Agent skill

Name Framework Migration First Step

by opensanctions in opensanctions/opensanctions

Migrate ad-hoc name cleaning in a crawler to h.reviewnames (Step 1 of the name framework migration).

Install Name Framework Migration First Step

skills CLI

$ npx skills add opensanctions/opensanctions --skill name-framework-migration-first-step -a claude-code

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

GitHub CLI

$ gh skill install opensanctions/opensanctions name-framework-migration-first-step --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/opensanctions/opensanctions.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/name-framework-migration-first-step .claude/skills/name-framework-migration-first-step && 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/

Paste into Claude Code

Install the "name-framework-migration-first-step" agent skill from https://github.com/opensanctions/opensanctions/tree/main/.claude/skills/name-framework-migration-first-step into .claude/skills/name-framework-migration-first-step/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "name-framework-migration-first-step", 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

$skill-installer install https://github.com/opensanctions/opensanctions/tree/main/.claude/skills/name-framework-migration-first-step

Type 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.

skills CLI

$ npx skills add opensanctions/opensanctions --skill name-framework-migration-first-step -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install opensanctions/opensanctions name-framework-migration-first-step --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/opensanctions/opensanctions.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/name-framework-migration-first-step .agents/skills/name-framework-migration-first-step && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "name-framework-migration-first-step" agent skill from https://github.com/opensanctions/opensanctions/tree/main/.claude/skills/name-framework-migration-first-step into .agents/skills/name-framework-migration-first-step/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "name-framework-migration-first-step", 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.

skills CLI

$ npx skills add opensanctions/opensanctions --skill name-framework-migration-first-step -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install opensanctions/opensanctions name-framework-migration-first-step --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/opensanctions/opensanctions.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/name-framework-migration-first-step .cursor/skills/name-framework-migration-first-step && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "name-framework-migration-first-step" agent skill from https://github.com/opensanctions/opensanctions/tree/main/.claude/skills/name-framework-migration-first-step into .cursor/skills/name-framework-migration-first-step/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "name-framework-migration-first-step", 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

$ gemini skills install https://github.com/opensanctions/opensanctions.git --path .claude/skills/name-framework-migration-first-step

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add opensanctions/opensanctions --skill name-framework-migration-first-step -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install opensanctions/opensanctions name-framework-migration-first-step --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/opensanctions/opensanctions.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/name-framework-migration-first-step .gemini/skills/name-framework-migration-first-step && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "name-framework-migration-first-step" agent skill from https://github.com/opensanctions/opensanctions/tree/main/.claude/skills/name-framework-migration-first-step into .gemini/skills/name-framework-migration-first-step/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "name-framework-migration-first-step", 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.

GitHub CLI

$ gh skill install opensanctions/opensanctions name-framework-migration-first-step

Installs 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).

skills CLI

$ npx skills add opensanctions/opensanctions --skill name-framework-migration-first-step -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/opensanctions/opensanctions.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/name-framework-migration-first-step .github/skills/name-framework-migration-first-step && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "name-framework-migration-first-step" agent skill from https://github.com/opensanctions/opensanctions/tree/main/.claude/skills/name-framework-migration-first-step into .github/skills/name-framework-migration-first-step/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "name-framework-migration-first-step", 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.

skills CLI

$ npx skills add opensanctions/opensanctions --skill name-framework-migration-first-step -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install opensanctions/opensanctions name-framework-migration-first-step --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/opensanctions/opensanctions.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/name-framework-migration-first-step .opencode/skills/name-framework-migration-first-step && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "name-framework-migration-first-step" agent skill from https://github.com/opensanctions/opensanctions/tree/main/.claude/skills/name-framework-migration-first-step into .opencode/skills/name-framework-migration-first-step/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "name-framework-migration-first-step", 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.

Facts

Skill name: name-framework-migration-first-step
GitHub stars: 831
Token cost: ~1.1k tokens
SKILL.md length: 406 words
Files: 2
Skills in repo: 11
Repo updated: Oct 7, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Migrate ad-hoc name cleaning in a crawler to h.reviewnames (Step 1 of the name framework migration).

