Borrowing it
Nothing to install: this file belongs to grahamton/merchGent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/grahamton/merchGent/main/.opencode/skills/skill-creator/SKILL.mdgit clone --depth 1 https://github.com/grahamton/merchGentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/grahamton/merchgent/skill-creator)<a href="https://agentmods.dev/skills/grahamton/merchgent/skill-creator"><img src="https://agentmods.dev/badge/skills/grahamton/merchgent/skill-creator.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00014 | $0.00653 |
| Opus 5 | $0.00007 | $0.00327 |
| Sonnet 5 | $0.00003 | $0.00131 |
| Haiku 4.5 | $0.00001 | $0.00065 |
Grade A, and why
skill-creator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill creator helps create other skills that are self-buildable.
The best way to use it is after a user already executed a flow and says: create a skill for this. Alternatively, if the user asks for a skill to be created, suggest they do the task first and ask for skill creation at the end.
This should trigger this scaffold:
- If the user needed to configure things, create a
.env.examplewithout credentials and include all required variables. - Ask the user if they want to store credentials. If yes, write them to a
.envfile in the skill, and suggest rotating keys later. - Always add a
.gitignorein the skill that ignores.env, and verify.envis not tracked. - If the user needed to interact with an API and you created scripts, add reusable scripts under
scripts/. - New skills should explain how to use the
scripts/and that.env.exampledefines the minimum config. - Skills should state that they infer what they can do from the available config.
Trigger phrases (critical)
The description field is how Claude decides when to use your skill. Include 2-3 specific phrases that should trigger it.
Bad example: "Use when working with content"
Good examples: "Use when user mentions 'content pipeline', 'add to content database', or 'schedule a post'" "Triggers on: 'rotate PDF', 'flip PDF pages', 'change PDF orientation'"
Quick validation:
- Contains at least one quoted phrase
- Uses "when" or "triggers"
- Longer than ~50 characters
Frontmatter template
---
name: my-skill
description: |
[What it does in one sentence]
Triggers when user mentions:
- "[specific phrase 1]"
- "[specific phrase 2]"
- "[specific phrase 3]"
---
Quick Usage (Already Configured)
Create a new skill folder
mkdir -p .opencode/skills/<skill-name>
Minimum scaffold files
SKILL.mdscripts/.env.env.example(use this to guide the minimum config).gitignore(ignore.env)
.env (credentials + config)
- Use
.env.exampleto document required credentials or external setup. - Do not include any real credentials in
.env.example.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 102 lines · 14 tokens per session scan A 36378ea012f5
skill-creator is a skill published in the GitHub repository grahamton/merchGent (0 stars, last pushed 4mo ago), licensed MIT. It adds 14 tokens to every session and 653 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
video-research
Teaches Claude how to effectively use the 28 video-research-mcp tools. Activates when working with video analysis, deep research, content extraction, web search, or knowledge store via the video-research MCP server.
ffmpeg-production
FFmpeg video/audio processing — conversion, scaling, compression, trimming, concatenation, AI post-processing. Not for audio ducking/voice mixing (tts-production) or Remotion rendering.
video-production
Orchestrate multi-clip AI video projects — style anchors, chaining patterns, frame-level QA, montage assembly. Not for video analysis, research, provider settings, or FFmpeg encoding.
gemini-visualize
Generates interactive HTML visualizations (concept maps, evidence networks, knowledge graphs) from Gemini analysis results. Triggers automatically after /gr:video, /gr:research, /gr:analyze.
mlflow-traces
Use when working with MLflow traces: debugging via MCP tools, analyzing performance, logging feedback, writing custom scorers/evaluations, or cleaning up trace data.
tts-production
Produces voiceover audio via ElevenLabs TTS API. Activates for TTS generation, voice tuning, audio ducking, or multilingual narration — not for voice AI agents, transcription, or music.