Citation Anchoring

Community

WILLOSCAR

citation-anchoring

Regression-check citation anchoring (citations stay in the same subsection) to prevent “polish drift” that breaks claim→evidence alignment.

Overview

Publisher	WILLOSCAR
Repository	`research-units-pipeline-skills`
Skill name	`citation-anchoring`
Stars	513
Forks	39
Bundled files	Instructions only
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by WILLOSCAR on GitHub. Read the source before you install it.

Installation

Install the Citation Anchoring AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/WILLOSCAR/research-units-pipeline-skills/tree/main/.codex/skills/citation-anchoring
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/WILLOSCAR/research-units-pipeline-skills/tree/main/.codex/skills/citation-anchoring

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/WILLOSCAR/research-units-pipeline-skills.git /tmp/research-units-pipeline-skills
mkdir -p .claude/skills
cp -r /tmp/research-units-pipeline-skills/.codex/skills/citation-anchoring .claude/skills/citation-anchoring

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Citation Anchoring in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Citation Anchoring on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Citation Anchoring is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Citation Anchoring (regression)

Triggers & routing

Trigger: citation anchoring, citation drift, regression, cite stability, 引用锚定, 引用漂移.
Use when: after editing/polishing, you want to confirm citations did not migrate across ### subsections.

Purpose: prevent a common failure mode: polishing rewrites text and accidentally moves citation markers into a different ### subsection, breaking claim→evidence alignment.

Inputs

output/DRAFT.md
output/citation_anchors.prepolish.jsonl (baseline; created by draft-polisher on first run)

Outputs

output/CITATION_ANCHORING_REPORT.md (PASS/FAIL + drift examples)

Baseline policy

draft-polisher captures a baseline once per run: output/citation_anchors.prepolish.jsonl.
Subsequent polish runs should keep per-H3 citation sets stable.

Workflow (analysis-only)

Role:

Auditor: only checks and reports; does not edit.

Steps:

Load the baseline anchors.
Parse the current output/DRAFT.md into ### subsections and extract citation keys per subsection.
Compare current sets to baseline sets:

keys added/removed within a subsection
keys that migrated across subsections

Write output/CITATION_ANCHORING_REPORT.md:

- Status: PASS only if no drift is detected
otherwise, - Status: FAIL with a short diff table + examples

Notes

If you intentionally restructure across subsections:

delete output/citation_anchors.prepolish.jsonl and regenerate a new baseline (then treat that as the new regression anchor).

Troubleshooting

Issue: baseline anchor file is missing

Fix:

Run draft-polisher once to generate output/citation_anchors.prepolish.jsonl, then rerun the anchoring check.

Issue: citations intentionally moved across subsections

Fix:

Delete output/citation_anchors.prepolish.jsonl and regenerate a new baseline (then treat that as the new regression anchor).

Frequently asked questions

What does the Citation Anchoring AI skill do?

Regression-check citation anchoring (citations stay in the same subsection) to prevent “polish drift” that breaks claim→evidence alignment.

Why use Citation Anchoring on TypingMind?

Because you install it once and use it with any model. Citation Anchoring is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Citation Anchoring in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/WILLOSCAR/research-units-pipeline-skills/tree/main/.codex/skills/citation-anchoring. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Citation Anchoring?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Citation Anchoring?

As many as you like. As long as a model supports skills, you can use Citation Anchoring with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Citation Anchoring AI skill free?

It is published on GitHub by WILLOSCAR. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Openclaw Qa Testing

openclaw

OrganizationPopular

Run, watch, debug, extend, or explain OpenClaw qa-lab and qa-channel scenarios, artifacts, and live lanes.

Proof Video

Add subtitles, captions, narration cues, or zoom to a proof video or PR recording using repo-local capture helpers and a system ffmpeg renderer.

Slack E2e

Test Slack with Convex-leased user OAuth or QA bots; check credentials, exercise owned messages, prove Gateway behavior, and distinguish API evidence from real Slack client interactions.

Telegram E2e Userbot

Prove user-visible OpenClaw Telegram behavior on Telegram's Test Server with Convex-leased team credentials; drive real-user turns and record messages, edits, deletions, reactions, typing, or rich…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Citation Anchoring (regression)

Triggers & routing

Inputs

Outputs

Baseline policy

Workflow (analysis-only)

Notes

Troubleshooting

Issue: baseline anchor file is missing

Issue: citations intentionally moved across subsections

Frequently asked questions

Related AI Skills

Set up your own AI workspace now