Works in 3 steps: Derive a branch name from the crawler… → Create and check out the branch → Confirm you are on the new branch before…
A crawler.py contains delimiter splits
SKILL.md covers Branch setup, Crawler source, Read first (in order) and Trigger patterns to find, plus 3 more sections
Calls git and uvx

What it does

Name Framework Migration First Step is an agent skill from opensanctions/opensanctions. Migrate ad-hoc name cleaning in a crawler to h.reviewnames (Step 1 of the name framework migration). Use when a crawler.py contains delimiter splits, regex substitutions, bracket stripping, or conditional logic applied to name strings before the name is added or applied.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `examples/migrations.md`).

It sits in Data & Analytics, covering Code migrations and Web scraping. The repository describes itself as: An open database of international sanctions data, persons of interest and politically exposed persons. The licence is MIT.

When your agent uses it

A crawler.py contains delimiter splits
Regex substitutions
Bracket stripping
Conditional logic applied to name strings before the name is added

Example prompts

“/name-framework-migration-first-step”

Requirements

Python 3

Workflow steps

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

Derive a branch name from the crawler path by taking the dataset name (the directory containing crawler.py) and prefixing it with…
Create and check out the branch
Confirm you are on the new branch before proceeding.

What it can do on your machine

Read from SKILL.md and the folder at commit 4499adf. 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
Shell commands in SKILL.md call:
- git
- uvx
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git and uvx, 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

Name Framework Migration First Step loads about 1.1k tokens when it runs. Until then it costs about 77 tokens; SKILL.md has 406 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~77
When it runs · the whole SKILL.md, loaded when a task matches: ~1.1k

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

The full file from opensanctions/opensanctions at commit 4499adf, republished under its MIT licence (© opensanctions). 406 words, ~1,092 tokens.

Download SKILL.mdSave it as .claude/skills/name-framework-migration-first-step/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: name-framework-migration-first-step
description: Migrate ad-hoc name cleaning in a crawler to h.review_names (Step 1 of the name framework migration). Use when a crawler.py contains delimiter splits, regex substitutions, bracket stripping, or conditional logic applied to name strings before the name is added or applied.
argument-hint: [crawler.py path]
disable-model-invocation: true

Perform Step 1 of the name framework migration in $ARGUMENTS: introduce h.review_names alongside the existing cleaning logic.

Branch setup

Before making any changes:

Derive a branch name from the crawler path by taking the dataset name (the directory containing crawler.py) and prefixing it with name-migration/. For example, datasets/us/ga/med_exclusions/crawler.py → name-migration/us-ga-med-exclusions.
Create and check out the branch:
```
git checkout -b <branch-name>
```
Confirm you are on the new branch before proceeding.

Crawler source

!cat $ARGUMENTS

Read first (in order)

examples/migrations.md — real before/after migrations; read before touching any crawler
zavod/docs/extract/names.md#migrating-to-the-name-cleaning-helpers — full three-step procedure and rationale
zavod/zavod/helpers/names.py — exact signatures for review_names, check_names_regularity, Names

Trigger patterns to find

Scan the crawler for any of these before acting:

python

# Delimiter splits
last_name, name = name_raw.split(",", 1)
name, *aliases = h.multi_split(raw, SPLITS)

# Bracket/parenthesis stripping
name = name.replace("(Acting)", "")
name = name.strip("„")

# Regex substitutions or splits on name content
parts = re.split(r"(?i)\baka\b", name, maxsplit=1)
names = h.multi_split(name_raw, ["(w zapisie także", "(", ")"])

# Conditional checks on name content before apply_name
if len(name_split) > 1:
    entity.add("alias", name_split[1:])

Migration steps

zavod/docs/extract/names.md (the "Step 1" subsections) is the authoritative procedure and holds the exact code for each path — follow it, do not rely on a paraphrase here. This section only orients you and flags what's specific to running it as a skill.

First decide the path by dataset type:

Sanctions / debarment dataset (e.g. tagged list.sanction or list.debarment): mirror the existing cleaned names into a suggested = h.Names(), then call h.check_names_regularity and h.review_names(..., suggested=..., is_irregular=..., default_accepted=True).
Non-sanctions dataset: leave the existing logic untouched and add h.review_names(context, entity, original=original, llm_cleaning=True) — no suggested, no is_irregular. Then reconcile any custom alias-marker list (e.g. a NAME_SPLITS constant) against rigour.names.name_split_phrases_list() and add uncovered phrases as reject_strings under names.schema_rules, per the doc.

