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…
$ npx skills add CorridorTech/PoseCap --skill ad-ground -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install CorridorTech/PoseCap ad-ground --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/CorridorTech/PoseCap.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/ad-ground .claude/skills/ad-ground && rm -rf skills-srcUse ~/.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/
Install the "ad-ground" agent skill from https://github.com/CorridorTech/PoseCap/tree/main/.claude/skills/ad-ground into .claude/skills/ad-ground/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ad-ground", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/CorridorTech/PoseCap/tree/main/.claude/skills/ad-groundType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add CorridorTech/PoseCap --skill ad-ground -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install CorridorTech/PoseCap ad-ground --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CorridorTech/PoseCap.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/ad-ground .agents/skills/ad-ground && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ad-ground" agent skill from https://github.com/CorridorTech/PoseCap/tree/main/.claude/skills/ad-ground into .agents/skills/ad-ground/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ad-ground", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add CorridorTech/PoseCap --skill ad-ground -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install CorridorTech/PoseCap ad-ground --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CorridorTech/PoseCap.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/ad-ground .cursor/skills/ad-ground && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "ad-ground" agent skill from https://github.com/CorridorTech/PoseCap/tree/main/.claude/skills/ad-ground into .cursor/skills/ad-ground/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ad-ground", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/CorridorTech/PoseCap.git --path .claude/skills/ad-ground--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add CorridorTech/PoseCap --skill ad-ground -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install CorridorTech/PoseCap ad-ground --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CorridorTech/PoseCap.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/ad-ground .gemini/skills/ad-ground && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "ad-ground" agent skill from https://github.com/CorridorTech/PoseCap/tree/main/.claude/skills/ad-ground into .gemini/skills/ad-ground/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ad-ground", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install CorridorTech/PoseCap ad-groundInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add CorridorTech/PoseCap --skill ad-ground -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/CorridorTech/PoseCap.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/ad-ground .github/skills/ad-ground && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "ad-ground" agent skill from https://github.com/CorridorTech/PoseCap/tree/main/.claude/skills/ad-ground into .github/skills/ad-ground/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ad-ground", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add CorridorTech/PoseCap --skill ad-ground -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install CorridorTech/PoseCap ad-ground --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/CorridorTech/PoseCap.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/ad-ground .opencode/skills/ad-ground && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "ad-ground" agent skill from https://github.com/CorridorTech/PoseCap/tree/main/.claude/skills/ad-ground into .opencode/skills/ad-ground/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ad-ground", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
ad-groundFour-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…
Ad Ground is an agent skill from CorridorTech/PoseCap. 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 and gate any deviation with an irrefutable justification before code is written. 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"…
Its SKILL.md is about 2k 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 Writing & Content, covering Git workflow, Blog and article writing and Refactoring. The licence is Apache-2.0.
5 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 626701b. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
ReadGlobGrepBashWebFetchWebSearchFrom allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
gitFrom the folder's file list and the shell code blocks in SKILL.md.
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.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Ad Ground loads about 2k tokens when it runs. Until then it costs about 178 tokens; SKILL.md has 862 words of instructions outside code blocks.
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.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
allowed-tools: Read, Glob, Grep, Bash, WebFetch, WebSearchAutomated 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.
The full file from CorridorTech/PoseCap at commit 626701b, republished under its Apache-2.0 licence (© CorridorTech). 862 words, ~1,954 tokens.
.claude/skills/ad-ground/SKILL.md (or your agent's skills folder).Implements WORKFLOW §4 + §5 end-to-end as a single research pass. The four sources are joined by AND, not OR — every non-trivial change runs the full research pass, then synthesizes a happy path, then justifies any deviation. Output is the input to whatever skill or freeform turn produces the implementation plan; this skill does not write code.
Confirm what is being researched. The research scope is the smallest verifiable surface that captures the change: a function to add, a library to pick, a pattern to apply. State it in one sentence before research starts. If the surface is broader than one sentence captures, ask the user to narrow it; broad research scopes produce diluted research.
