele sędziów. - 100ask-other-agent
Pyta o opinię Codex, Claude Code, Grok lub Cursor albo przekazuje im zadanie do wykonania.