ad-update

Preview and safely update the machine-global Agentic Development kit. Use when the user asks to update agentic, refresh installed skills, get the latest kit, sync the engineering skills, inspect kit drift, or invokes `/ad-update`. Project scope is explicit; preserves local edits unless the user explicitly requests force.

Ir para a instalação

Repositório: alexandremendoncaalvaro/agentic-development
Última atividade na origem: 14 de agosto de 2026 às 16:55
Idioma detectado do SKILL.md: inglês
Estrelas: 1
Forks: 0

Opções de instalação

Por padrão, está selecionado o prompt que primeiro revisa a origem. Você pode mudar para um comando direto ou baixar uma cópia local.

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Um comando direto ignora o prompt de revisão. Verifique a origem antes de executá-lo.

npx skills add https://github.com/alexandremendoncaalvaro/agentic-development --skill ad-update

O comando permanece em uma só linha. Role horizontalmente para revisá-lo antes de copiar.

Prefere uma cópia local? Baixe os arquivos disponíveis atualmente no SkillsMP.

Revise os arquivos de origem

Leia o SKILL.md e os arquivos complementares exibidos pelo SkillsMP antes de decidir se vai instalar.

Explorador de arquivos

2 arquivos

SKILL.md

Instruções da origem · Visualização somente leitura

Voltar à pesquisa Voltar à instalação

ad-ground

Four-source pre-implementation research — official docs, validated implementation references (open-source repos, Stack Overflow / forum answers, blog posts, gists), in-repo patterns, and git history — then synthesize a happy path, persist its claim-to-source evidence as an auditable project record, and gate any deviation before code is written. Grades evidence and confidence per WORKFLOW §17; routes insufficient evidence to ad-spike. Auto-invokes on non-trivial work, refactors, library or pattern selection, "research before coding", "before implementing", "which library", "which pattern", "how to approach", "ground before coding". Workflow-operational counterpart to WORKFLOW.md §4 + §5.

2026-08-17

ad-philosophy

Universal agent behavior and documentation discipline — think before coding, decide when grounded (only ask on judgment calls), ground in real patterns, prefer simplicity, make surgical changes, define verifiable goals, verify before claiming done, report for a decision-maker (conclusion first, self-contained, translate-not-dump), and write documentation that captures only definitions and decisions. Auto-invokes on non-trivial changes, refactors, debugging, "think before coding", "ground before coding", "verify done", "decide when grounded", "employee not co-pilot", "report for a decision-maker", "before implementing", on documentation work — "writing docs", "writing readme", "writing architecture", "writing adr", "writing task", "audit docs" — or whenever the task is ambiguous enough that guardrails matter.

2026-08-17

ad-research

Research-to-conclusion methodology (WORKFLOW §17 + §4-5) — turn an open question ("should we adopt X?", "is approach A better than B?", "what is the state of the art on Y?") into an evidence-graded study at doc/research/NNNN-<slug>.md whose output is a defensible conclusion, not code. Runs the Evidence-Based loop (Ask, Acquire, Appraise, Apply, Assess) plus the scientific method (falsifiable hypothesis, experiment) when the question is measurable; reuses ad-ground's four-source pass for Acquire, grades each claim's evidence strength and the confidence to proceed (WORKFLOW §17), and graduates a binding conclusion into an ADR. Triggers on "research", "study", "investigate", "reach a conclusion", "should we adopt", "A vs B", "state of the art", "evaluate options", "literature review", "evidence for", "/ad-research". Distinct from ad-ground (records the path for an already-decided implementation) and ad-spike (validates one uncertain technique); routes to ad-spike when evidence is insufficient and to ad-adr when

2026-08-17

Ver todas deste repositório

name	ad-update
description	Preview and safely update the machine-global Agentic Development kit. Use when the user asks to update agentic, refresh installed skills, get the latest kit, sync the engineering skills, inspect kit drift, or invokes `/ad-update`. Project scope is explicit; preserves local edits unless the user explicitly requests force.
summary	Preview and safely apply the current machine-global Agentic Development kit update, preserving local skill edits by default.

<background_information> Update the machine-global Agentic Development materialization. This is the session-native entry point for the CLI; it does not update a globally installed executable or make unrelated repository changes. A repository-local materialization is a deliberate --scope project exception. </background_information>

Step 1 — preview. From any directory, run:

npx --yes @alexandrealvaro/agentic@latest update --dry-run --yes

Report the plan before describing an outcome. Explain ! lines as preserved or skipped files and - lines as verified retired-skill migration removals. A dry-run that shows no material changes is a valid result.

Step 2 — apply only when requested. If the user explicitly asks to update, refresh, sync, or apply the kit, run:

npx --yes @alexandrealvaro/agentic@latest update --yes

If the request is only to inspect, explain, or preview, stop after Step 1. Pass --agent claude-code or --agent codex only when the user scopes the host. Do not add --force unless the user explicitly chooses to replace a locally edited file after seeing the plan. For a deliberate project materialization, run the same command from that repository root with --scope project; only that mode supports the root-document safeguards.

Step 3 — migrate a legacy project only when the user asks to clean prior project copies. First preview from that repository root:

npx --yes @alexandrealvaro/agentic@latest update --scope project --migrate-legacy --dry-run --yes

Then apply the reviewed plan without --dry-run. The migration removes state-recorded pristine skills, exact historical copies of WORKFLOW.md / WORKFLOW-FLOWS.md, and the bounded generated skills section in AGENTS.md or CLAUDE.md. It preserves changed skills and unknown workflow files; use --force only after the user explicitly chooses to remove a changed skill.

Step 4 — verify and report. Report the command's concrete result: created, updated, preserved, skipped, and migrated files. State whether the global kit was changed; never call it "latest" merely because the command ran. If a local edit was preserved, name the path and offer the user's actual choices: keep it, reconcile it manually, or re-run with explicit --force.

The CLI's state-aware comparison and named migrations are authoritative. Do not delete skill directories manually to make an update appear clean; use the explicit legacy migration when the user wants to remove a former project installation.

<output_contract> Report the dry-run plan first. Apply only when the request authorizes an update, then report exact changed, preserved, skipped, and migrated paths plus any next decision. Do not claim an npm distribution tag without verifying it separately. </output_contract>

ad-update

Informações da origem

Opções de instalação

Revise os arquivos de origem

Mais deste repositório

Mais deste repositório