aaif-clean-data

aaif-clean-data is a skill for Claude Code from aaif/community-events. It costs 100 tokens per session (3,735 once invoked), scanned A, original, MIT.

A data-cleaning workflow for an AAIF Community Intake spreadsheet, where AAIF is the organization collecting participant information. It checks names, cities, LinkedIn links, emails, duplicates, and city details before suggesting changes.

In plain words
What is it for?
Use it to scan intake responses, standardize text and LinkedIn URLs, identify bad emails and duplicate entries, derive cities from free-text answers, and apply approved corrections to the source sheet.
Why use it?
It finds inconsistent or missing information without changing the spreadsheet silently. Each proposed fix includes a before-and-after comparison, and approved changes are recorded for traceability.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the aaif-events plugin — 20 skills shipped together

Good fit Use it to scan intake responses, standardize text and LinkedIn URLs, identify…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aaif/community-events/aaif-clean-data
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add aaif/community-events --skill aaif-clean-data
Clone the repo
git clone --depth 1 https://github.com/aaif/community-events

Made for: Claude Code.

Or install aaif-events, the plugin that ships this one along with the rest of its 20 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for aaif-clean-data

README.md
[![agentmods](https://agentmods.dev/badge/skills/aaif/community-events/aaif-clean-data.svg)](https://agentmods.dev/skills/aaif/community-events/aaif-clean-data)
Your own site
<a href="https://agentmods.dev/skills/aaif/community-events/aaif-clean-data"><img src="https://agentmods.dev/badge/skills/aaif/community-events/aaif-clean-data.svg" alt="Measured on agentmods" height="20"></a>
Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,735 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00100 $0.03735
Opus 5 $0.00050 $0.01868
Sonnet 5 $0.00020 $0.00747
Haiku 4.5 $0.00010 $0.00374

Measured 7d ago against content hash a0181075d055, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

aaif-clean-data scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/clean.py, scripts/test_clean.py, scripts/test_extract_city.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/aaif-clean-data/SKILL.md · 241 lines

How it starts

The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Clean AAIF Intake Data

Normalize the intake data without silently changing it: detect issues, propose fixes with a before→after diff, and only write when the user approves. Fixes are applied to the source tab Form Responses (id 1cWkjCI5AGK9RX_fs23P5jRA4I2nixgnHuapvwHseZ5o) so the cleaned values flow through to the computed role tabs. Every applied change is noted per row in an Autofixes column on Form Responses (created on first use) — provenance for what the cleanup touched.

Prereq: the gws CLI must be installed and authenticated (gws-cli-access memory). See aaif-intake-ops-sheet memory for the sheet's structure. All reads/writes go by header name, never column letter.

The modes (engine: scripts/clean.py)

  1. Scan (default, read-only) — detect & propose:

    python3 ${CLAUDE_SKILL_DIR}/scripts/clean.py scan        # human-readable
    python3 ${CLAUDE_SKILL_DIR}/scripts/clean.py scan --json # structured
    

    Mechanical fixes proposed automatically: trim/collapse whitespace, re-case clearly all-upper/all-lower names & cities, canonicalize LinkedIn URLs (https://www.linkedin.com/in/..., strip tracking params & trailing slash). Flags raised (need judgment): City="Other", missing/invalid email, duplicate email, LinkedIn that isn't a profile URL, missing name.

  2. Apply (writes, on approval only) — feed an approved change list:

    python3 ${CLAUDE_SKILL_DIR}/scripts/clean.py apply changes.json
    

    changes.json is [{"row": <source row>, "header": "<column>", "value": "<new>"}]. It is gitignored (the repo is public) but still PII — names, emails, cities of real applicants — so delete it after the run; never attach or paste it. Writes those cells in Form Responses and appends a note per row to the Autofixes column, formatted <phrase> -> <new value> (; joins phrases within one run, | joins runs). The value is carried so a second edit to the same field isn't deduped away as a repeat of the first; separators are stripped out of it, because a phrase that can't be split back out re-appends every run.

Read the full file on GitHub · 241 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 241 lines · 100 tokens per session scan A a0181075d055

Subscribe to this mod's changes

aaif-clean-data is a skill published in the GitHub repository aaif/community-events (9 stars, last pushed 3d ago), licensed MIT. It adds 100 tokens to every session and 3,735 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.