Agent Builder
shareAI-lab/learn-claude-code
Design and build AI agents for any domain. An agent skill from shareAI-lab/learn-claude-code.
How to write Claude Code agents: example blocks, model choice, least-privilege tools.
Install Writing Agents
$ npx skills add xiaolai/nlpm --skill writing-agents -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install xiaolai/nlpm writing-agents --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/xiaolai/nlpm.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/nlpm/writing-agents .claude/skills/writing-agents && rm -rf skills-srcUse ~/.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/
Install the "writing-agents" agent skill from https://github.com/xiaolai/nlpm/tree/main/skills/nlpm/writing-agents into .claude/skills/writing-agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "writing-agents", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/xiaolai/nlpm/tree/main/skills/nlpm/writing-agentsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add xiaolai/nlpm --skill writing-agents -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install xiaolai/nlpm writing-agents --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/xiaolai/nlpm.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/nlpm/writing-agents .agents/skills/writing-agents && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "writing-agents" agent skill from https://github.com/xiaolai/nlpm/tree/main/skills/nlpm/writing-agents into .agents/skills/writing-agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "writing-agents", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add xiaolai/nlpm --skill writing-agents -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install xiaolai/nlpm writing-agents --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/xiaolai/nlpm.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/nlpm/writing-agents .cursor/skills/writing-agents && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "writing-agents" agent skill from https://github.com/xiaolai/nlpm/tree/main/skills/nlpm/writing-agents into .cursor/skills/writing-agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "writing-agents", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/xiaolai/nlpm.git --path skills/nlpm/writing-agents--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add xiaolai/nlpm --skill writing-agents -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install xiaolai/nlpm writing-agents --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/xiaolai/nlpm.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/nlpm/writing-agents .gemini/skills/writing-agents && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "writing-agents" agent skill from https://github.com/xiaolai/nlpm/tree/main/skills/nlpm/writing-agents into .gemini/skills/writing-agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "writing-agents", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install xiaolai/nlpm writing-agentsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add xiaolai/nlpm --skill writing-agents -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/xiaolai/nlpm.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/nlpm/writing-agents .github/skills/writing-agents && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "writing-agents" agent skill from https://github.com/xiaolai/nlpm/tree/main/skills/nlpm/writing-agents into .github/skills/writing-agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "writing-agents", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add xiaolai/nlpm --skill writing-agents -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install xiaolai/nlpm writing-agents --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/xiaolai/nlpm.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/nlpm/writing-agents .opencode/skills/writing-agents && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "writing-agents" agent skill from https://github.com/xiaolai/nlpm/tree/main/skills/nlpm/writing-agents into .opencode/skills/writing-agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "writing-agents", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
writing-agents- GitHub stars
- 148
- Token cost
- ~3k tokens
- SKILL.md length
- 984 words
- Files
- 1
- Skills in repo
- 15
- Repo updated
- First seen
- Licence
- ISC
At a glance
How to write Claude Code agents: example blocks, model choice, least-privilege tools.
- Works in 7 steps: Example Blocks Make or Break Triggering → Model Selection → Tool Least-Privilege → …
- AI & LLM Engineering work in your project
- SKILL.md covers 1. Example Blocks Make or…, 2. Model Selection, 3. Tool Least-Privilege and 4. Output Format, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Writing Agents is an agent skill from xiaolai/nlpm. How to write Claude Code agents: example blocks, model choice, least-privilege tools.
Its SKILL.md is about 3k 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 AI & LLM Engineering. The repository describes itself as: Natural-Language Programming Manager — scan, lint, and score NL artifacts with Claude-native quality scoring. The licence is ISC.
When your agent uses it
- AI & LLM Engineering work in your project
Example prompts
- “/writing-agents”
Workflow steps
7 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 307328b. 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
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown, xml and yaml).
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 Agents loads about 3k tokens when it runs. Until then it costs about 25 tokens; SKILL.md has 984 words of instructions outside code blocks.
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 xiaolai/nlpm at commit 307328b, republished under its ISC licence (© xiaolai). 984 words, ~3,012 tokens.
