human-eval-handoff-repair

human-eval-handoff-repair is a skill for Claude Code from yha9806/academic-writing-toolkit. It costs 78 tokens per session (2,111 once invoked), scanned A, original, MIT.

A checking and repair process for human-evaluation handoff packages, such as annotation spreadsheets returned by reviewers or labelers.

In plain words
What is it for?
Matching rows using stable keys, checking labels against the current schema, converting older labels, and producing files for unresolved rows.
Why use it?
It prevents labels from being copied into the wrong tasks when package versions, row orders, or schemas differ.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Matching rows using stable keys, checking labels against the current schema, converting older labels, and producing files for unresolved rows.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yha9806/academic-writing-toolkit/human-eval-handoff-repair
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 yha9806/academic-writing-toolkit --skill human-eval-handoff-repair
Clone the repo
git clone --depth 1 https://github.com/yha9806/academic-writing-toolkit

Made for: Claude Code.

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 human-eval-handoff-repair

README.md
[![agentmods](https://agentmods.dev/badge/skills/yha9806/academic-writing-toolkit/human-eval-handoff-repair/github.svg)](https://agentmods.dev/skills/yha9806/academic-writing-toolkit/human-eval-handoff-repair)
Your own site
<a href="https://agentmods.dev/skills/yha9806/academic-writing-toolkit/human-eval-handoff-repair"><img src="https://agentmods.dev/badge/skills/yha9806/academic-writing-toolkit/human-eval-handoff-repair/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for human-eval-handoff-repair

Your own site · 80×15
<a href="https://agentmods.dev/skills/yha9806/academic-writing-toolkit/human-eval-handoff-repair"><img src="https://agentmods.dev/badge/skills/yha9806/academic-writing-toolkit/human-eval-handoff-repair.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,111 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00078 $0.02111
Opus 5 $0.00039 $0.01056
Sonnet 5 $0.00016 $0.00422
Haiku 4.5 $0.00008 $0.00211

Measured 12d ago against content hash 13ba16e418db, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

human-eval-handoff-repair 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 12d ago.

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.

archive/skills/human-eval-handoff-repair/SKILL.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Human Eval Handoff Repair

Use this skill when the user asks to inspect, repair, migrate, or validate human-evaluation packages or filled annotation CSVs, especially when multiple package versions exist.

First Principle

Never trust row number, filename, or visible ID alone. Treat a filled CSV as usable only after it is aligned to the target public package by stable task-specific keys and its editable labels pass schema checks.

Do not fix labels by guessing. If a row cannot be matched safely, leave its annotation fields blank and produce a refill/import template plus an unmatched reference file.

Inputs To Locate

  • Target public handoff package folder or ZIP.
  • Filled CSVs from annotators.
  • Any older package claimed as the source version.
  • Current task schemas from the target UI data or target task CSVs.
  • If relevant, QC reports from the target package.

Prefer a user-specified output directory. If none is specified, write generated reports and repaired files under codex_outputs/ in the current workspace. Avoid synced personal document folders unless the user explicitly asks for them.

Task Types And Stable Keys

Use these stable keys before copying any labels:

  • Claim Warrant Audit: item_id, tradition, medium, period, layer, dimension_id, claim_text.
  • Release Suitability Audit: item_id, source_bucket, pipeline_mode, option_a_source, option_b_source, governed_option, option_a_text, option_b_text.
  • Card Faithfulness Spot Audit: audit_field_id, tradition, card_type, dimension_id, field_name, field_value, source_reference_excerpt.

If the exact stable key does not match, do not formally aggregate the row. Text-only fuzzy candidates may be generated for manual review, but must not be treated as validated mappings.

Editable Label Columns

Claim Warrant Audit editable columns:

  • support_source
  • overreach
  • certainty_calibration
  • recommended_action
  • annotator_confidence
  • notes

Release Suitability Audit editable columns:

Read the full file on GitHub · 205 lines

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. 12d ago First seen · 205 lines · 78 tokens per session scan A 13ba16e418db

Subscribe to this mod's changes

human-eval-handoff-repair is a skill published in the GitHub repository yha9806/academic-writing-toolkit (38 stars, last pushed 4d ago), licensed MIT. It adds 78 tokens to every session and 2,111 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

ledger-import-fixture-replay

Use when replaying Ledger import CSV fixtures to verify sourceRef preservation, cent normalization, and deterministic posting dates.

z3z1ma/10x · 29 tokens

PDF → spreadsheet — extract data into Excel (Local MCP)

Use when the user wants to pull data out of one or more PDFs (invoices, bank/credit-card statements, receipts, reports, tables) and put it into a spreadsheet. pdfread is one of the most-used tools; this codifies the read-PDF → structure → write-Excel workflow. Powered by Local MCP, on-device.

lanchuske/local-mcp-releases · 82 tokens

latex-writer

Write, structure, and compile LaTeX documents for academic purposes. Use this skill whenever the user needs to write a LaTeX document, choose the right document class or packages, format equations, manage bibliographies, create figures and tables in LaTeX, troubleshoot errors, or prepare a journal-ready manuscript.…

muhammad1438/academic-writer-skills · 0 tokens

data-management-plan

Write and review data management plans (DMPs) for research grants and projects. Use this skill whenever the user needs to write a DMP for NIH, NSF, UKRI, EU Horizon, or another funder; understand FAIR data principles; choose a data repository; describe data formats and metadata standards; handle sensitive or…

muhammad1438/academic-writer-skills · 0 tokens

xlsx

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from…

hamzabellouch/agent-skills · 206 tokens

weekly-crm-report

Cleans a weekly CRM export and produces a regional sales summary. Activates when the user asks to clean a CRM export, deduplicate sales rows, calculate regional totals, or generate a weekly sales report from a CSV.

FrancyJGLisboa/agent-skill-creator · 49 tokens