Agent skill

Ad Bootstrap

by CorridorTech in CorridorTech/PoseCap

Generate AGENTS.md at the repo root by scanning the codebase first, pre-filling placeholders from observed signals, and asking only the genuine gaps.

Apache-2.0Auto-check: warningsAgent Workflows

Install Ad Bootstrap

The automated check flagged lines worth reading first. See the safety section below.

skills CLI
$ npx skills add CorridorTech/PoseCap --skill ad-bootstrap -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install CorridorTech/PoseCap ad-bootstrap --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/CorridorTech/PoseCap.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/ad-bootstrap .claude/skills/ad-bootstrap && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ad-bootstrap
GitHub stars
224
Token cost
~2.4k tokens
SKILL.md length
702 words
Files
1
Skills in repo
15
Repo updated
First seen
Licence
Apache-2.0

At a glance

Generate AGENTS.md at the repo root by scanning the codebase first, pre-filling placeholders from observed signals, and asking only the genuine gaps.

  • Works in 5 steps: Detect mode → Scan (brownfield only) → Pre-fill → …
  • The user wants to bootstrap
  • SKILL.md covers Step 0 — Detect mode, Step 1 — Scan (brownfield only), Step 2 — Pre-fill and Step 3 — Show only the gaps, plus 4 more sections
  • Calls git and node

What it does

Ad Bootstrap is an agent skill from CorridorTech/PoseCap. Generate AGENTS.md at the repo root by scanning the codebase first, pre-filling placeholders from observed signals, and asking only the genuine gaps. Use whenever the user wants to bootstrap, scaffold, generate, create, set up, or audit AGENTS.md / agents.md / CLAUDE.md (the operational guide for agents working on this project). Covers greenfield (empty repo), brownfield (code exists, no AGENTS.md), and audit (drift report against existing AGENTS.md).

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Agent instruction files. The licence is Apache-2.0.

When your agent uses it

  • The user wants to bootstrap
  • Audit AGENTS.md / agents.md / CLAUDE.md (the operational guide for agents working on this project)

Example prompts

  • “/ad-bootstrap”

Requirements

  • Pre-approved tools (allowed-tools): Read, Write, Glob, Grep, Bash

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Detect mode
  2. Scan (brownfield only)
  3. Pre-fill
  4. Show only the gaps
  5. Write the file

What it can do on your machine

Read from SKILL.md and the folder at commit 626701b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Glob
    • Grep
    • Bash

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git
    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ad Bootstrap loads about 2.4k tokens when it runs. Until then it costs about 117 tokens; SKILL.md has 702 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~117
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: warnings

The automated check found patterns that need a careful read before installing.

  • NoteMentions a .env fileSKILL.md:17
    ignore`, `.gitattributes`, `.DS_Store`, `.env*`, `.idea`, `.vscode`, `LICENSE*`, `README.md`) → **greenfield** mode. The
  • WarningMentions a credentials file (SSH keys, cloud or package-manager tokens)SKILL.md:178
    * `<files-not-to-read line — .env, .npmrc, etc>`
  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Write, Glob, Grep, Bash

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from CorridorTech/PoseCap at commit 626701b, republished under its Apache-2.0 licence (© CorridorTech). 702 words, ~2,367 tokens.

Download SKILL.mdSave it as .claude/skills/ad-bootstrap/SKILL.md (or your agent's skills folder).
name
ad-bootstrap
description
Generate AGENTS.md at the repo root by scanning the codebase first, pre-filling placeholders from observed signals, and asking only the genuine gaps. Use whenever the user wants to bootstrap, scaffold, generate, create, set up, or audit AGENTS.md / agents.md / CLAUDE.md (the operational guide for agents working on this project). Covers greenfield (empty repo), brownfield (code exists, no AGENTS.md), and audit (drift report against existing AGENTS.md).
allowed-tools
Read, Write, Glob, Grep, Bash
summary
Generate or audit `AGENTS.md` at the repo root.

