Agent skill

Writers Helper

by magnus919 in magnus919/agent-skills

Guide any writer, fiction or nonfiction, through the whole writing lifecycle: premise and planning, outlining and worldbuilding, research, drafting and finishing, editing and revision, breaking…

MITAuto-check passedDocuments & Office

Install Writers Helper

skills CLI
$ npx skills add magnus919/agent-skills --skill writers-helper -a claude-code

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

GitHub CLI
$ gh skill install magnus919/agent-skills writers-helper --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/magnus919/agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/writers-helper .claude/skills/writers-helper && 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
writers-helper
GitHub stars
115
Token cost
~3.2k tokens
SKILL.md length
1,366 words
Files
32 (incl. scripts, references)
Skills in repo
131
Repo updated
First seen
Licence
MIT

At a glance

Guide any writer, fiction or nonfiction, through the whole writing lifecycle: premise and planning, outlining and worldbuilding, research, drafting and finishing, editing and revision, breaking…

  • Works in 8 steps: Protect the draft. During drafting: no… → Know where the story is. Before… → Diagnose before prescribing. When a… → …
  • Formatting deliverables into document files (see word-document
  • SKILL.md covers Operating principles…, Intake — first questions, Working modes and Stage routing, plus 7 more sections
  • Runs Python scripts from its folder; calls python3

What it does

Writers Helper is an agent skill from magnus919/agent-skills. Guide any writer, fiction or nonfiction, through the whole writing lifecycle: premise and planning, outlining and worldbuilding, research, drafting and finishing, editing and revision, breaking creative blocks, generating position-aware prompts and exercises, building sustainable writing habits, and the business of publishing — book proposals, query letters, synopses, agents, publishers, and book deals. Do not use for formatting deliverables into document files (see word-document, pdf-document, epub), for…

Its SKILL.md is about 3.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 34 other files, including scripts and reference files (for example `README.md`, `evals/evals.json` and `references/blocks-and-prompts.md`).

It sits in Documents & Office, covering Creative writing and fiction, Proposals and quotes and Technical documentation. It works with Microsoft Word. The repository describes itself as: Curated collection of AI agent skills for Hermes and other agent frameworks. The licence is MIT.

When your agent uses it

  • Formatting deliverables into document files (see word-document
  • Business documentation (see technical-documentation)
  • For pure grammar and spelling reference

Example prompts

  • “/writers-helper”

Requirements

  • Python 3

Workflow steps

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

  1. Protect the draft. During drafting: no critique, no re-reading, no mid-draft research. Keep a "gaps" list for facts to verify later. First…
  2. Know where the story is. Before generating a prompt, a scene, or feedback, ask which structural position the story occupies (beginning /…
  3. Diagnose before prescribing. When a writer is stuck, name the actual cause first — fear, energy, thin material, broken scene, wrong fix…
  4. Sequence revision. Structure first, then prose, then mechanics. Enforce a rest period and trusted readers before line editing. Do not let…
  5. Numbers are contracts. Word counts, page counts, act lengths, and format specs exist for a reason. Check work against them and surface…
  6. Voice sovereignty. The author's voice and final judgment outrank yours. Every suggestion is provisional; preserve and serve the writer's…
  7. Honest economics. Show real money math for deals, royalties, and self-publishing. Flag fee-charging "agents," reading fees, and…
  8. Copyright hygiene. Never reproduce text from published sources. Paraphrase and synthesize ideas; write original examples.

What it can do on your machine

Read from SKILL.md and the folder at commit 22b4723. 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

    Ships 5 files in scripts/ (Python, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    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

Writers Helper loads about 3.2k tokens when it runs, and up to ~25k if it reads all its reference files. Until then it costs about 159 tokens; SKILL.md has 1,366 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~159
When it runs · the whole SKILL.md, loaded when a task matches
~3.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~25k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from magnus919/agent-skills at commit 22b4723, republished under its MIT licence (© magnus919). 1,366 words, ~3,234 tokens.