Download SKILL.mdSave it as
.claude/skills/writing-agents/SKILL.md (or your agent's skills folder).- name
- writing-agents
- description
- How to write Claude Code agents: example blocks, model choice, least-privilege tools.
- version
- 0.2.0
- user-invocable
- false
Writing Agents
Scope: covers Claude Code agent
.mdfile authoring (Markdown + frontmatter at.claude/agents/). Codex CLI defines agents differently — as[agents.<name>]TOML tables in.codex/config.toml; see [[nlpm:conventions-codex]]. Antigravity subagents are under-documented at this writing; see [[nlpm:conventions-antigravity]]. For multi-agent orchestration, see [[orchestration]]. For plugin architecture, see [[writing-plugins]].
1. Example Blocks Make or Break Triggering
Without <example> blocks, Claude guesses when to dispatch your agent. With them, it pattern-matches against real scenarios.
Target: 1 well-chosen example + 1 "Not for …" sentence, whole description ≤1,200 characters.
The description sits in the Agent tool's text on every turn and is the only thing Claude sees when choosing an agent. Examples therefore stay in the description -- moved into the body, they are invisible to routing -- but every extra example is always-on context. One example that shows the main positive trigger, trigger phrases in the prose, and an explicit exclusion carry the routing signal at a fraction of the tokens.
Example Block Anatomy
<example>
Context: [what the user is doing -- not just "user needs help"]
user: "[realistic user message that should trigger this agent]"
assistant: "[what Claude says when dispatching -- shows the decision logic]"
</example>Bad Example (too vague -- 40% trigger accuracy)
<example>
Context: User needs code review
user: "review my code"
assistant: "I'll use the reviewer agent."
</example>Problems: generic context, generic query, no decision logic shown.
Good Example (specific scenario -- 92% trigger accuracy)
<example>
Context: User just pushed changes to the authentication module and wants feedback before merging
user: "Can you check if the auth changes look good before I create the PR?"
assistant: "I'll dispatch the security-reviewer agent to check the auth changes for vulnerabilities, token handling, and session management best practices."
</example>Why it works: specific context (auth module, pre-PR), realistic query (how users actually talk), decision logic visible (what the agent will check).
One Example, Prose Triggers, One Exclusion
| Part | Purpose | What it carries |
|---|---|---|
| Prose trigger phrases | Breadth | Obvious, edge-case and non-obvious triggers, one short phrase each |
1 <example> | Anchor | The main positive trigger: user asks, assistant dispatches |
| "Not for …" sentence | Boundary | The adjacent request that belongs to a sibling agent or to no agent |
Example for a "performance-profiler" agent:
description: |
Profiles slow endpoints, memory growth and query plans. Use when a request is
slow, memory climbs over time (possible leak), or the user is choosing between
two implementations on speed. Not for fixing the code it measures; it reports
hot spots only.
<example>
Context: User wants to profile their API
user: "Profile the /api/users endpoint, it's slow"
assistant: "I'll dispatch the performance-profiler to trace the /api/users endpoint..."
</example>A second example is allowed when a distinct trigger cannot be said in prose, but it costs context on every turn; nlpm's R09 gives full credit for one.
2. Model Selection
| Task type | Model | Signal words in body | Examples |
|---|---|---|---|
| Mechanical / parsing / formatting / counting | haiku | count, list, extract, format, parse, scan | scanner, parser, formatter, counter, lister |
| Analysis / reasoning / moderate judgment | sonnet | analyze, review, evaluate, summarize, compare | linter, reviewer, extractor, summarizer |
| Complex judgment / orchestration / multi-agent | opus | coordinate, decide, assess, synthesize, architect | QC coordinator, architect, strategy planner |
Quick Heuristic
Count the instruction lines in your agent body. Then check for judgment words.
< 20 instruction lines AND no judgment words → haiku
20-50 instruction lines OR judgment words → sonnet
> 50 instruction lines OR coordination logic → opusJudgment words: evaluate, decide, assess, determine, weigh, prioritize, recommend, judge, infer, synthesize.
