toneforge
Word add-in that checks for consistency across the document and can set a style by training on a style sample
Install / Use
npx skills add Gekko47/ToneForgeInstalls into whichever agent you are using.
.clinerules
Cline rules
Quality Score
Category
Content & MediaSupported Platforms
Tags
Our assessment of toneforge
toneforge scores 59/100 on our quality scale, 1111th of 1,155 Content & Media skills we index.
Its .clinerules is 4.5 KB long, well organised into 8 sections with 1 code example: a solid amount of guidance for an agent.
It has no GitHub stars yet, so there is no community track record; judge it on its content.
Maintenance, license and trust
- We could not determine when the repository was last updated.
- Our last check on 2026-11-10 found the source still online.
- No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
- Its trust signals score 68/100, with 3 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.
AI review by kimi-k2.7-code on 2026-10-02. Automated pattern scan on 2026-10-01. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
toneforge compared with similar skills
All 4 of these similar skills score higher than toneforge; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| toneforge (this skill)by Gekko47 | 59 | 0 | — | .clinerules |
| siyuanby siyuan-note | 100 | 47.3k | today | MCP Server |
| changelog-videoby heygen-com | 100 | 83.8k | 3d ago | SKILL.md |
| content-research-writerby ComposioHQ | 100 | 79.4k | 59d ago | SKILL.md |
| ad-creativeby coreyhaines31 | 100 | 60.1k | 5d ago | SKILL.md |
Frequently asked questions
- How do I install toneforge?
- Run
npx skills add Gekko47/ToneForge. The install tabs above show the steps for each supported agent. - Which AI agents does toneforge work with?
- It is written for Cline, as a .clinerules file. Other agents that read the same format can often use it too.
- Is toneforge safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It declares no license and scores 68/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is toneforge still maintained?
- We could not determine when the repository was last updated.
Skill content
View source on GitHubToneForge Cline Rules
These rules govern how Cline (and other AI coding assistants) interact with the ToneForge repository. They are always active. The path-scoped rules in this directory add detail when you touch the relevant files, and the skills in .cline/skills/ load on demand.
Read before changing anything
ROADMAP.md— the canonical stage ordering, status ledger, hard rules, and release gates. When another document disagrees with it, it wins.- The relevant stage file in
docs/stages/. docs/architecture.md— module boundaries, before adding any import.docs/decision-log.md— so you do not repeat a rejected decision.
Stage protocol
- Read the stage file and the canonical roadmap.
- Load only the skills the work actually needs.
- Inspect the current implementation before modifying it.
- Implement only the agreed stage scope.
- Run targeted tests.
- Run
npm run verify. - Update
docs/project-state.mdevidence and the ROADMAP status. - Record architectural decisions in
docs/decision-log.md. - State the result as PASS / PASS WITH DOCUMENTED LIMITATION / IMPLEMENTED / PARTIAL / BLOCKED / FAIL, and name what remains open.
- Commit only after the gate passes.
Hard rules
- Deterministic first. Anything measurable or safely enumerable is code.
- AI only where interpretation is necessary. A model is for tone, voice, rhetorical style, semantic flow, register, and meaning-preserving rewrites. AI is optional and never required for deterministic governance.
- One canonical profile. The same
StyleProfiledrives both Reformat and Consistency Review;GovernanceProfileis an additive envelope, not a replacement. - One mutation path. Rules and UI never mutate Word. Everything flows through
ChangePlan→ revision adapter →applyReviewedPlan. - No credential is ever persisted by the add-in. Not in
Office.roamingSettings, not inlocalStorage, not in the bundle. Keys live in the gitignored.envread by the Node-side development broker, or in the local gateway's memory.ProviderConnectionhas no secret-capable field. - Never commit secrets.
- Never claim verification you did not perform. The Word-host gate is human and currently open. A mocked result is a typed contract, not an integration.
Known open gates
npm run host:matrixreports hosts with 0 fully passing. Real Word verification is manual and recorded indocs/manual-verification.md.- Production credential custody is unresolved. The local dev broker is a development stand-in, not a release component.
- The consistency engine (C1–C10) has never run against a real document or a real model; its checks are uncalibrated heuristics.
A green automated run is never a release claim (ADR-0051).
Skills
toneforge-scaffold— where a file belongs, and the verification chaintoneforge-architecture— module boundaries and the deterministic-first exceptiontoneforge-officejs— reading Word, the single mutation path, tracked-editing gatestoneforge-llm— providers, the gateway, credentials, consentstoneforge-testing— Vitest, mocks, coveragetoneforge-consistency— the cross-report engine (C1–C10)
Roo Code equivalents live in .roo/ and are kept in sync with these.
Commit conventions
feat(word): add native revision adapter
feat(style): add deterministic style metrics
feat(ai): add resilient provider adapters
spike: verify Word revision and document capabilities
chore: scaffold ToneForge Office add-in
test: complete regression and review pass
Before committing
- [ ]
npm run typecheckpasses - [ ]
npm run lintpasses with zero warnings - [ ]
npm run formatpasses - [ ]
npm run secrets:scanpasses - [ ]
npm run docs:validatepasses - [ ]
npm run skills:validatepasses - [ ]
npm run testpasses - [ ]
npm run test:coveragemeets the 80% thresholds - [ ]
npm run buildsucceeds - [ ]
npm run validatesucceeds - [ ]
docs/project-state.mdevidence updated - [ ]
docs/decision-log.mdupdated if an architectural decision was made
npm run verify runs all of these in order.
Related Skills
siyuan
47.3kAn open-source, privacy-first, self-hosted knowledge workspace where humans and AI agents work together 开源、隐私优先、自托管的知识工作空间,让人与智能体在此协作
changelog-video
83.8kTurn a weekly changelog .md into a finished branded changelog video (square 1080, ~45-60s, Annie VO, animated brand background, mock-UI visualizations, lowkey captions)
content-research-writer
79.4kAssists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.
ad-creative
60.1kWhen the user wants to write or judge ad creative, or asks which ad, hook, or angle to run or kill: headlines, primary text, and variations for Google, Meta, LinkedIn, and TikTok, fresh angles when creative fatigues. Test hypotheses name the metric, comparison, and expected direction.
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