Download SKILL.mdSave it as .claude/skills/writers-helper/SKILL.md (or your agent's skills folder). This skill also uses 31 other files; get the full folder from GitHub.
name
writers-helper
description
Guide any writer, fiction or nonfiction, through the whole writing lifecycle: premise and planning, outlining and worldbuilding, research, drafting and finishing, editing and revision, breaking creative blocks, generating position-aware prompts and exercises, building sustainable writing habits, and the business of publishing — book proposals, query letters, synopses, agents, publishers, and book deals. Do not use for formatting deliverables into document files (see word-document, pdf-document, epub), for technical or business documentation (see technical-documentation), or for pure grammar and spelling reference.
license
MIT

Writing — The Writer's Personal Skill

Help one writer (or one writing project) move from idea to published book. This skill is a synthesis of classic writer's-craft teaching — distilled from a 44-book writing library — covering every stage: planning, research, drafting, revision, creative blocks, prompts, habits, and the business side (proposals, query letters, agents, publishers, deals).

Operating principles (non-negotiable)

  1. Protect the draft. During drafting: no critique, no re-reading, no mid-draft research. Keep a "gaps" list for facts to verify later. First drafts are raw material; quality gates belong to revision.
  2. Know where the story is. Before generating a prompt, a scene, or feedback, ask which structural position the story occupies (beginning / halfway / crisis / climax). Position-aware guidance beats generic advice every time.
  3. Diagnose before prescribing. When a writer is stuck, name the actual cause first — fear, energy, thin material, broken scene, wrong fix — then match the remedy. Never hand out a generic "keep writing."
  4. Sequence revision. Structure first, then prose, then mechanics. Enforce a rest period and trusted readers before line editing. Do not let polish hide a broken story.
  5. Numbers are contracts. Word counts, page counts, act lengths, and format specs exist for a reason. Check work against them and surface mismatches as questions.
  6. Voice sovereignty. The author's voice and final judgment outrank yours. Every suggestion is provisional; preserve and serve the writer's voice, never flatten it into your own.
  7. Honest economics. Show real money math for deals, royalties, and self-publishing. Flag fee-charging "agents," reading fees, and vanity-press traps.
  8. Copyright hygiene. Never reproduce text from published sources. Paraphrase and synthesize ideas; write original examples.

Intake — first questions

Before doing anything, establish:

  • Project type: fiction or nonfiction; genre; format (novel, short story, picture book, poetry, proposal, essay...).
  • Stage: idea, planning, research, drafting, revising, polishing, submitting, published.
  • Goal & deadline: what "done" means and when (use the goal math in references/workflow-and-planning.md to turn this into a daily target).
  • Audience: who the writing is for; the reader relationship shapes voice and structure.
  • Constraint: one-page deliverable, word-count cap, publisher requirements, collaboration.

Then choose a working mode (below) and the reference(s) that fit.

Working modes

ModeUse whenRoute to
PlannerStarting a project; needs premise, outline, worldbuilding, research planreferences/workflow-and-planning.md, references/craft-and-structure.md, references/genres-and-formats.md
CoachBlocked, unfocused, or building habits; wants prompts and exercisesreferences/blocks-and-prompts.md, references/habits-and-lifestyle.md, scripts/writing-prompt.py, scripts/session-planner.py
EditorA draft exists; needs critique, revision passes, line editing, proofreadingreferences/editing-and-revision.md, references/prose-and-style.md, scripts/manuscript-stats.py
Business partnerQuery letters, proposals, agents, publishers, deals, submissionsreferences/publishing-and-career.md, templates/book-proposal.md, templates/query-letter.md, templates/synopsis.md, templates/submission-log.md, scripts/submission-tracker.py

Stage routing

StageWhat to doRead
Idea → premiseTest the idea, write a one-line pitch, check the high-concept barreferences/workflow-and-planning.md
PlanningOutline, backward design, scene staking, worldbuilding, goal mathreferences/workflow-and-planning.md, references/craft-and-structure.md, templates/premise-canvas.md, templates/story-outline.md, templates/worldbuilding-questionnaire.md
ResearchWrite first, verify later; keep a gaps list; avoid rabbit holesreferences/workflow-and-planning.md
DraftingSession ritual, flow sprints, finishing momentumreferences/drafting-and-process.md, scripts/session-planner.py, scripts/habit-log.py
BlockedDiagnose the block type, then apply the matched fix; generate promptsreferences/blocks-and-prompts.md, scripts/writing-prompt.py
RevisingRest, trusted readers, structure-first passes, scene questionsreferences/editing-and-revision.md, templates/critique-checklist.md, templates/revision-plan.md
PolishingProse passes, grammar, proofreading; measure the manuscriptreferences/prose-and-style.md, scripts/manuscript-stats.py
SubmittingQuery, synopsis, proposal, agent list, trackingreferences/publishing-and-career.md, templates/query-letter.md, templates/synopsis.md, templates/book-proposal.md, scripts/submission-tracker.py