Cost Impact
| Model | Relative cost | When to upgrade |
|---|---|---|
| haiku | 1x | Agent produces wrong output on edge cases |
| sonnet | 10x | Agent produces wrong output on easy cases |
| opus | 30x | Agent coordinates other agents or makes architectural decisions |
Rule: start with haiku, upgrade only when output quality requires it.
3. Tool Least-Privilege
Only list tools the agent body actually references. Every extra tool is a potential misuse vector.
Common Mistakes
| Agent type | Common over-grant | Correct tools |
|---|---|---|
| Audit/review agent | Write, Edit, Bash | Read, Glob, Grep |
| Code generator | Read, Grep (unused) | Write, Edit, Bash |
| Orchestrator | Read, Write (does no IO) | Task |
| Scanner | Bash (uses grep) | Grep, Glob, Read |
Tool Reference
| Tool | When to include |
|---|---|
| Read | Agent reads file contents |
| Write | Agent creates new files |
| Edit | Agent modifies existing files |
| Glob | Agent searches for files by pattern |
| Grep | Agent searches file contents |
| Bash | Agent runs shell commands (linters, tests, builds) |
| Task | Agent dispatches sub-agents |
| WebFetch | Agent fetches a URL |
4. Output Format
Every agent MUST define its output format in the body. Without it, output varies between invocations -- making results unparseable by parent agents.
Pattern: Structured Report
## Output Format
### {Section Title}
| Column1 | Column2 | Column3 |
|---------|---------|---------|
| ... | ... | ... |
### Summary
- Total items: {N}
- Issues found: {N}
- Pass/Fail: {verdict}Pattern: Severity-Tagged Findings
## Output Format
For each finding, output:
**[SEVERITY] Finding title**
- File: `path/to/file`
- Line: {N}
- Finding: {description}
- Fix: {concrete suggestion}
Severity levels: CRITICAL > HIGH > MEDIUM > LOW > INFOPattern: Pass/Fail Gate
## Output Format
Final line must be exactly one of:
- `PASS: All checks passed`
- `WARN: {N} warnings found (see above)`
- `FAIL: {N} errors found (see above)`5. System Prompt Structure
Order matters. Claude reads top-to-bottom and front-loads early instructions.
The Five Sections
## Mission
[1-2 sentences: what this agent does and WHY it exists]
## Instructions
1. [First step]
2. [Second step]
3. [Third step]
...
## Boundaries
- Do NOT [thing that would be harmful]
- Do NOT [thing that's out of scope]
- If [ambiguous situation], then [explicit resolution]
## Output Format
[Exact template -- see section 4 above]
## Error Handling
- If no files found: report "No matching files" and exit
- If tool fails: report the error and continue with remaining work
- If scope is unclear: analyze the narrower interpretationShow full SKILL.md (411 more words)Show less
Section Sizing
| Section | Target lines | Over-budget signal |
|---|---|---|
| Mission | 2-3 | More than one paragraph |
| Instructions | 5-15 | More than 20 numbered steps |
| Boundaries | 3-7 | More than 10 "Do NOT" items |
| Output Format | 5-15 | Defining more than 3 output sections |
| Error Handling | 3-5 | More than 5 error cases |
Total agent body: aim for 25-45 lines. Over 60 lines means the agent is doing too much -- split it.
6. Worked Example
Before (score 43/100)
---
name: code-checker
description: Check code
model: opus
tools: [Read, Write, Edit, Bash, Grep, Glob, Task]
---You are a code checker. Check the user's code for issues.
Look at the files and find problems. Report what you find.Problems (each scored line is a row in the nlpm:scoring Agents table):
- R09 -- zero
<example>blocks in the description: unreliable triggering (-15) - R09 -- no "Not for" clause: nothing tells routing what to rule out (-5)
- R10 -- opus for a review task that sonnet handles (-5)
- R11 -- Write, Edit, Bash, Task declared but no body step uses them (-3 each, -12)
- R11 -- a review agent declares Write and Edit (-10)
- R12 -- no output format: inconsistent results (-10)
- Description has 0 trigger phrases and no "Use when..." (not scored for agents; R04 is a skills row, but routing still suffers)
- No boundaries and no error handling (not scored; they cause scope creep and silent failures)
Total: -57, so 100 - 57 = 43.