Invariants for both paths:

original is the unmodified raw source string, captured before any cleaning.
Existing entity.add / h.apply_name calls stay in place unchanged and keep driving output; reviews are not applied until Step 3.
Call h.review_names at most once per entity.

Show full SKILL.md (140 more words)Show less

Tell the user, after the edit: for sanctions, check a sample of created reviews and confirm the export has no name changes, and deploy Step 3 ASAP so new entities aren't default-accepted; for non-sanctions, check a sample of the LLM extraction.

After changes

After every edit to the crawler file, run:

uvx ruff check --fix $ARGUMENTS && uvx ruff format $ARGUMENTS

Fix any errors ruff reports before proceeding.

Once all changes are complete and ruff passes, stage the file:

git add $ARGUMENTS

Then output the suggested commit message (do not commit):

[<dataset_slug>] name migration

where <dataset_slug> is derived from the path by stripping datasets/ and /crawler.py and replacing / with _ (e.g. datasets/us/ga/med_exclusions/crawler.py → [us_ga_med_exclusions] name migration).

Do not

Do not proceed to Step 3 of the three-step migration procedure (switching to apply_reviewed_names) — that requires completed reviews first
Do not construct Names by guessing field names — read zavod/zavod/helpers/names.py first
Do not add explanatory comments beyond what the code requires

Files

SKILL.md and 1 other file in .claude/skills/name-framework-migration-first-step of opensanctions/opensanctions.

SKILL.md
examples/migrations.md

Open the folder on GitHubat commit 4499adf

Compare with similar skills

Name Framework Migration First Step 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.

Name Framework Migration First Step compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Name Framework Migration First Step this skillopensanctions/opensanctions	831	—	~1.1k	Automated safety check: Pass	MIT	today
Monitor With HaolemeHaolemeApp/Haoleme	157	—	~1.3k	Automated safety check: Pass	AGPL-3.0	1 mo ago
Firecrawl Competitive Intelfirecrawl/skills	115	—	~604	Automated safety check: Pass	ISC	yesterday
Frappe Agent MigratorImpertio-Studio/Frappe_Claude_Skill_Package	187	—	~2.8k	Automated safety check: Notes	MIT	20 days ago
Brd Browser Debugbrightdata/skills	264	—	~2k	Automated safety check: Pass	MIT	yesterday
System Design Case CatalogHoangNguyen0403/agent-skills-standard	570	—	~1.1k	Automated safety check: Pass	MIT	yesterday

Similar skills

Monitor With Haoleme
HaolemeApp/Haoleme
Selectively monitor important long-running or resource-intensive commands with Haoleme by prefixing them with hao, so status, output, and completion notifications sync to the mobile app.
157 GitHub stars~1.3k tokensUpdated 1 mo ago
Data & AnalyticsAuto-check passed
Firecrawl Competitive Intel
firecrawl/skills
Monitor competitor pricing, features, changelogs, dashboards, and product changes with Firecrawl.
115 GitHub stars~604 tokensUpdated yesterday
Data & AnalyticsAuto-check passed
Frappe Agent Migrator
Impertio-Studio/Frappe_Claude_Skill_Package
A skill your agent uses when migrating a Frappe app between major versions, detecting breaking API changes, or resolving post-migration errors.
187 GitHub stars~2.8k tokensUpdated 20 days ago
Data & AnalyticsAuto-check: notes
Brd Browser Debug
brightdata/skills
Debug Bright Data Scraping Browser sessions using the Browser Sessions API.
264 GitHub stars~2k tokensUpdated yesterday
Data & AnalyticsAuto-check passed
System Design Case Catalog
HoangNguyen0403/agent-skills-standard
Answer classic system design problems as constraint-to-solution sketches and coach interview practice: URL shortener, rate limiter, news feed, chat, notification, autocomplete, crawler, unique id.
570 GitHub stars~1.1k tokensUpdated yesterday
Data & AnalyticsAuto-check passed
Tmux
trpc-group/trpc-agent-go
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
1.8k GitHub starsUsed in 23 repos~868 tokens
Data & AnalyticsAuto-check passed