References

  • references/workflow-and-planning.md — the writing lifecycle, premises and one-line pitches, outlining and backward design, worldbuilding, research discipline, goal math
  • references/craft-and-structure.md — plot as character change, the four energetic markers, scene anatomy, character and motivation, dialogue, POV, suspense, show-don't-tell
  • references/prose-and-style.md — voice, sentence craft, word choice, grammar essentials, clichés, readability, proofreading discipline
  • references/drafting-and-process.md — two-mode drafting, fast drafting, session ritual, momentum and finishing, the self-contract, daily practice
  • references/editing-and-revision.md — revision sequencing, critique protocol, layered passes, line editing, manuscript metrics
  • references/blocks-and-prompts.md — block diagnosis and matched fixes, position-aware prompt formula, exercise library, inner-critic management
  • references/habits-and-lifestyle.md — the ten habit categories, writing space, sustainability, reading as apprenticeship, identity
  • references/publishing-and-career.md — proposals, query letters, synopses, agents, publishers, deals, rights, rejection, platform
  • references/genres-and-formats.md — word-count ladders, genre contracts (romance, fantasy/SF, children's, poetry, comedy, graphic novels, screenwriting), manuscript conventions
  • references/pitfalls-and-solutions.md — the common failure modes at every stage, each with a fix

Templates

All templates are fill-in worksheets with guidance built in. Read the matching reference first, then use the template to structure the work.

  • templates/premise-canvas.md — test and sharpen a story idea before outlining
  • templates/story-outline.md — three-part outline with the four energetic markers and scene stakes
  • templates/scene-skeleton.md — one page per scene: the seven essential elements
  • templates/character-profile.md — goal, obstacle, loss plus flaw, strength, fear, dream, secret
  • templates/worldbuilding-questionnaire.md — setting, rules, society, history, sensory signature
  • templates/session-plan.md — a concrete daily writing session with targets and ritual
  • templates/critique-checklist.md — big-picture and targeted questions for readers and self-review
  • templates/revision-plan.md — order the passes from structure to proofreading
  • templates/prompt-cards.md — the prompt formula and original sample prompts per story position
  • templates/book-proposal.md — the nonfiction proposal, section by section
  • templates/query-letter.md — fiction and nonfiction one-page query structures
  • templates/synopsis.md — one-page synopsis structure and rules
  • templates/submission-log.md — track submissions, responses, and follow-ups
Show full SKILL.md (576 more words)Show less

Available Scripts

Python 3, standard library only, non-interactive, --json where noted. See --help on each.

ScriptPurposeInvocation
scripts/writing-prompt.pyGenerates position-aware three-part prompt sets (affirmation, plot element, writing assignment) with a record block; options --position, --count, --seed, --json. Run it in Coach mode when a writer is blocked or wants exercises — after diagnosing which structural position the story occupies.python3 scripts/writing-prompt.py --position halfway --count 3
scripts/session-planner.pyPlans a timed writing session: blocks, breaks, per-block word targets, flow-sprint pacing from --target-words/--minutes/--words-per-hour; --json for structured output. Run it at the start of a drafting session to turn a word-count goal into a concrete schedule.python3 scripts/session-planner.py --minutes 90 --target-words 1200
scripts/manuscript-stats.pyAnalyzes a manuscript file for editing signals: word count, sentence stats, passive voice, adverb density, crutch words, readability, per-chapter pacing (--chapter-regex, --json). Run it in Editor mode before and between revision passes to measure rather than guess.python3 scripts/manuscript-stats.py manuscript.txt --json
scripts/habit-log.pyJournals each writing session (date, words, minutes, energy via --log) and reports day/week/month progress and streaks via --report; state lives in a JSONL log (--file). Run it after every session when building sustainable writing habits.python3 scripts/habit-log.py --log 2026-08-08 850 45 4 --report week
scripts/submission-tracker.pyTracks queries and proposals (title, target, type, sent date, status, notes via --add; field edits via --update) and reports the pipeline with --list/--status, flagging follow-ups past --follow-up-days. Run it throughout Submitting mode so no query goes stale untracked.python3 scripts/submission-tracker.py --add "The Glass Orchard" "Agent Name" query 2026-08-08 sent --list

When not to use

  • Document formatting and packaging: Word, PDF, PowerPoint, Excel, or EPUB deliverables — use word-document, pdf-document, powerpoint, excel, or epub instead. This skill works on the words, not the file format.
  • Technical or business documentation: release notes, API docs, runbooks — use technical-documentation or adr-authoring for architecture decisions.
  • Pure grammar/spelling reference: a one-off question about a rule is better served by a style guide; this skill applies grammar within the editing workflow, not as a reference lookup.
  • Reading or writing EPUB files as an ebook task — route to epub.
  • Non-writing creative coaching — use genius-life or life-coach for general creativity/life practice outside a specific writing project.

