New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Xia

by hoangnb24 in hoangnb24/skills

Research unfamiliar implementation work before coding. An agent skill from hoangnb24/skills.

No licenceAuto-check passed

Install Xia

skills CLI
$ npx skills add hoangnb24/skills --skill xia -a claude-code

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

GitHub CLI
$ gh skill install hoangnb24/skills xia --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/hoangnb24/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/khuym/skills/xia .claude/skills/xia && 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
xia
GitHub stars
230
Token cost
~604 tokens
SKILL.md length
289 words
Files
4 (incl. references)
Skills in repo
6
Repo updated
First seen
Licence
None found

At a glance

Research unfamiliar implementation work before coding. An agent skill from hoangnb24/skills.

  • Works in 6 steps: Confirm whether research was waived. → Read repo contracts and map the stack… → Search locally for existing… → …
  • Work is ambiguous
  • SKILL.md covers Hard Gate, Depth, Required Flow and Evidence Labels, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Xia is an agent skill from hoangnb24/skills. Research unfamiliar implementation work before coding. Use when work is ambiguous, version-sensitive, or risky and requires repo mapping, local reuse, upstream patterns, or current docs.

Its SKILL.md is about 600 tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `agents/openai.yaml`, `references/research-brief-template.md` and `references/xia-protocol.md`).

When your agent uses it

  • Work is ambiguous
  • Version-sensitive
  • Risky and requires repo mapping
  • Upstream patterns

Example prompts

  • “/xia”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Confirm whether research was waived.
  2. Read repo contracts and map the stack from real artifacts.
  3. Search locally for existing functionality and extension points.
  4. Check upstream patterns only after local evidence is clear.
  5. Check current official docs with version awareness.
  6. Return a concise research brief using references/research-brief-template.md.

What it can do on your machine

Read from SKILL.md and the folder at commit 9a579fc. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

    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

Xia loads about 604 tokens when it runs, and up to ~2.2k if it reads all its reference files. Until then it costs about 48 tokens; SKILL.md has 289 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~48
When it runs · the whole SKILL.md, loaded when a task matches
~604
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.2k

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 passed

The automated check found no risky patterns in SKILL.md.

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 289 words (~604 tokens).

“Xia is the anti-reinvention scout. Use it before unfamiliar, ambiguous, version-sensitive, or high-risk implementation work when a research brief should come before planning or code.”

— opening of SKILL.md by hoangnb24
name
xia

Read the full SKILL.md on GitHub

Files

SKILL.md and 3 other files (references) in plugins/khuym/skills/xia of hoangnb24/skills.

  • SKILL.md
  • agents/openai.yaml
  • references/research-brief-template.md
  • references/xia-protocol.md

Open the folder on GitHubat commit 9a579fc

Compare with similar skills

Xia 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.

Xia compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Xia this skillhoangnb24/skills230—~604Automated safety check: PassNone
Omh Codebase Onboardingrlaope/oh-my-hermes3.2k—~1.8kAutomated safety check: PassMIT
Codebase Onboardingaffaan-m/ECC275k3 repos~2kAutomated safety check: PassMIT
Acquire Codebase Knowledgegithub/awesome-copilot40k1 repos~2.3kAutomated safety check: PassMIT
Codebase Memory MCPgithub/awesome-copilot40k—~4kAutomated safety check: PassMIT
OpenHarness End-to-End EvalsHKUDS/OpenHarness16k1 repos~2.1kAutomated safety check: NotesMIT

Similar skills

  • Omh Codebase Onboarding

    rlaope/oh-my-hermes

    [omh] Unfamiliar repository needing a guided tour: create a repo map, reading path, glossary, risk map, and first-task runway for unfamiliar codebases.

    3.2k GitHub stars~1.8k tokensUpdated today
    DevelopmentAuto-check passed

  • Codebase Onboarding

    affaan-m/ECC

    Analyze an unfamiliar codebase and generate a structured onboarding guide with architecture map, key entry points, conventions, and a starter CLAUDE.md.

    275k GitHub starsUsed in 3 repos~2k tokens
    DevelopmentAuto-check passed

  • Acquire Codebase Knowledge

    github/awesome-copilot

    Official

    Maps an unfamiliar codebase into seven evidence-backed documents in docs/codebase/, using a scan script and templates, for onboarding or architecture write-ups.

