New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Writing Skills

by speakeasy-api in speakeasy-api/gram

A skill your agent uses when adding, editing, or reviewing an agent skill in this repo (.agents/skills/), when new guidance needs to reach every supported harness (.claude, .codex, .opencode…

AGPL-3.0Auto-check passedAgent Workflows

Install Writing Skills

skills CLI
$ npx skills add speakeasy-api/gram --skill writing-skills -a claude-code

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

GitHub CLI
$ gh skill install speakeasy-api/gram writing-skills --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/speakeasy-api/gram.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/writing-skills .claude/skills/writing-skills && 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
writing-skills
GitHub stars
273
Token cost
~878 tokens
SKILL.md length
445 words
Files
1
Skills in repo
39
Repo updated
First seen
Licence
AGPL-3.0

At a glance

A skill your agent uses when adding, editing, or reviewing an agent skill in this repo (.agents/skills/), when new guidance needs to reach every supported harness (.claude, .codex, .opencode…

  • Works in 4 steps: Baseline per the eval loop below, then… → Run mise run skills:sync — creates the… → Do not add a manual skills table to… → …
  • Reviewing an agent skill in this repo (.agents/skills/)
  • SKILL.md covers Mechanics, Frontmatter, Body shape and Eval loop (required), plus 2 more sections
  • Calls mise

What it does

Writing Skills is an agent skill from speakeasy-api/gram. Use when adding, editing, or reviewing an agent skill in this repo (.agents/skills/), when new guidance needs to reach every supported harness (.claude, .codex, .opencode, .cursor), or when deciding whether repeated agent failures should become a skill. Triggers: "add a skill", "write a skill", "SKILL.md", "skills:sync".

Its SKILL.md is about 880 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 Agent Workflows, covering Skill authoring. The repository describes itself as: Securely scale AI usage across your organization. A single stack to Connect, Secure, Observe and Distribute agents, MCPs, and Skills within your company. The licence is AGPL-3.0.

When your agent uses it

  • Reviewing an agent skill in this repo (.agents/skills/)
  • New guidance needs to reach every supported harness (.claude
  • Deciding whether repeated agent failures should become a skill

Example prompts

  • “add a skill”
  • “write a skill”
  • “SKILL.md”
  • “/writing-skills”

Workflow steps

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

  1. Baseline per the eval loop below, then author .agents/skills//SKILL.md — kebab-case, verb-first name (writing-skills, not skill-creation).
  2. Run mise run skills:sync — creates the symlinks in .claude/skills/, .codex/skills/, .opencode/skills/, .cursor/skills/ and prunes stale…
  3. Do not add a manual skills table to CLAUDE.md; harnesses discover skills from the synced directories and each skill's frontmatter.
  4. Commit the skill and the symlinks together.

What it can do on your machine

Read from SKILL.md and the folder at commit 1378037. 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:

    • mise

    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

Writing Skills loads about 878 tokens when it runs. Until then it costs about 84 tokens; SKILL.md has 445 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~84
When it runs · the whole SKILL.md, loaded when a task matches
~878

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 speakeasy-api/gram at commit 1378037, republished under its AGPL-3.0 licence (© speakeasy-api). 445 words, ~878 tokens.

Download SKILL.mdSave it as .claude/skills/writing-skills/SKILL.md (or your agent's skills folder).
name
writing-skills
description
Use when adding, editing, or reviewing an agent skill in this repo (.agents/skills/), when new guidance needs to reach every supported harness (.claude, .codex, .opencode, .cursor), or when deciding whether repeated agent failures should become a skill. Triggers: "add a skill", "write a skill", "SKILL.md", "skills:sync".

Writing repo skills

Skills are agent-facing reference docs in .agents/skills/<name>/SKILL.md, symlinked into each supported harness's dotfolder. Core principle: a skill is only as good as a cold agent's ability to act on it — validate with fresh-context subagents performing the real workflow, not by rereading it yourself.

Mechanics

  1. Baseline per the eval loop below, then author .agents/skills/<name>/SKILL.md — kebab-case, verb-first name (writing-skills, not skill-creation).
  2. Run mise run skills:sync — creates the symlinks in .claude/skills/, .codex/skills/, .opencode/skills/, .cursor/skills/ and prunes stale ones. Never hand-create the links; you will miss a harness.
  3. Do not add a manual skills table to CLAUDE.md; harnesses discover skills from the synced directories and each skill's frontmatter.
  4. Commit the skill and the symlinks together.