Completion and exit conditions

  • Deliver the requested artifact: an outline, a draft, a revision pass, a query letter, a proposal, a submission list, or a completed session plan.
  • Confirm the current approach is adequate when the writer is already succeeding without intervention.
  • For diagnosis loops (blocks, structural problems), stop after at most three non-converging passes and report the evidence with the options, rather than churning the writer.

Prerequisites

  • Python 3 with the standard library only for all five scripts — no external packages, API keys, or services.
  • A plain-text manuscript file for manuscript-stats.py; writable JSONL state files for habit-log.py and submission-tracker.py (both default to a file in the working directory; pass --file to pin one).
  • The relevant references read first: scripts support the workflow, they do not replace the craft judgment in references/.

Limitations

  • Scripts measure and structure; they do not judge. Stats flag passive voice and pacing, but revision decisions stay with the Editor-mode judgment above — never let metrics override voice sovereignty.
  • manuscript-stats.py analyzes what you hand it (plain text); it cannot open .docx/.epub files or see formatting.
  • habit-log.py and submission-tracker.py are single-writer local tools with no sync or multi-user awareness; keep their JSONL files out of shared paths if more than one person writes there.
  • Generated prompts are position-aware patterns, not custom plot advice — pair them with the story's actual premise and characters.

© magnus919, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 31 other files (scripts, references) in writers-helper of magnus919/agent-skills.

  • SKILL.md
  • README.md
  • evals/evals.json
  • references/blocks-and-prompts.md
  • references/craft-and-structure.md
  • references/drafting-and-process.md
  • references/editing-and-revision.md
  • references/genres-and-formats.md
  • references/habits-and-lifestyle.md
  • references/pitfalls-and-solutions.md
  • references/prose-and-style.md
  • references/publishing-and-career.md
  • references/workflow-and-planning.md
  • scripts/habit-log.py
  • scripts/manuscript-stats.py
  • scripts/session-planner.py
  • scripts/submission-tracker.py
  • scripts/writing-prompt.py
  • … and 14 more

Open the folder on GitHubat commit 22b4723

Compare with similar skills

Writers Helper 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.

Writers Helper compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Writers Helper this skillmagnus919/agent-skills115—~3.2kAutomated safety check: PassMIT
Hermes3000 WritingHybridAIOne/hybridclaw159—~2.7kAutomated safety check: PassMIT
Readme From DOCXzhimaAi/ChatClaw307—~2kAutomated safety check: PassGPL-3.0
Weak Agent Testkklimuk/docx-cli216—~6.7kAutomated safety check: NotesMIT
Msp BrandRTFM-IT-Services-LLC/msp-claude-skills115—~3.7kAutomated safety check: PassCustom licence
Minimax DOCXnexu-io/open-design100k—~302Automated safety check: PassApache-2.0

Similar skills

  • Hermes3000 Writing

    HybridAIOne/hybridclaw

    Use Hermes3000 to plan, draft, revise, save, check consistency, and export long-form manuscripts through the Hermes3000 AI writing portal API.

    159 GitHub stars~2.7k tokensUpdated today
    Documents & OfficeAuto-check passed
  • Readme From DOCX

    zhimaAi/ChatClaw

    Update README and docs/readmes from Word docx (English and Chinese).

    307 GitHub stars~2k tokensUpdated 5 mo ago
    Documents & OfficeAuto-check passed
  • Weak Agent Test

    kklimuk/docx-cli

    Run the weak-agent adversarial test harness against docx-cli.

    216 GitHub stars~6.7k tokensUpdated today
    Documents & OfficeAuto-check: notes
  • Msp Brand

    RTFM-IT-Services-LLC/msp-claude-skills

    A skill your agent uses whenever generating ANY document, marketing material, email, proposal, slide deck, or other customer- or internal-facing content for your MSP, so that naming, visual style…

    115 GitHub stars~3.7k tokensUpdated 8 days ago
    Documents & OfficeAuto-check passed
  • Minimax DOCX

    nexu-io/open-design

    Professional DOCX document creation and editing using OpenXML SDK.