/ad-bootstrap

Produces AGENTS.md at the repo root, ≤150 lines, every line operational. Generic agent behavior (think-before-coding, verify-before-claiming-done, etc.) does not belong here — that lives in the ad-philosophy skill.

Step 0 — Detect mode

Inspect the repo:

  • AGENTS.md exists at the repo root → audit mode. Do not rewrite it. Stop after producing a drift list (see Step 4).
  • AGENTS.md absent and the directory only holds trivial entries (.git, node_modules, .gitignore, .gitattributes, .DS_Store, .env*, .idea, .vscode, LICENSE*, README.md) → greenfield mode. There is nothing to scan; walk the template's <placeholders> with the user one at a time and skip Step 1.
  • AGENTS.md absent and meaningful code is present → brownfield mode. Scan first, pre-fill, ask only the gaps.

Step 1 — Scan (brownfield only)

Read in this order, taking the first that exists for each category:

  • Manifests: package.json, pyproject.toml, Cargo.toml, go.mod, Gemfile, composer.json, pubspec.yaml.
  • README.md, plus any doc/ or docs/ directory.
  • Top-level directory listing.
  • doc/adr/ — binding decisions; read every ADR.
  • GUIDELINES.md at repo root — if present, the AGENTS.md sections that have a corresponding GUIDELINES.md section (Code Style → §2; Quality Gates → §8; Commit & PR → §10; Security & Privacy → §12) emit as pointer stubs instead of inline rules' ' reciprocity and ADR-0030 §1.
  • .claude/, .cursor/, .openai/, .agents/ — existing agent config.
  • Hook configs: .husky/, .pre-commit-config.yaml, .github/workflows/, .gitlab-ci.yml, .circleci/.
  • Lockfiles: package-lock.json, yarn.lock, pnpm-lock.yaml, poetry.lock, Cargo.lock.
  • git remote -v for the repo URL.

Build a model of: stack (languages and versions), entry points, build / test / lint commands, conventions, quality gates, security boundaries, gotchas confirmed by code.

Step 2 — Pre-fill

For every <placeholder> in the template below, fill from observed signals. No fabrication. If a section has no signal, write <TODO: not yet wired> in one line and move on. Do not write meta-prose explaining the gap.

Step 3 — Show only the gaps

Print to the user:

  • (a) placeholders that could not be filled from repo signals;
  • (b) signals that conflict (two test commands, two style configs, README contradicts code, etc.).

One question per gap. Skip everything filled confidently. Do not ask philosophical questions ("is this doc for agents or humans?", "what is the most important quality bar?") — those are decisions, not interview material.

When the host exposes Plan Mode, the agent may render the proposed AGENTS.md body inside the plan (the user reviews and approves before write) instead of writing-then-presenting. Plan Mode is opt-in — skip for incremental edits where the user already saw the prior content.

Show full SKILL.md (309 more words)Show less

Step 4 — Write the file

On user confirmation, write AGENTS.md at the repo root. Cut every line that does not change agent behavior. No "External Resources" section (URLs are derivable from git remote and the manifest). No appended Universal Agent Behavior block. No marketing prose.

Audit mode override: do not write the file. Produce a drift list. Format each line as:

[file or section]: spec says X, code says Y. Suggested resolution: change spec / change code / discuss.

If something the user says contradicts what the code shows, surface the conflict. Don't silently trust the user; don't silently trust the code.

Template — AGENTS.md

markdown
# AGENTS.md

## Project Overview

`<one sentence: what it does, who runs it, the constraint a wrong change would violate>`

**Stack:** `<languages + versions, runtimes, frameworks, database>`
**Entry points:** `<main services and where to find them>`

## Setup, Build, Test

```bash
# Install
<command>

# Build
<command>

# Test (single file preferred over full suite)
<single test command>
<full suite command>

# Run before any commit
<lint>
<format>
<typecheck>
```

Document non-obvious flags or env vars inline.

## Quality Gates

<when-no-guidelines>
Deterministic enforcement — agent cannot skip.

