ad-skill

Draft a new Claude Code or Codex skill at .claude/skills/<name>/SKILL.md (or .agents/skills/<name>/SKILL.md for Codex), using the Anthropic Skills format. Use when the user wants to create, write, draft, or scaffold a custom skill for an agentic coding tool. Asks one question per missing field; never invents skill names or triggers.

Jump to install

Repository: alexandremendoncaalvaro/agentic-development
Last source activity: August 11, 2026 at 19:16
Detected SKILL.md language: English
Stars: 1
Forks: 0

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

A direct command skips the review prompt. Inspect the source before running it.

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

The command stays on one line. Scroll horizontally to inspect it before copying.

Prefer a local copy? Download the files currently available to SkillsMP.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

File Explorer

2 files

SKILL.md

Source instructions · Read-only preview

Back to search Back to installation

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

View all from this repository

name	ad-skill
description	Draft a new Claude Code or Codex skill at .claude/skills/<name>/SKILL.md (or .agents/skills/<name>/SKILL.md for Codex), using the Anthropic Skills format. Use when the user wants to create, write, draft, or scaffold a custom skill for an agentic coding tool. Asks one question per missing field; never invents skill names or triggers.
summary	Draft a new Claude Code or Codex skill at the appropriate path.

<background_information> Drafts .claude/skills/<name>/SKILL.md (Claude Code) or .agents/skills/<name>/SKILL.md plus agents/openai.yaml (Codex). Spec: code.claude.com/docs/en/skills. Open standard: agentskills.io. Examples: github.com/anthropics/skills. </background_information>

Step 1 — confirm target. Ask the user: - Name — kebab-case, lowercase, ≤64 chars. Becomes the directory name and the slash command. - Target agent(s) — Claude Code, Codex, or both. Determines path and frontmatter shape. - Personal or project — `~/.claude/skills//` (personal) vs `.claude/skills//` (project, committed). Default: project.

Step 2 — interview to fill. Ask one question per missing field, in this order:

What it does — one sentence, primary triggering signal.
When to invoke — common task framings the user would say. Combined description + when_to_use is capped at 1,536 chars per the Anthropic spec.
Tools needed — Read, Write, Glob, Grep, Bash, Task, ... Restrict to what the skill actually uses.
Body shape — instructions, optional template, output contract. Keep ≤500 lines; move long material to sibling files (reference.md, examples.md, scripts/).

Do NOT invent values. When the user does not know something, ask. Do NOT invent fields not in the spec — only declare frontmatter fields that actually apply.

Step 3 — write the file(s).

Path:

Claude Code project: .claude/skills/<name>/SKILL.md
Claude Code personal: ~/.claude/skills/<name>/SKILL.md
Codex project: .agents/skills/<name>/SKILL.md plus .agents/skills/<name>/agents/openai.yaml (cc-sdd convention).

Frontmatter per agent:

Claude Code: name, description, allowed-tools (and any other field from the spec the user asked for).
Codex: minimal frontmatter — name, description. Body uses XML tags (<background_information>, <instructions>, <template>, <output_contract>). The agents/openai.yaml carries interface.display_name, interface.short_description, policy.allow_implicit_invocation.

Body: imperative instructions ("do X", not "this skill does X"). Every line is recurring token cost once the skill loads — be terse. Don't restate AGENTS.md.

Step 4 — stop after writing. Do not invoke the new skill, do not pre-fill it with example content, do not test it. The user will exercise it themselves.

<output_contract> A single new SKILL.md at the chosen path (plus agents/openai.yaml for Codex). Frontmatter declares only the fields actually used. Body is imperative and terse. No external file dependencies the user did not ask for. </output_contract>

Test the new skill's description triggers by invoking it from a real conversation — verify auto-triggering on the keywords you chose.
Kit skills ship to every install. Add the source for both hosts and its parity tests; propose an ADR + Task when the capability changes the kit's public surface or behavior.
If the skill carries a sibling subagent, declare it in manifest.json and add the source under agents/.

ad-skill

Install options

Review the source files

Next

Next

ad-skill

Source facts

Install options

Review the source files

More from this repository

Next

Next

More from this repository