After (score 100/100)
---
name: code-checker
description: |
Static analysis agent — checks code for bugs, type errors, and anti-patterns.
Use when reviewing code quality, running pre-commit checks, validating changes
before PR, or scanning a module suspected of a production defect. Not for style
issues (defer to the linter) or for fixing code; it reports only.
<example>
Context: User just finished implementing a new feature and wants a quality check
user: "Check the auth module for any bugs before I push"
assistant: "I'll dispatch the code-checker agent to analyze src/auth/ for bugs, type errors, and anti-patterns."
</example>
model: sonnet
tools: [Read, Glob, Grep]
---## Mission
Analyze source code files for bugs, type errors, and anti-patterns.
Produce a structured report with severity-tagged findings.
## Instructions
1. Use Glob to discover files matching the target pattern
2. Use Read to examine each file
3. Use Grep to cross-reference imports and usage patterns
4. For each finding, classify severity and provide a concrete fix
5. Produce the output report
## Boundaries
- Do NOT modify any files (read-only analysis)
- Do NOT run shell commands
- Do NOT report style issues (defer to linter)
- If no target pattern specified, analyze all files in src/
## Output Format
For each finding:
**[SEVERITY] Finding title**
- File: `path/to/file`
- Line: {N}
- Finding: {description}
- Fix: {concrete fix}
Final line:
- `PASS: No issues found`
- `WARN: {N} warnings found`
- `FAIL: {N} errors found`
## Error Handling
- If no files match the pattern: report "No matching files for pattern: {X}"
- If a file cannot be read: skip it and note in the reportChanges made (one per problem above):
- R09: added 1
<example>block in the description (+15) - R09: added a "Not for" clause -- style issues and fixing code (+5)
- R10: opus -> sonnet (analysis-tier task: reasoning, not orchestration) (+5)
- R11: tools 7 -> 3; Glob, Read and Grep are each named by an instruction step (+12)
- R11: dropped Write and Edit from a read-only review agent (+10)
- R12: defined the output format (+10)
- Description: 0 -> 6 trigger phrases and a "Use when" sentence (not scored)
- Added boundaries and error handling (not scored)
Total: +57, so 43 + 57 = 100.
7. Common Mistakes
| Mistake | Impact | Fix |
|---|---|---|
| No examples | 40% trigger accuracy | Add 1 specific scenario example + a "Not for" sentence |
| 3-4 examples in the description | Always-on context on every turn | Keep the best one; move trigger phrases into the prose |
| Opus for mechanical work | 30x cost for same result | Use haiku for parsing, sonnet for analysis |
| All tools granted | Agent writes when it should only read | List only tools the body references |
| No output format | Different format each run | Define exact output template |
| Body over 60 lines | Agent is doing too much | Split into focused sub-agents |
| "Be thorough" in body | Meaningless filler | Replace with specific instructions |
| No error handling | Silent failures | Add 3-5 error cases with resolution |
© xiaolai, ISC. 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 skills/nlpm/writing-agents of xiaolai/nlpm.
Open the folder on GitHubat commit 307328b
Compare with similar skills
Writing Agents 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Writing Agents this skillxiaolai/nlpm | 148 | — | ~3k | Automated safety check: Pass | ISC | |
| Agent BuildershareAI-lab/learn-claude-code | 78k | 5 repos | ~1.2k | Automated safety check: Pass | MIT | |
| Add Uint Supportpytorch/pytorch | 104k | 2 repos | ~2.3k | Automated safety check: Pass | Custom licence | |
| LLM Benchmarking with lm-evaluation-harnessOrchestra-Research/AI-Research-SKILLs | 13k | 8 repos | ~3k | Automated safety check: Pass | MIT | |
| Segment Anything Model GuideOrchestra-Research/AI-Research-SKILLs | 13k | 8 repos | ~3.3k | Automated safety check: Pass | MIT | |
| 1passwordtrpc-group/trpc-agent-go | 1.9k | 14 repos | ~656 | Automated safety check: Pass | Apache-2.0 |
Similar skills
Add Uint Support
pytorch/pytorch
Add unsigned integer (uint) type support to PyTorch operators by updating ATDISPATCH macros.