* Pre-commit hook (fast): `<lint, format, secret-scan>`
* Pre-push hook (thorough): `<build + unit + integration>`
* Visual/E2E for UI (if applicable): `<e.g., Cypress, Playwright, Claude in Chrome — leave blank for non-UI projects>`
* Hook config lives in: `<.husky/, .pre-commit-config.yaml, .claude/settings.json — see code.claude.com/docs/en/hooks>`
* CI blocks on: `<list>`
</when-no-guidelines>

<when-guidelines-md-exists>
See [`GUIDELINES.md`](GUIDELINES.md) §8 for the full reference. Non-negotiable subset:

* `<distilled pre-push hook line>`
* `<distilled pre-commit hook line — or "intentionally absent" if not wired>`
* Never bypass: no `--no-verify`, no skipped hooks, no deleted failing tests.
</when-guidelines-md-exists>

## Code Style

<when-no-guidelines>
Only what differs from language defaults.

* `<e.g., ES modules, not CommonJS>`
* `<e.g., destructure imports>`
* `<e.g., no `any` outside `internal/types/`>`
* `<e.g., Pydantic for all request/response shapes>`
</when-no-guidelines>

<when-guidelines-md-exists>
See [`GUIDELINES.md`](GUIDELINES.md) §2 for the full reference. Non-negotiable subset:

* `<language-specific naming convention line>`
* `<error-handling pattern line>`
* `<module-surface line — ESM vs CommonJS, named-vs-default exports, etc.>`
</when-guidelines-md-exists>

## Architectural Principles

Binding decisions live in [`doc/adr/`](doc/adr/). Do not reinvent.

## Repository Layout

`<where logic, tests, docs, infra live — only if not obvious from the tree>`
`<.claude/skills/ — list of available skills, if any>`
`<.claude/agents/ — list of custom subagents, if any>`
`<doc/adr/ — list of binding ADRs, if any>`
`<doc/tasks/ — task tracking convention, if used>`

## Commit & PR Conventions

<when-no-guidelines>
* Commits: `<conventional / project-specific>`
* Branches: `<feat/, fix/, chore/>`
* PRs require: `<green CI, one review, linked issue>`
* Never push to `<main>` directly.
</when-no-guidelines>

<when-guidelines-md-exists>
See [`GUIDELINES.md`](GUIDELINES.md) §10 for the full reference. Non-negotiable subset:

* `<commit-format line — Conventional Commits + DCO sign-off>`
* `<branch-strategy line — main / feature-branch policy>`
* Never push to `<main>` directly.
</when-guidelines-md-exists>

## Security & Privacy

<when-no-guidelines>
* Secrets: `<location — never committed>`
* Files the agent must not read or modify: `<list>`
* Data classification: `<e.g., no PII in logs>`
* Pre-approved commands (no prompt): `<e.g., gh, npm test, npm run lint>`
* MCP servers approved: `<list>`
</when-no-guidelines>

<when-guidelines-md-exists>
See [`GUIDELINES.md`](GUIDELINES.md) §12 for the full reference. Non-negotiable subset:

* `<secret-handling line — env files gitignored>`
* `<files-not-to-read line — .env, .npmrc, etc>`
* `<pre-approved commands line — agent-allowed no-prompt list>`
</when-guidelines-md-exists>

## Gotchas

Real traps. Each one should map to an incident or to specific code.

* `<e.g., migrations not idempotent — never edit, always create new>`
* `<e.g., DB is UTC, app displays America/Sao_Paulo>`

Output contract

A single AGENTS.md at the repo root, ≤150 lines, every line operational. No "External Resources" section. No appended Universal Agent Behavior block — that lives in the ad-philosophy skill. No meta-prose explaining gaps. In audit mode: a drift list, no file written.