If the change is genuinely trivial (rename, typo, one-line refactor on a tested path), skip this skill.
For each language and library in scope, cite the canonical doc URL and version. Use WebFetch to confirm the page exists and read the relevant section; use WebSearch to locate it if the URL is unknown. If neither produces a confident hit, ask the user for a known-good link rather than fabricating one. Output: bulleted citations, one per language/library, each with URL plus a one-line summary of the relevant guidance.
Find ≥1 (prefer 2–3) public implementation references solving the same technical research scope with similar techniques. References include open-source repos, Stack Overflow / forum answers, blog posts, and gists — anything with citable code or an explicit code-bearing answer. The match is technical, not domain — a CRUD-app-with-auth and a CLI-with-auth both hit "auth flow", and either is valid for the auth research scope. Use WebSearch (e.g. site:github.com <research scope> language:<lang>, site:stackoverflow.com <research scope>, <library> <research scope> example) and follow up with WebFetch of the specific page. Cite <source>:<locator> — <repo>:<path>:<line-range> for repos, <URL> for Stack Overflow / forum / blog / gist — and quote the relevant block. Never paraphrase code from training memory. If search is inconclusive, ask the user for a known reference.
Grep / glob the current repo for analogous patterns. Cite <file>:<line> plus a one-line description of how the existing example handles the same shape. If the codebase has no analog, state that explicitly (real signal, not a gap).
Run git log --all --oneline -- <relevant-paths>, git log --all --grep=<keyword>, and a sweep of sibling active branches (git branch -a, then git log <branch> -- <paths> on those that look related). Surface any prior attempt or sibling solution — including abandoned ones — with <commit-sha> plus the touching file path and a one-line description. If the search is genuinely empty, state "no prior attempt found" — that is the valid Source D outcome when there isn't one. Narrow with --grep or -S on multi-thousand-commit repos.
In one paragraph, name the most-grounded approach for the research scope and cite at least one source per Source A / B / C. Source D is included when it produced a hit; otherwise mark "no prior attempt found." The paragraph is the canonical answer the engineer would give if asked "what is the canonical, idiomatic way to solve this here?" — the question WORKFLOW.md §4 frames.
If the implementation the user (or you) is about to write deviates from the synthesized happy path, write the justification before any code lands. The justification must name the specific constraint, evidence, or trade-off forcing the deviation — generic "we want it differently" is insufficient. If the justification cannot be written confidently, loop back to Step 1 and look harder; do not deviate without it.
The gate is prescriptive, not descriptive: WORKFLOW §4 asks "was the deviation deliberate?"; this gate asks "is the deviation defensible against the four sources?" Write the answer down.
Before handing off to implementation, report a soft verdict against four checks:
If any check fails, surface the gap to the user and ask before proceeding rather than blocking. The user retains the authority to skip; the discipline is in surfacing, not in enforcement.
When the host exposes AskUserQuestion, render the checkpoint as a structured multi-choice card listing the six checks with their yes/no/n.a. status plus a final proceed / pause for more research selector — instead of dropping the verdict as plain text. Falls back to numbered text on hosts without the primitive (Codex).
A single message structured as:
## Recortte
<one sentence>
## Source A — official documentation
- <lang/lib>: <URL@version> — <one-line summary>
## Source B — validated implementation references
- <repo>:<path>:<line-range> — <one-line summary> # repo form <quoted code block>
```
- <URL> — <one-line summary> # Stack Overflow / forum / blog / gist
```
<quoted code block>
```<file>:<line> — <one-line summary><commit-sha> <touching-path> — <one-line summary><one paragraph synthesizing A + B + C + D, with citations>
<what stays canonical><list of deviations><deviation>: <irrefutable justification><gap if no><gap if no><gap if no><gap if no>
No code is written by this skill. The output feeds the next turn (or `/ad-task`, `/ad-philosophy`'s Goal-Driven Execution, or freeform implementation).
## Next
- Implement per the synthesized happy path. Cite the sources you grounded against in commit messages or task `Notes`.
