Agent skill

Happier Docs

by happier-dev in happier-dev/happier

Create, update, reorganize, or review Happier internal technical documentation and published user/operator/contributor docs with evidence-backed product truth, exact release status, canonical-page…

MITAuto-check passedDevelopment

Install Happier Docs

skills CLI
$ npx skills add happier-dev/happier --skill happier-docs -a claude-code

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

GitHub CLI
$ gh skill install happier-dev/happier happier-docs --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/happier-dev/happier.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/happier-docs .claude/skills/happier-docs && 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
happier-docs
GitHub stars
1.9k
Token cost
~2.7k tokens
SKILL.md length
1,396 words
Files
1
Skills in repo
28
Repo updated
First seen
Licence
MIT

At a glance

Create, update, reorganize, or review Happier internal technical documentation and published user/operator/contributor docs with evidence-backed product truth, exact release status, canonical-page…

  • Works in 8 steps: Classify the documentation impact → Identify audience, page type, and… → Establish product truth and release basis → …
  • A change affects docs/
  • SKILL.md covers 1. Classify the documentation…, 2. Identify audience, page…, 3. Establish product truth and… and 4. Choose the edit contract, plus 4 more sections
  • Calls yarn

What it does

Happier Docs is an agent skill from happier-dev/happier. Create, update, reorganize, or review Happier internal technical documentation and published user/operator/contributor docs with evidence-backed product truth, exact release status, canonical-page ownership, human voice, minimal editing, and appropriate validation. Use whenever a change affects docs/, apps/docs/, or behavior that may make existing Happier documentation incomplete or false.

Its SKILL.md is about 2.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Technical documentation. The repository describes itself as: Web, Desktop & Mobile client and orchestrator for Codex, Claude Code, OpenCode, Pi, Cursor, Grok, Antigravity, Kimi, Augment Code, Qwen, fully end-to-end encrypted. The licence is MIT.

When your agent uses it

  • A change affects docs/
  • Behavior that may make existing Happier documentation incomplete

Example prompts

  • “/happier-docs”

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. Classify the documentation impact
  2. Identify audience, page type, and canonical owner
  3. Establish product truth and release basis
  4. Choose the edit contract
  5. Prefer generating over writing
  6. Draft for meaning and human voice
  7. Validate the documentation contract
  8. Handoff

What it can do on your machine

Read from SKILL.md and the folder at commit 1f03ccd. 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

    Shell commands in SKILL.md call:

    • yarn

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use yarn, which can reach the network depending on how they are called.

    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

Happier Docs loads about 2.7k tokens when it runs. Until then it costs about 103 tokens; SKILL.md has 1,396 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~103
When it runs · the whole SKILL.md, loaded when a task matches
~2.7k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from happier-dev/happier at commit 1f03ccd, republished under its MIT licence (© happier-dev). 1,396 words, ~2,672 tokens.

Download SKILL.mdSave it as .claude/skills/happier-docs/SKILL.md (or your agent's skills folder).
name
happier-docs
description
Create, update, reorganize, or review Happier internal technical documentation and published user/operator/contributor docs with evidence-backed product truth, exact release status, canonical-page ownership, human voice, minimal editing, and appropriate validation. Use whenever a change affects `docs/**`, `apps/docs/**`, or behavior that may make existing Happier documentation incomplete or false.

Happier Documentation

Keep documentation truthful, useful, current, and owned without turning every code change into prose churn. Follow the root constitution and, for published docs, apps/docs/AGENTS.md. For an explicit deep review or QA request, use .agents/skills/happier-review as the orchestrator and apply this skill as the documentation-domain standard; this skill does not create a competing general review workflow.

1. Classify the documentation impact

For the changed behavior or contract, decide whether it affects:

  • internal technical/product architecture under docs/**;
  • published user/operator/self-hoster/contributor behavior under apps/docs/content/docs/**;
  • both surfaces;
  • neither surface, with a concrete reason.

A refactor that leaves every documented contract unchanged may need no docs edit. A behavior, command, setting, support status, workflow, failure/recovery path, protocol, persistence shape, compatibility rule, deployment requirement, or canonical owner change normally does.

2. Identify audience, page type, and canonical owner

Classify published pages as task guide, concept, reference, troubleshooting, or development documentation. Internal docs explain architecture, contracts, ownership, and contributor-facing implementation constraints.

Search by the feature, command, setting, route, schema, provider/agent id, UI label, error, and reader phrasing before creating a page. Update, move, consolidate, or retire the canonical page instead of adding a parallel explanation. Map links, navigation, related pages, examples, and translations or screenshots that depend on the changed documentation contract.