AGENTS.md is a narrative document, so the Documentation Discipline rules in WORKFLOW.md §2 apply at write time:

  • No emoji anywhere in the file.
  • No dates, version stamps, DRAFT markers, or changelog blocks. Stack versions are facts (Node ≥18); release timelines are not.
  • Project Overview is the business-context-first paragraph — why the project exists before what it does.
  • One scope: this file is the operational guide for agents. Do not duplicate ARCHITECTURE.md patterns or ADR rationale here; link instead.
  • No speculation. If a section has no signal, write <TODO: not yet wired> once; do not narrate "this could be added later".

Next

  • In team / mature: run /ad-architecture once load-bearing patterns emerge in the code.
  • When you scope a product (multi-feature, target user, success metrics): /ad-prd (Layer 3 of the six-layer artifact stack; excluded from poc).
  • When you start your first feature: /ad-spec (Layer 4 of the six-layer artifact stack; references parent PRD for product-scope inheritance).
  • Skip both above in poc / solo until the project genuinely needs them — the WORKFLOW §1 prune principle applies.
  • ad-philosophy auto-loads on non-trivial work; no explicit invocation needed.

© CorridorTech, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/ad-bootstrap of CorridorTech/PoseCap.

Open the folder on GitHubat commit 626701b

Compare with similar skills

Ad Bootstrap next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Ad Bootstrap compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ad Bootstrap this skillCorridorTech/PoseCap224—~2.4kAutomated safety check: WarnApache-2.0
Using Agent Skillsaddyosmani/agent-skills103k4 repos~2.4kAutomated safety check: PassMIT
Claude ReflectBayramAnnakov/claude-reflect1.7k2 repos~627Automated safety check: PassMIT
Writing For Agentsbestofjs/bestofjs3.1k19 repos~2.7kAutomated safety check: PassMIT
Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills21k—~1.9kAutomated safety check: PassMIT
Task Observerrebelytics/one-skill-to-rule-them-all3.2k1 repos~12kAutomated safety check: PassCC-BY-4.0

Similar skills

  • Using Agent Skills

    addyosmani/agent-skills

    Meta-skill for choosing which workflow skill fits the task at hand, plus always-on habits: surface assumptions, stop on confusion, push back, keep it simple and stay in scope.

    103k GitHub starsUsed in 4 repos~2.4k tokens
    Agent WorkflowsAuto-check passed
  • Claude Reflect

    BayramAnnakov/claude-reflect

    Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md.

    1.7k GitHub starsUsed in 2 repos~627 tokens
    Agent WorkflowsAuto-check passed
  • Writing For Agents

    bestofjs/bestofjs

    Writing documents for agents. An agent skill from bestofjs/bestofjs.

    3.1k GitHub starsUsed in 19 repos~2.7k tokens
    Agent WorkflowsAuto-check passed
  • Neat-Freak Knowledge Closeout

    KKKKhazix/khazix-skills

    Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.

    21k GitHub stars~1.9k tokensUpdated 6 days ago
    Agent WorkflowsAuto-check passed
  • Task Observer

    rebelytics/one-skill-to-rule-them-all

    Monitors task execution for skill improvement opportunities.

    3.2k GitHub starsUsed in 1 repo~12k tokens
    Agent WorkflowsAuto-check passed
  • SkillOpt Sleep Cycle

    microsoft/SkillOpt

    Official

    Runs an on-demand or nightly sleep cycle that reviews past Claude Code sessions and proposes validated updates to CLAUDE.md and skills.

    18k GitHub stars~2.3k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

More from CorridorTech/PoseCap

All 15 skills in this repo
  • Ad Adr

    CorridorTech/PoseCap

    Draft a new ADR (Architecture Decision Record) at doc/adr/NNNN-<short-title.md, using Michael Nygard's Context/Decision/Consequences/Alternatives pattern.

    224 GitHub stars~1k tokensUpdated today
    Auto-check: notes
  • Ad Architecture

    CorridorTech/PoseCap

    Generate ARCHITECTURE.md at the repo root by scanning the code first, pre-filling layers/patterns/observability/deployment from observed signals, then asking only the genuine gaps.