Frontmatter

name + description only. The description is triggering conditions ONLY — third person, starts "Use when …", packed with the symptoms, synonyms, commands, and error strings an agent would match on. Never summarize the skill's workflow there: agents follow the summary and skip the body.

Body shape

Succinct reference, not narrative: overview with the core principle → quick-reference table → per-workflow detail → common mistakes. Target well under 1000 words. One excellent example beats many. Make only claims you have verified by running the commands, and record observed failure modes with exact error text — hypothetical caveats age badly, empirical ones survive review.

Show full SKILL.md (230 more words)Show less

Eval loop (required)

Baseline first: watch an agent attempt the task WITHOUT the skill and record the failure verbatim. No baseline failure ⇒ no skill needed.

  1. Write the minimal skill addressing those observed failures.
  2. Dispatch a fresh-context subagent with no prior knowledge. It must perform a REAL instance of the workflow using only the skill — consulting fallback docs counts as a documentation failure — and return structured feedback: VERDICT (ship/no-ship), RATING /10, ANSWERS, CONFUSIONS quoting the text at fault, SUGGESTED EDITS.
  3. Fold the feedback in; repeat with a new subagent each round until one returns ship-as-is (9+/10) with no load-bearing confusions.

Vary rounds between do-the-task and adversarial trap questions; live environments surface what desk-checking cannot. Edits after the ship verdict also get a round — one-line additions included.

Vendored skills

Every skill an agent should have is committed under .agents/skills/ and linked into each harness by mise run skills:sync. Third-party skills are copied in and committed the same way; there is no installer that fetches them.

Common mistakes

  • Hand-symlinking one harness dir and missing the other three — mise skills:sync owns the links.
  • Description that summarizes the procedure — agents act on it and never read the body.
  • Caveats invented at the desk instead of failures observed in a run — evaluators refute them.
  • Leaning on plugin or private docs — this repo is public and other harnesses lack them; skills must be self-contained.

© speakeasy-api, AGPL-3.0. 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/writing-skills of speakeasy-api/gram.

Open the folder on GitHubat commit 1378037

Compare with similar skills

Writing Skills 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.

Writing Skills compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Writing Skills this skillspeakeasy-api/gram273—~878Automated safety check: PassAGPL-3.0
Skill CreatorAzure/azqr79589 repos~8.2kAutomated safety check: PassApache-2.0
Claude Code Skill Developer Guidediet103/claude-code-infrastructure-showcase10k11 repos~3.5kAutomated safety check: PassMIT
Darwin Skill Optimizeralchaincyf/darwin-skill6.2k1 repos~4.7kAutomated safety check: PassMIT
Claude Code Command Developmentanthropics/claude-plugins-official38k10 repos~4.8kAutomated safety check: PassApache-2.0
Claude Code Plugin Structureanthropics/claude-plugins-official38k10 repos~3.4kAutomated safety check: PassApache-2.0

Similar skills

  • Skill Creator

    Azure/azqr

    Official

    Create new skills, modify and improve existing skills, and measure skill performance.

    795 GitHub starsUsed in 89 repos~8.2k tokens
    Agent WorkflowsAuto-check passed

  • Claude Code Skill Developer Guide

    diet103/claude-code-infrastructure-showcase

    A guide to creating and managing Claude Code skills with auto-activation: skill-rules.json triggers, hooks, enforcement levels, YAML frontmatter and progressive disclosure.

    10k GitHub starsUsed in 11 repos~3.5k tokens
    Agent WorkflowsAuto-check passed

  • Darwin Skill Optimizer

    alchaincyf/darwin-skill

    Scores SKILL.md files on a nine-dimension rubric, then improves them in a keep-or-revert loop with independent judge agents, test prompts, git history and human checkpoints.

    6.2k GitHub starsUsed in 1 repo~4.7k tokens
    Agent WorkflowsAuto-check passed

  • Claude Code Command Development

    anthropics/claude-plugins-official

    Official

    Explains how to write Claude Code slash commands: Markdown files with YAML frontmatter, arguments, file references, bash context and interactive prompts.