More from opensanctions/opensanctions

All 11 skills in this repo

Crawler Pep
opensanctions/opensanctions
Scaffold a new PEP (Politically Exposed Persons) crawler — members of a parliament, legislature, senate, chamber of deputies, cabinet, judiciary, or an asset-declaration register — from a source URL…
831 GitHub stars~1.9k tokensUpdated today
Auto-check: notes
Crawler Constants To Yml
opensanctions/opensanctions
Move hardcoded lookup/config constants (gender maps, header dicts, value translations, column-label maps, date formats) out of a crawler and into the dataset .yml — as datapatch lookups wherever…
831 GitHub stars~1.4k tokensUpdated today
Auto-check: notes
Dataset Metadata
opensanctions/opensanctions
Bring a dataset .yml's metadata in line with house conventions (title, summary, description, coverage, publisher, maintainer comments).
831 GitHub stars~604 tokensUpdated today
Auto-check: notes
Legislature Metadata
opensanctions/opensanctions
Refactor the title, description and coverage frequency of a legislature/parliament PEP dataset .yml into the house style.
831 GitHub stars~953 tokensUpdated today
Auto-check passed
Refactor Crawler
opensanctions/opensanctions
Rewrite messy or AI-generated crawler code into clean, production-ready style that follows the zavod best practices.
831 GitHub stars~1.1k tokensUpdated today
Auto-check: notes
Release Datasets
opensanctions/opensanctions
Release one or more datasets by adding them to a topical collection, bumping coverage.start, and verifying.
831 GitHub stars~566 tokensUpdated today
Auto-check passed

Questions about Name Framework Migration First Step

What does Name Framework Migration First Step do?

Migrate ad-hoc name cleaning in a crawler to h.reviewnames (Step 1 of the name framework migration). Name Framework Migration First Step is an agent skill from opensanctions/opensanctions.reviewnames (Step 1 of the name framework migration).

When should I use Name Framework Migration First Step?

Name Framework Migration First Step fits situations like: A crawler.py contains delimiter splits; regex substitutions; bracket stripping; conditional logic applied to name strings before the name is added.

How do I install Name Framework Migration First Step in Claude Code?

Run `npx skills add opensanctions/opensanctions --skill name-framework-migration-first-step -a claude-code`. Or copy the skill folder (.claude/skills/name-framework-migration-first-step in opensanctions/opensanctions) into .claude/skills/name-framework-migration-first-step in your project. Claude Code loads it when a task matches its description.

How do I install Name Framework Migration First Step in Codex?

Run `npx skills add opensanctions/opensanctions --skill name-framework-migration-first-step -a codex`. Or copy the skill folder (.claude/skills/name-framework-migration-first-step in opensanctions/opensanctions) into .agents/skills/name-framework-migration-first-step in your project. Codex loads it when a task matches its description.

Can I use Name Framework Migration First Step 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 opensanctions/opensanctions --skill name-framework-migration-first-step -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/name-framework-migration-first-step, .gemini/skills/name-framework-migration-first-step, .github/skills/name-framework-migration-first-step and .opencode/skills/name-framework-migration-first-step in your project.

What does Name Framework Migration First Step need to run?

Going by SKILL.md and its folder, Name Framework Migration First Step needs the command-line tools its instructions call (git and uvx). Our summary lists: Python 3.

Does Name Framework Migration First Step access the network?

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

Is Name Framework Migration First Step 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 Name Framework Migration First Step use?

Name Framework Migration First Step is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Name Framework Migration First Step use?

About 1.1k tokens (SKILL.md is roughly 4.4k 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 Name Framework Migration First Step?

Skills that share tags, products or a category with Name Framework Migration First Step: Monitor With Haoleme (HaolemeApp/Haoleme, 157 stars), Firecrawl Competitive Intel (firecrawl/skills, 115 stars), Frappe Agent Migrator (Impertio-Studio/Frappe_Claude_Skill_Package, 187 stars) and Brd Browser Debug (brightdata/skills, 264 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Name Framework Migration First Step?

opensanctions (a GitHub organization) maintains it in opensanctions/opensanctions, which has 831 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 7, 2026.

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

Install Name Framework Migration First Step

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Branch setup

Crawler source

Read first (in order)

Trigger patterns to find

Migration steps

After changes

Do not

Files

Compare with similar skills

Similar skills

More from opensanctions/opensanctions

Related

Questions about Name Framework Migration First Step