Placement is part of authorship, not cleanup afterwards. A published page belongs to exactly one section, is listed in that section's meta.json at the point a reader should meet it, and is linked from that section's index.mdx. A page missing from either is unreachable in a way that breaks no link and shows up in no diff. Moving a page is the same four edits in reverse. The section inventory is in apps/docs/AGENTS.md.

3. Establish product truth and release basis

Documentation is a claim, not proof. For Happier behavior:

  • inspect the reachable implementing producer and consumer, not only a matching string;
  • identify gates, defaults, platform/provider variation, failure/recovery behavior, and compatibility seams material to the claim;
  • establish the page's target stable, preview, development, or explicitly future basis from immutable release/artifact evidence when availability is release-sensitive;
  • distinguish shipped, preview, development-only, experimental, deprecated, planned, and merely possible behavior.

README files, existing docs, changelogs, plans, issues, PR descriptions, commit messages, comments, and generated summaries are orientation. They do not independently prove that behavior is reachable or released.

For vendor-owned behavior, use current official vendor documentation and keep attribution with the claim. Do not state a competitor's limitation as Happier's own conclusion. Never invent product names, capabilities, support levels, guarantees, dates, quotes, or personal experience. Cut unsupported superlatives and comparisons.

Use .agents/skills/happier-compatibility when documentation claims depend on released/predecessor formats, mixed versions, upgrades, rollback, migrations, or persisted historical data.

4. Choose the edit contract

Use the narrowest mode that serves the reader. Every added section or sentence must improve a decision, action, mental model, evidence boundary, or material caveat; prose that only restates another canonical owner does not earn its place:

  • Patch: add or correct bounded material and preserve every unaffected claim, example, link, caveat, and structural choice.
  • Polish: improve clarity and flow while preserving structure, information density, factual scope, and recognizable voice.
  • Rewrite: redesign structure or framing only when explicitly requested or when the current document cannot serve its audience.

An approved or preferred version becomes the baseline for later edits. A high change count in a correction pass is a warning sign, not evidence of quality. Every correction is a new claim: verify it as carefully as the text it replaces and do not swap one unsupported absolute for its opposite.

Before a substantial rewrite, inventory every material claim involving behavior, commands, settings, support, platforms, providers, compatibility, security, failure/recovery, readiness, and exact names. Account for each in the result. Humanizing is not summarizing.

5. Prefer generating over writing

Before drafting a reference table, check whether the same list already exists as structured data. Agent capabilities, feature flags, keyboard shortcuts, rate limits, download links and — where the plugin platform is present — runtime events, bundled plugins and the SDK's public surface all do. apps/docs/scripts/generateReference.mjs is the registry of what is generated today. Hand-maintained restatements of code are the single largest source of documentation drift in this repository, because nothing connects the data changing to the prose describing it.

Generate it, or link to the generated page. A generated page is compared against a fresh render on every build, so drift fails instead of shipping. Reserve hand-written prose for what a generator cannot produce: the mental model, the reason the mechanism exists, the failure modes, the judgement calls.

Two traps live inside the generators themselves. A hand-kept map of display names inside a generator drifts exactly like one inside a page — read the names from the source the app reads. And a declared field is not behaviour until you have found its consumer: publishing a flag whose value contradicts what the product does is worse than publishing nothing.

Where a capability is gated — a server feature flag, an experimental toggle, the account-level Experiments switch, a platform, a channel — the gate is part of the claim. Read uiFeatureRegistry.ts and features/catalog.ts rather than assuming availability, and state the gate where the reader meets the feature.

Show full SKILL.md (544 more words)Show less

6. Draft for meaning and human voice

Write like a thoughtful builder helping another developer: warm, direct, concrete, and technically honest.

  • Start with the reader's intent or outcome, not the implementation or a promotional hook.
  • For a substantial unfamiliar system, establish the mental model, normal path, important limits, and why the mechanism matters before cataloguing controls.
  • Lead with the user consequence, then include enough implementation detail to make the behavior trustworthy.
  • Keep commands, exact product terms, security boundaries, platform/provider differences, fallbacks, recovery, and readiness close to the claims they qualify.
  • Use topic headings that remain meaningful without the body and contain words readers recognize.
  • Follow the page skeleton in apps/docs/AGENTS.md — outcome lede, availability, prerequisites, the normal path, limits, failure modes, ## Related. A reader who has read one page should already know how to read the next.
  • Use the vocabulary in apps/docs/AGENTS.md: agents are Agents, provider is reserved for model/identity/voice/SCM providers, and a quoted UI label must match what the app renders today.
  • Avoid promotional fog, artificial urgency, generic importance, invented slogans, repetitive field-label bullets, and definition primarily by negation.
  • Preserve warmth, useful detail, and natural rhythm. Treat anti-slop patterns as diagnostic signals, not forbidden grammar.
  • Keep repository paths and implementation trivia out of user/operator prose unless the page is explicitly development-facing.
  • Never expose secrets, tokens, private URLs, internal-only evidence, or sensitive screenshots.

