write-skill
/write-skill
Use when someone asks for a new skill, a slash command or a reusable agent recipe for working on this repo, or to fix a skill that is wrong or out of date. Keeps every skill usable by Claude Code and Codex alike, links it into .agents/skills and lists it in AGENTS.md. Not for the plugin, which ships no skills.
- Author
- serionist ↗
- Repository
- claude-session-restore ↗
- Licence
- MIT
- Last repository change
- 28.10.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 28.10.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Use when someone asks for a new skill, a slash command or a reusable agent recipe for working on this repo, or to fix a skill that is wrong or out of date. Keeps every skill usable by Claude Code and Codex alike, links it into .agents/skills and lists it in AGENTS.md. Not for the plugin, which ships no skills.
Original author description
Use when someone asks for a new skill, a slash command or a reusable agent recipe for working on this repo, or to fix a skill that is wrong or out of date. Keeps every skill usable by Claude Code and Codex alike, links it into .agents/skills and lists it in AGENTS.md. Not for the plugin, which ships no skills.
How it works
- Steps
- Done means
- Never
- Traps
SKILL.md preview
---
name: write-skill
description: >-
Use when someone asks for a new skill, a slash command or a reusable agent recipe for working on this repo, or to fix
a skill that is wrong or out of date. Keeps every skill usable by Claude Code and Codex alike, links it into
.agents/skills and lists it in AGENTS.md. Not for the plugin, which ships no skills.
---
# Write a skill
Skills here serve the people and agents who work on this repo, in Claude Code and Codex alike; the plugin users
install has none. A skill is a recipe an agent follows: steps in a fixed order, a definition of done, hard nevers, and
the traps already paid for. Deterministic work belongs in a script the skill calls, not in prose the agent has to get
right.
## Steps
1. **Check it is needed.** Search `.claude/skills/` for a skill that already covers the request; change that one
rather than adding a near-duplicate.
2. **Create the folder** `.claude/skills/<name>/` with `SKILL.md`. The folder name equals `name`: lowercase letters,
digits and hyphens, at most 64 characters.
3. **Frontmatter** holds `name` and `description`, and nothing else. The description puts the trigger first
("Use when ..."), names the requests that should fire it, and stays within 1,024 characters. Write it as a `>-`
block, as every skill here does: a `: ` or ` #` in a plain value is invalid YAML for the tools that parse it
strictly.
4. **Body,** at most about 200 lines, in the house shape (`start-work` is the model):
- what the skill is for, in two or three sentences;
- **Steps:** numbered, each naming the file, tool or command it touches. A scope (a diff, a review, a branch) is
named as the git command that resolves it, never in words;
- **Done means:** what must be true when the agent stops;
- **Never:** the hard rules;
- **Traps,** once there are some: what broke, when, the guard.
A file the skill reads beside `SKILL.md` (such as `lenses.md`) sits in its folder and is named in the step that
uses it.
5. **Scripts** a skill needs live in `tools/`, Node's standard library only, with tests in `tools/<name>.test.ts`, and
are named by their path from the repo root (`node tools/<name>.ts`). If the work is deterministic, write the script
first.
6. **Link it for Codex:** `node tools/setup.ts link <name>`. It writes `.agents/skills/<name>` into git's index as a
symlink to the skill, so the commit has the link on any machine, a Windows clone without Developer Mode included.
Commit the link with the skill.
7. **List it** in `AGENTS.md`, in the skills line under How a change lands: its name and when to use it.
8. **Run `node tools/gate.ts quick`.** It checks the frontmatter (only `name` and `description`, the name equal to the
folder, the description set, "Use when ..." first, within 1,024 characters), that `AGENTS.md` names the skill, and
that each skill has its link and each link leads to a skill. The rest is review.
## Done means
- The skill fires on the requests in its description and on nothing unrelated.
- Every path, tool and command it names exists.
- `.agents/skills/<name>` links to it, `AGENTS.md` names it, and gate quick passes.
## Never
- Claude-only syntax in a skill: `!` shell injection, `$ARGUMENTS`, `${CLAUDE_SKILL_DIR}`, `${CLAUDE_PROJECT_DIR}`,
or `allowed-tools`.
- A skill that restates a rule instead of pointing at it: name the section of `AGENTS.md` or `REVIEW.md`.
- A rule kept only in a skill's prose when a check could keep it: add the check to `tools/gate.ts`, with its test.
- `ln -s` from Git Bash, or a copied folder, for the link: use `node tools/setup.ts link`.
## Traps
| What broke | When | The guard |
|---|---|---|
| A skill's folder name differed from its `name`, and the tool dropped the skill without a word | another repo, 2026-10 | gate quick compares them |
| Git Bash's `ln -s` copied the folder instead of linking it, and Codex read a stale copy | another repo, 2026-10 | `setup.ts link`; gate quick reads each link's mode from git's index |
| A description with `: ` in it read fine in Claude Code and was invalid YAML in Codex | another repo, 2026-10 | Every description is a `>-` block; gate quick refuses a plain one with `: ` |
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · serionist/claude-session-restore | 90 | MIT |
| hassan-mohiddin/freeflow | 100 | MIT |
| jelvodev/yaap | 100 | MIT |
| cao-partners-au/olc-agent-skills-starter | 100 | MIT |
| wilbeibi/claude-toolkit | 100 | MIT |
| NormandErwan/claude-casebook | 98 | BSD-3-Clause |
| hassan-mohiddin/freeflow | 96 | MIT |
| LandonSchropp/agent-toolkit | 90 | MIT |
| pwguler/skills | 82 | MIT |
Database snapshot: 13.11.2026 · package version 68b4e53fb49e (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100create-skill
Create a new agent skill (or Claude Code slash command) from a plain-language description, using live spec fetching, pattern research, and an approval-gated blueprint before any files are written. Use whenever the user wants to build, scaffold, or author a new skill, subagent… - 100skills-creator
Create plugin components (skills, agents, commands, full plugins) and decide skill vs agent architecture. TRIGGER WHEN: creating, adding or scaffolding a new skill, agent, command or plugin ("new skill", "new agent", "new plugin", "skills-creator"). DO NOT TRIGGER WHEN: auditing… - 100skill-creator
Create new AI agent skills for Claude Code, Codex, and Cursor. Use when asked to create a skill, add a new agent capability, or set up a slash command. - 100new-skill-creator
Scaffold a new Agent Skill end-to-end into a skills repo you maintain (folder, SKILL.md, optional protocol.yon for dual-doc skills, tri-runtime links for Claude Code + Codex + the shared .agents/ dir, commit and push). The maintainer's authoring loop — it links your own clone… - 100create-command
Create a new slash command for Claude Code. Guides the user through defining the command name, what it does, and generates the markdown file in .claude/commands/. Use when the user says 'create a command', 'new command', 'add a slash command', 'I want a shortcut for', or wants… - 100edit-tool
Creates, modifies, and orchestrates Claude Code tools (skills, agents, scripts). Use when user requests creating, updating, improving, or editing any Claude Code extension — skills, sub-agents, slash commands, script wrappers. Triggers include "create/make/new…