    224 GitHub stars~1.5k tokensUpdated today
    Auto-check: notes
  • Ad Archive

    CorridorTech/PoseCap

    Hard-delete completed plan files (tasks Status:done, specs Status:shipped, PRDs Status:superseded, ADRs Status:superseded or deprecated) via git rm, leaving git history as the only ledger.

    224 GitHub stars~1.9k tokensUpdated today
    Auto-check: notes
  • Ad Drift

    CorridorTech/PoseCap

    Read-only drift audit — compare AGENTS.md, ARCHITECTURE.md, ADR statuses, feature specs in doc/specs/, and documentation discipline against what the code actually does.

    224 GitHub stars~1.8k tokensUpdated today
    Auto-check: notes
  • Ad Hooks

    CorridorTech/PoseCap

    Scaffold deterministic quality gates per WORKFLOW.md §11 — pre-commit (lint, format, secret-scan), pre-push (build, unit, integration).

    224 GitHub stars~2.4k tokensUpdated today
    Auto-check: notes
  • Ad Next

    CorridorTech/PoseCap

    Survey the project's state across the six-layer artifact stack and recommend prioritized next actions, modeled on flutter doctor.

    224 GitHub stars~3.3k tokensUpdated today
    Auto-check: notes

Categories

Questions about Ad Bootstrap

What does Ad Bootstrap do?

Generate AGENTS.md at the repo root by scanning the codebase first, pre-filling placeholders from observed signals, and asking only the genuine gaps. Ad Bootstrap is an agent skill from CorridorTech/PoseCap.md at the repo root by scanning the codebase first, pre-filling placeholders from observed signals, and asking only the genuine gaps.

When should I use Ad Bootstrap?

Ad Bootstrap fits situations like: the user wants to bootstrap; audit AGENTS.md / agents.md / CLAUDE.md (the operational guide for agents working on this project).

How do I install Ad Bootstrap in Claude Code?

Run `npx skills add CorridorTech/PoseCap --skill ad-bootstrap -a claude-code`. Or copy the skill folder (.claude/skills/ad-bootstrap in CorridorTech/PoseCap) into .claude/skills/ad-bootstrap in your project. Claude Code loads it when a task matches its description.

How do I install Ad Bootstrap in Codex?

Run `npx skills add CorridorTech/PoseCap --skill ad-bootstrap -a codex`. Or copy the skill folder (.claude/skills/ad-bootstrap in CorridorTech/PoseCap) into .agents/skills/ad-bootstrap in your project. Codex loads it when a task matches its description.

Can I use Ad Bootstrap in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add CorridorTech/PoseCap --skill ad-bootstrap -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ad-bootstrap, .gemini/skills/ad-bootstrap, .github/skills/ad-bootstrap and .opencode/skills/ad-bootstrap in your project.

What does Ad Bootstrap need to run?

Going by SKILL.md and its folder, Ad Bootstrap needs the command-line tools its instructions call (git and node). Its frontmatter pre-approves these tools: Read, Write, Glob, Grep, Bash.

Does Ad Bootstrap access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Ad Bootstrap safe to install?

Our automated static check of SKILL.md flagged 1 warning(s): mentions a credentials file (ssh keys, cloud or package-manager tokens). Read the flagged lines before installing; the check is not a guarantee either way.

What licence does Ad Bootstrap use?

Ad Bootstrap is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ad Bootstrap use?

About 2.4k tokens (SKILL.md is roughly 9.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Ad Bootstrap?

Skills that share tags, products or a category with Ad Bootstrap: Using Agent Skills (addyosmani/agent-skills, 103k stars), Claude Reflect (BayramAnnakov/claude-reflect, 1.7k stars), Writing For Agents (bestofjs/bestofjs, 3.1k stars) and Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ad Bootstrap?

CorridorTech (a GitHub organization) maintains it in CorridorTech/PoseCap, which has 224 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on October 7, 2026.

Source: CorridorTech/PoseCap on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.