7. Validate the documentation contract

Run the narrowest checks that can falsify the edit:

  • inspect materially changed commands, links, examples, settings, defaults, and support statements;
  • run yarn --cwd apps/docs check:content — it resolves every internal link and #fragment, verifies that each documented Settings → … path names strings the app renders, and enforces the structural rules a reader feels but no compiler sees: every page listed in a meta.json, every section hub linking the pages beneath it, no cross-reference written as an unclickable code span, and no code-derived list drifting from its source. It runs inside the build, so these fail rather than ship; apps/docs/AGENTS.md lists what each check rejects;
  • run yarn --cwd apps/docs test for the guardrails themselves;
  • run yarn --cwd apps/docs types:check for published MDX/schema/TypeScript/generated-content changes;
  • run yarn --cwd apps/docs build when routing, navigation, generation, rendering, or production build behavior can be affected;
  • use current non-sensitive screenshots only when they materially improve a UI-heavy workflow;
  • for substantial published UI instructions, use the risk-appropriate live product check when runnable and authorized.

Do not add wording-policing tests. Validate parsing, generation, routing, links, commands, and factual behavior rather than exact prose.

When you find a class of breakage that no check can see — not one broken page, but a shape of defect that could recur silently — add the check rather than only fixing the instances. Every check in checkContent.mjs exists because its defect shipped and then stayed shipped. Give the new check a hard failure when its own input goes missing from inside this package: a check that skips on a missing directory is indistinguishable from a check that passes, and will read green through the next rename.

8. Handoff

Report:

  • canonical pages created, updated, moved, consolidated, or intentionally left unchanged;
  • audience/page type and target release/channel basis;
  • implementing evidence for decision-material claims;
  • materially affected surfaces and related pages checked;
  • validation actually run and anything unavailable;
  • remaining stale, uncertain, or intentionally deferred documentation and the next action.

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

Files

Just SKILL.md in .agents/skills/happier-docs of happier-dev/happier.

Open the folder on GitHubat commit 1f03ccd

Compare with similar skills

Happier Docs 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.

Happier Docs compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Happier Docs this skillhappier-dev/happier1.9k—~2.7kAutomated safety check: PassMIT
Diagram Designcathrynlavery/diagram-design45k1 repos~7.5kAutomated safety check: PassMIT
Simple Englishmoeru-ai/airi50k2 repos~4.6kAutomated safety check: PassMIT
Get API Docs with chubandrewyng/context-hub14k2 repos~775Automated safety check: PassMIT
Doc SyncJetBrains/ideavim10k2 repos~2.6kAutomated safety check: PassMIT
Mailspring App ScreenshotsFoundry376/Mailspring18k—~1.5kAutomated safety check: PassGPL-3.0

Similar skills

  • Diagram Design

    cathrynlavery/diagram-design

    Creates branded diagrams, from architecture, flowchart and sequence to charts and maps, as self-contained HTML with inline SVG, with import from draw.io, Mermaid and Excalidraw.

    45k GitHub starsUsed in 1 repo~7.5k tokens
    DevelopmentAuto-check passed
  • Simple English

    moeru-ai/airi

    Write or rewrite technical text with the rules of ASD-STE100 Simplified Technical English so it is clear, unambiguous, and free of AI slop.

    50k GitHub starsUsed in 2 repos~4.6k tokens
    DevelopmentAuto-check passed
  • Get API Docs with chub

    andrewyng/context-hub

    Fetches current documentation for third-party APIs and SDKs with the chub CLI before the agent writes code against them, instead of relying on remembered API shapes.

    14k GitHub starsUsed in 2 repos~775 tokens
    DevelopmentAuto-check passed
  • Doc Sync

    JetBrains/ideavim

    Official

    Keeps IdeaVim documentation in sync with code changes. An agent skill from JetBrains/ideavim.