    40k GitHub starsUsed in 1 repo~2.3k tokens
    DevelopmentAuto-check passed

  • Codebase Memory MCP

    github/awesome-copilot

    Official

    A skill your agent uses when exploring unfamiliar code, mapping architecture, finding symbols or relationships, tracing callers, callees, data flow or dependencies, assessing impact, auditing dead…

    40k GitHub stars~4k tokensUpdated today
    Auto-check passed

  • OpenHarness End-to-End Evals

    HKUDS/OpenHarness

    Validates OpenHarness features by running real multi-turn agent loops with live LLM calls against an unfamiliar codebase, checking actual tool execution.

    16k GitHub starsUsed in 1 repo~2.1k tokens
    Testing & QAAuto-check: notes

  • Auditable Playbook Designer

    cursor/plugins

    Official

    Designs a step-by-step playbook for large or unfamiliar work, runs it as a loop of hypotheses and measurements, and logs decisions so a human can review them later.

    10k GitHub starsUsed in 8 repos~1k tokens
    Agent WorkflowsAuto-check passed

More from hoangnb24/skills

  • Tldraw API

    hoangnb24/skills

    Create, inspect, edit, persist, and verify tldraw canvases through the tldraw Desktop local Canvas API without mouse-driven Computer Use.

    230 GitHub stars~1.5k tokensUpdated 2 mo ago
    Auto-check passed

  • Prompt Leverage

    hoangnb24/skills

    Upgrade raw prompts into execution-ready instructions. An agent skill from hoangnb24/skills.

    230 GitHub stars~725 tokensUpdated 2 mo ago
    Auto-check passed

  • Goal Griller

    hoangnb24/skills

    Turn vague ideas into verifiable Codex goals. An agent skill from hoangnb24/skills.

    230 GitHub stars~1.1k tokensUpdated 2 mo ago
    Auto-check passed

  • Smart Commits

    hoangnb24/skills

    Organize an existing Git tree into logical commits and push them.

    230 GitHub stars~795 tokensUpdated 2 mo ago
    Auto-check passed

  • Sequence Execution Plan

    hoangnb24/skills

    Build dependency-aware plans from goals, incidents, backlogs, or priorities.

    230 GitHub stars~2.4k tokensUpdated 2 mo ago
    Auto-check passed

Questions about Xia

What does Xia do?

Research unfamiliar implementation work before coding. An agent skill from hoangnb24/skills. Xia is an agent skill from hoangnb24/skills. Research unfamiliar implementation work before coding.

When should I use Xia?

Xia fits situations like: work is ambiguous; version-sensitive; risky and requires repo mapping; upstream patterns.

How do I install Xia in Claude Code?

Run `npx skills add hoangnb24/skills --skill xia -a claude-code`. Or copy the skill folder (plugins/khuym/skills/xia in hoangnb24/skills) into .claude/skills/xia in your project. Claude Code loads it when a task matches its description.

How do I install Xia in Codex?

Run `npx skills add hoangnb24/skills --skill xia -a codex`. Or copy the skill folder (plugins/khuym/skills/xia in hoangnb24/skills) into .agents/skills/xia in your project. Codex loads it when a task matches its description.

Can I use Xia 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 hoangnb24/skills --skill xia -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/xia, .gemini/skills/xia, .github/skills/xia and .opencode/skills/xia in your project.

What does Xia need to run?

SKILL.md names no scripts, command-line tools or credentials: Xia is instructions for the agent only.

Does Xia access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Xia safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Xia use?

No licence was found for Xia or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Xia use?

About 604 tokens (SKILL.md is roughly 2.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.6k tokens, read only when the agent opens those files.

What are the alternatives to Xia?

Skills that share tags, products or a category with Xia: Omh Codebase Onboarding (rlaope/oh-my-hermes, 3.2k stars), Codebase Onboarding (affaan-m/ECC, 275k stars), Acquire Codebase Knowledge (github/awesome-copilot, 40k stars) and Codebase Memory MCP (github/awesome-copilot, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Xia?

hoangnb24 (a GitHub user) maintains it in hoangnb24/skills, which has 230 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on July 18, 2026.

Source: hoangnb24/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.