LLM Benchmarking with lm-evaluation-harness
Orchestra-Research/AI-Research-SKILLs
Runs lm-evaluation-harness to benchmark language models on academic suites such as MMLU, GSM8K and HumanEval, compare models and track training checkpoints.
Segment Anything Model Guide
Orchestra-Research/AI-Research-SKILLs
Guide to using Meta's Segment Anything Model for zero-shot image segmentation with point, box or mask prompts, or automatic mask generation.
1password
trpc-group/trpc-agent-go
Set up and use 1Password CLI (op). An agent skill from trpc-group/trpc-agent-go.
Planning With Files
jarrodwatts/claude-code-config
Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge storage.
More from xiaolai/nlpm
All 15 skills in this repoConventions
xiaolai/nlpm
Universal NL conventions: SKILL.md open spec, AGENTS.md, vague quantifiers, naming.
Conventions Antigravity
xiaolai/nlpm
Antigravity and Gemini CLI artifact schemas: .gemini/ paths, extensions, hooks.
Conventions Codex
xiaolai/nlpm
Codex CLI artifact schemas: config.toml, .codex-plugin, skills, hooks, AGENTS.md.
Orchestration
xiaolai/nlpm
Multi-agent workflow patterns: parallel dispatch, pipelines, QC gates, retries.
Patterns
xiaolai/nlpm
NL artifact anti-patterns: vague quantifiers, bare prohibitions, oversized skills.
Scoring
xiaolai/nlpm
100-point NL artifact rubric: penalty tables per artifact type, calibration cases.
Related
Categories
Questions about Writing Agents
What does Writing Agents do?
How to write Claude Code agents: example blocks, model choice, least-privilege tools. Writing Agents is an agent skill from xiaolai/nlpm. How to write Claude Code agents: example blocks, model choice, least-privilege tools.
When should I use Writing Agents?
Writing Agents fits situations like: AI & LLM Engineering work in your project.
How do I install Writing Agents in Claude Code?
Run `npx skills add xiaolai/nlpm --skill writing-agents -a claude-code`. Or copy the skill folder (skills/nlpm/writing-agents in xiaolai/nlpm) into .claude/skills/writing-agents in your project. Claude Code loads it when a task matches its description.
How do I install Writing Agents in Codex?
Run `npx skills add xiaolai/nlpm --skill writing-agents -a codex`. Or copy the skill folder (skills/nlpm/writing-agents in xiaolai/nlpm) into .agents/skills/writing-agents in your project. Codex loads it when a task matches its description.
Can I use Writing Agents 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 xiaolai/nlpm --skill writing-agents -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-agents, .gemini/skills/writing-agents, .github/skills/writing-agents and .opencode/skills/writing-agents in your project.
What does Writing Agents need to run?
SKILL.md names no scripts, command-line tools or credentials: Writing Agents is instructions for the agent only.
Does Writing Agents 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 Agents 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 Agents use?
Writing Agents is published under the ISC licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Writing Agents use?
About 3k tokens (SKILL.md is roughly 12k 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 Agents?
Skills that share tags, products or a category with Writing Agents: Agent Builder (shareAI-lab/learn-claude-code, 78k stars), Add Uint Support (pytorch/pytorch, 104k stars), LLM Benchmarking with lm-evaluation-harness (Orchestra-Research/AI-Research-SKILLs, 13k stars) and Segment Anything Model Guide (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Writing Agents?
xiaolai (a GitHub user) maintains it in xiaolai/nlpm, which has 148 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on October 9, 2026.
Source: xiaolai/nlpm on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.