    10k GitHub starsUsed in 2 repos~2.6k tokens
    DevelopmentAuto-check passed
  • Mailspring App Screenshots

    Foundry376/Mailspring

    Captures screenshots of the running Mailspring dev app for docs, PRs or visual checks by launching it with a debugging port, driving the UI and clipping to an element.

    18k GitHub stars~1.5k tokensUpdated today
    DevelopmentAuto-check passed
  • Draw.io Diagram Studio

    Agents365-ai/drawio-skill

    Creates and edits editable draw.io diagrams from descriptions, code, infrastructure files, SQL and API schemas, with sync, review, test and export tools.

    10k GitHub stars~2.4k tokensUpdated 5 days ago
    DevelopmentAuto-check: notes

More from happier-dev/happier

All 28 skills in this repo
  • Happier Review

    happier-dev/happier

    Conduct evidence-backed Happier code, plan-completeness, session, worktree, feature, commit, branch, PR, codebase, and release-readiness reviews with affected-corridor analysis, high-confidence…

    1.9k GitHub stars~4.5k tokensUpdated today
    Auto-check passed
  • Happier CI Stabilize

    happier-dev/happier

    Stabilize failing, flaky, slow, or repeatedly rerun Happier CI and nightlies by collecting all reachable failures from one exact attempt, correcting canonical causes in one batch, simplifying…

    1.9k GitHub stars~2.2k tokensUpdated today
    Auto-check passed
  • Happier Commit Worktree

    happier-dev/happier

    Reconnoiter, classify, validate, group, and commit a large or continuously changing Happier worktree as coherent, human-understandable commits while preserving concurrent work and excluding…

    1.9k GitHub stars~3.9k tokensUpdated today
    Auto-check passed
  • Happier Release

    happier-dev/happier

    Resolve Happier's private release authority and run an exact-SHA release or nightly through cheap admission, verified CI evidence, resumable immutable candidates, and terminal publication proof.

    1.9k GitHub stars~2.4k tokensUpdated today
    Auto-check passed
  • Happier Diagnose

    happier-dev/happier

    Diagnose and explain a Happier runtime, session, daemon, provider (Claude/Codex/OpenCode), authentication, or connectivity incident from logs, structured diagnostics, runtime state, and source…

    1.9k GitHub stars~2.1k tokensUpdated today
    Auto-check passed
  • Happier Implement

    happier-dev/happier

    Implement, change, build, fix, refactor, migrate, or apply accepted review findings in the Happier repositories with canonical-owner discovery, scope-preserving solution economy, TDD, efficient…

    1.9k GitHub stars~4.2k tokensUpdated today
    Auto-check passed

Categories

Questions about Happier Docs

What does Happier Docs do?

Create, update, reorganize, or review Happier internal technical documentation and published user/operator/contributor docs with evidence-backed product truth, exact release status, canonical-page…. Happier Docs is an agent skill from happier-dev/happier. Create, update, reorganize, or review Happier internal technical documentation and published user/operator/contributor docs with evidence-backed product truth, exact release status, canonical-page ownership, human voice, minimal editing, and appropriate validation.

When should I use Happier Docs?

Happier Docs fits situations like: A change affects docs/; behavior that may make existing Happier documentation incomplete.

How do I install Happier Docs in Claude Code?

Run `npx skills add happier-dev/happier --skill happier-docs -a claude-code`. Or copy the skill folder (.agents/skills/happier-docs in happier-dev/happier) into .claude/skills/happier-docs in your project. Claude Code loads it when a task matches its description.

How do I install Happier Docs in Codex?

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

Can I use Happier Docs 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 happier-dev/happier --skill happier-docs -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/happier-docs, .gemini/skills/happier-docs, .github/skills/happier-docs and .opencode/skills/happier-docs in your project.

What does Happier Docs need to run?

Going by SKILL.md and its folder, Happier Docs needs the command-line tools its instructions call (yarn).

Does Happier Docs 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 Happier Docs 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. Review the folder before installing.

What licence does Happier Docs use?

Happier Docs is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Happier Docs use?

About 2.7k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Happier Docs?

Skills that share tags, products or a category with Happier Docs: Diagram Design (cathrynlavery/diagram-design, 45k stars), Simple English (moeru-ai/airi, 50k stars), Get API Docs with chub (andrewyng/context-hub, 14k stars) and Doc Sync (JetBrains/ideavim, 10k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Happier Docs?

happier-dev (a GitHub organization) maintains it in happier-dev/happier, which has 1,883 GitHub stars. The repository holds 28 skills in this directory. The repository was last updated on October 8, 2026.

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