    38k GitHub starsUsed in 10 repos~4.8k tokens
    Agent WorkflowsAuto-check passed

  • Claude Code Plugin Structure

    anthropics/claude-plugins-official

    Official

    Explains the directory layout, plugin.json manifest and component organization of a Claude Code plugin, including auto-discovery and portable paths.

    38k GitHub starsUsed in 10 repos~3.4k tokens
    Agent WorkflowsAuto-check passed

  • Skill Release Gate

    rohitg00/ai-engineering-from-scratch

    Evaluates an Agent Skill bundle before release for structure, trigger quality, artifact improvement, script correctness, safety, installed-tree integrity and host portability.

    66k GitHub stars~1k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from speakeasy-api/gram

All 39 skills in this repo

  • Gram Playwright CLI

    speakeasy-api/gram

    A skill your agent uses when automating the Speakeasy dashboard in a browser, capturing screenshots, inspecting pages.

    273 GitHub stars~3.4k tokensUpdated today
    Auto-check passed

  • Transactional Email

    speakeasy-api/gram

    A skill your agent uses when adding, changing, restyling, reviewing, validating, or previewing a Speakeasy transactional email, in Go or in LMX/MJML — a template<name.go, a TemplateKey constant, a…

    273 GitHub stars~4.7k tokensUpdated today
    Auto-check passed

  • Admin Shadcn

    speakeasy-api/gram

    A skill your agent uses when adding, changing, or styling UI in client/admin (the Speakeasy admin dashboard) that touches shadcn/ui — a button, dialog, table, sidebar, badge, select, tabs, tooltip…

    273 GitHub stars~1k tokensUpdated today
    Auto-check passed

  • Authoring Platform MCP Skills

    speakeasy-api/gram

    A skill your agent uses when adding, editing, reviewing, testing, or locating a reviewed skill distributed with the Platform MCP plugin; triggers include "Platform MCP skill", "platformmcpskills"…

    273 GitHub stars~2.2k tokensUpdated today
    Auto-check passed

  • Clickhouse

    speakeasy-api/gram

    A skill your agent uses when changing or reviewing Speakeasy ClickHouse schemas, migrations, queries, inserts, access principals, bootstrap SQL, Cloud compatibility, partial migration failures, or…

    273 GitHub stars~3.2k tokensUpdated today
    Auto-check passed

  • Feature Flag

    speakeasy-api/gram

    A skill your agent uses when gating a feature behind a flag, dogfooding or gradually rolling out a change, choosing between productfeatures and PostHog feature flags, adding or checking a product…

    273 GitHub stars~2.6k tokensUpdated today
    Auto-check passed

Categories

Questions about Writing Skills

What does Writing Skills do?

A skill your agent uses when adding, editing, or reviewing an agent skill in this repo (.agents/skills/), when new guidance needs to reach every supported harness (.claude, .codex, .opencode…. Writing Skills is an agent skill from speakeasy-api/gram.cursor), or when deciding whether repeated agent failures should become a skill.

When should I use Writing Skills?

Writing Skills fits situations like: reviewing an agent skill in this repo (.agents/skills/); new guidance needs to reach every supported harness (.claude; deciding whether repeated agent failures should become a skill.

How do I install Writing Skills in Claude Code?

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

How do I install Writing Skills in Codex?

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

Can I use Writing Skills 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 speakeasy-api/gram --skill writing-skills -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/writing-skills, .gemini/skills/writing-skills, .github/skills/writing-skills and .opencode/skills/writing-skills in your project.

What does Writing Skills need to run?

Going by SKILL.md and its folder, Writing Skills needs the command-line tools its instructions call (mise).

Does Writing Skills 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 Writing Skills 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 Writing Skills use?

Writing Skills is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Writing Skills use?

About 878 tokens (SKILL.md is roughly 3.5k 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 Writing Skills?

Skills that share tags, products or a category with Writing Skills: Skill Creator (Azure/azqr, 795 stars), Claude Code Skill Developer Guide (diet103/claude-code-infrastructure-showcase, 10k stars), Darwin Skill Optimizer (alchaincyf/darwin-skill, 6.2k stars) and Claude Code Command Development (anthropics/claude-plugins-official, 38k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Writing Skills?

speakeasy-api (a GitHub organization) maintains it in speakeasy-api/gram, which has 273 GitHub stars. The repository holds 39 skills in this directory. The repository was last updated on October 9, 2026.

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