    100k GitHub stars~302 tokensUpdated yesterday
    Documents & OfficeAuto-check passed
  • Sow Pws Builder

    aiskillstore/marketplace

    Trigger for: writing, revising, converting, or descoping a federal Statement of Work, Performance Work Statement, SOW, PWS, or SOO; develop executable requirements; define contract scope; create…

    433 GitHub stars~3.1k tokensUpdated yesterday
    Documents & OfficeAuto-check passed

More from magnus919/agent-skills

All 131 skills in this repo
  • Artifact Pyramids

    magnus919/agent-skills

    Organize durable agent research outputs as summaries, analysis, and evidence dossiers.

    119 GitHub stars~2.7k tokensUpdated today
    Auto-check passed
  • Ascii City Engine

    magnus919/agent-skills

    Build portable, first-person colored ASCII city engines and small GIS-derived city packs.

    119 GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Color Management

    magnus919/agent-skills

    Manage color workflows with ICC profiles, working spaces, gamut mapping, and color science.

    119 GitHub stars~2.6k tokensUpdated today
    Auto-check: notes
  • Data Scientist

    magnus919/agent-skills

    A skill your agent uses for PhD-level expertise in data science, statistics, and machine learning: rigorous statistical analysis, experimental design, causal inference, advanced modeling, research…

    119 GitHub stars~4.1k tokensUpdated today
    Auto-check passed
  • Docker Compose

    magnus919/agent-skills

    Use Docker Compose to define, run, debug, and harden multi-container applications.

    119 GitHub stars~2k tokensUpdated today
    Auto-check: notes
  • Fpga Development

    magnus919/agent-skills

    Design, review, simulate, and verify FPGA logic using explicit RTL contracts, clock and reset models, CDC analysis, timing constraints, and reproducible implementation evidence.

    119 GitHub stars~2.7k tokensUpdated today
    Auto-check passed

Works with

Questions about Writers Helper

What does Writers Helper do?

Guide any writer, fiction or nonfiction, through the whole writing lifecycle: premise and planning, outlining and worldbuilding, research, drafting and finishing, editing and revision, breaking…. Writers Helper is an agent skill from magnus919/agent-skills. Guide any writer, fiction or nonfiction, through the whole writing lifecycle: premise and planning, outlining and worldbuilding, research, drafting and finishing, editing and revision, breaking creative blocks, generating position-aware prompts and exercises, building sustainable writing habits, and the business of publishing — book proposals, query letters, synopses, agents, publishers, and book deals.

When should I use Writers Helper?

Writers Helper fits situations like: formatting deliverables into document files (see word-document; business documentation (see technical-documentation); for pure grammar and spelling reference.

How do I install Writers Helper in Claude Code?

Run `npx skills add magnus919/agent-skills --skill writers-helper -a claude-code`. Or copy the skill folder (writers-helper in magnus919/agent-skills) into .claude/skills/writers-helper in your project. Claude Code loads it when a task matches its description.

How do I install Writers Helper in Codex?

Run `npx skills add magnus919/agent-skills --skill writers-helper -a codex`. Or copy the skill folder (writers-helper in magnus919/agent-skills) into .agents/skills/writers-helper in your project. Codex loads it when a task matches its description.

Can I use Writers Helper 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 magnus919/agent-skills --skill writers-helper -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/writers-helper, .gemini/skills/writers-helper, .github/skills/writers-helper and .opencode/skills/writers-helper in your project.

What does Writers Helper need to run?

Going by SKILL.md and its folder, Writers Helper needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Writers Helper 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 Writers Helper 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Writers Helper use?

Writers Helper is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Writers Helper use?

About 3.2k tokens (SKILL.md is roughly 13k 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 21k tokens, read only when the agent opens those files.

What are the alternatives to Writers Helper?

Skills that share tags, products or a category with Writers Helper: Hermes3000 Writing (HybridAIOne/hybridclaw, 159 stars), Readme From DOCX (zhimaAi/ChatClaw, 307 stars), Weak Agent Test (kklimuk/docx-cli, 216 stars) and Msp Brand (RTFM-IT-Services-LLC/msp-claude-skills, 115 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Writers Helper?

magnus919 (a GitHub user) maintains it in magnus919/agent-skills, which has 115 GitHub stars. The repository holds 131 skills in this directory. The repository was last updated on October 10, 2026.

Source: magnus919/agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.