- `/ad-task` if the work needs explicit decomposition into checkbox-toggle work units.
- `/ad-review main..HEAD` (or current scope) before merge — WORKFLOW §10.
- `/ad-adr` if the deviation gate surfaced a binding architectural decision.© 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
Just SKILL.md in .claude/skills/ad-ground of CorridorTech/PoseCap.
Open the folder on GitHubat commit 626701b
Ad Ground 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Ad Ground this skillCorridorTech/PoseCap | 220 | — | ~2k | Automated safety check: Notes | Apache-2.0 | |
| Ad Groundalexandremendoncaalvaro/CorridorKey-Runtime | 755 | 1 repos | ~1.5k | Automated safety check: Pass | Custom licence | |
| SepiaNanako0129/sepia | 3k | — | ~3.6k | Automated safety check: Pass | MIT | |
| Blogtheopenco/llmgateway | 1.7k | — | ~2.2k | Automated safety check: Pass | Custom licence | |
| Release Postquarto-dev/quarto-r | 160 | 1 repos | ~2.5k | Automated safety check: Pass | MIT | |
| Penguin Harness DevPrism-Shadow/penguin-harness | 2.5k | — | ~3.4k | Automated safety check: Pass | Apache-2.0 |
alexandremendoncaalvaro/CorridorKey-Runtime
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…
Nanako0129/sepia
Make AI-generated writing read as human-written, in fiction and in professional prose.
theopenco/llmgateway
Write and validate an LLM Gateway marketing blog post in the repository's current house style, including structured frontmatter and a gpt-image-2 OpenGraph image.
quarto-dev/quarto-r
Create professional package release blog posts following Tidyverse or Shiny blog conventions.
Prism-Shadow/penguin-harness
A skill your agent uses when developing PenguinHarness itself — changing packages/{core,server,web,cli,desktop,landing,docs,skills}, the built-in model catalog, the installers or the release…
web-infra-dev/rstest
Generate a narrative version release blog post from commits within a tag range.
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.
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.
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.
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.
CorridorTech/PoseCap
Scaffold deterministic quality gates per WORKFLOW.md §11 — pre-commit (lint, format, secret-scan), pre-push (build, unit, integration).
CorridorTech/PoseCap
Survey the project's state across the six-layer artifact stack and recommend prioritized next actions, modeled on flutter doctor.
Categories
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…. Ad Ground is an agent skill from CorridorTech/PoseCap. 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 and gate any deviation with an irrefutable justification before code is written.
Ad Ground fits situations like: tasks that involve Git workflow; tasks that involve Blog and article writing; tasks that involve Refactoring.
Run `npx skills add CorridorTech/PoseCap --skill ad-ground -a claude-code`. Or copy the skill folder (.claude/skills/ad-ground in CorridorTech/PoseCap) into .claude/skills/ad-ground in your project. Claude Code loads it when a task matches its description.
Run `npx skills add CorridorTech/PoseCap --skill ad-ground -a codex`. Or copy the skill folder (.claude/skills/ad-ground in CorridorTech/PoseCap) into .agents/skills/ad-ground in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add CorridorTech/PoseCap --skill ad-ground -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-ground, .gemini/skills/ad-ground, .github/skills/ad-ground and .opencode/skills/ad-ground in your project.
Going by SKILL.md and its folder, Ad Ground needs the command-line tools its instructions call (git). Its frontmatter pre-approves these tools: Read, Glob, Grep, Bash, WebFetch, WebSearch.
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.
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
Ad Ground 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.
About 2k tokens (SKILL.md is roughly 7.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Ad Ground: Ad Ground (alexandremendoncaalvaro/CorridorKey-Runtime, 755 stars), Sepia (Nanako0129/sepia, 3k stars), Blog (theopenco/llmgateway, 1.7k stars) and Release Post (quarto-dev/quarto-r, 160 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
CorridorTech (a GitHub organization) maintains it in CorridorTech/PoseCap, which has 220 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.
