skill-template
An agent skill by muratcankoylan, from muratcankoylan/Agent-Skills-for-Context-Engineering. Tags: developer-tools, documents, strategy.
What it does
Template for creating new Agent Skills for context engineering. Use this template when adding new skills to the collection.
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add muratcankoylan/Agent-Skills-for-Context-Engineering --skill skill-template
Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering
cp -r Agent-Skills-for-Context-Engineering/template ~/.claude/skills/skill-template
Safety box score
Grade A, minimal risk: 5 of 100 risk points, rated 2026-10-19. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This is a documentation-only skill template: it contains guidance for writing other skills and two stub reference files, but no executable code, network actions, or privileged operations. The only real risk is prompt-shaping/instructional content, especially the explicit discussion of system-prompt injection and persona wording.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 0 (none) | No shell commands, scripts, code evaluation, or native executables are present in `SKILL.md` or the reference stubs. |
| Network access | 0 (none) | The files do not download content or send data to remote hosts; the only external references are descriptive placeholders. |
| Filesystem reach | 0 (none) | Nothing in the skill writes, deletes, or reads outside the project; the only paths mentioned are internal `references/` links. |
| Secrets & credentials | 0 (none) | There is no handling of tokens, passwords, key files, `.env` files, browser sessions, or credential prompts. |
| Privilege & persistence | 0 (none) | The skill does not request sudo, service installation, shell startup changes, or other privileged system changes. |
| Instruction hijack surface | 1 (low) | `SKILL.md` explicitly discusses prompt placement and persona framing, e.g. "The description is injected into the system prompt" and "Write in third person," which is prompt-shaping content but not a bypass instruction. |
| Irreversible actions | 0 (none) | The template does not push, deploy, publish, send messages, pay, book, or delete anything. |
| Transparency | 0 (none) | All provided files are plain markdown; there are no binaries, encoded blobs, or runtime-fetched installers. |
Before installing
- Verify any real skill derived from this template removes the stub reference text in `references/` and does not add hidden prompt instructions.
- If adapting it, review the final `SKILL.md` for any added commands, remote fetches, or credential-handling steps before enabling it.
- Keep the template as documentation only; do not treat the placeholder references as operative instructions.
Rated 2026-10-19 by an automated review of 3 files from the skill's repository.
Source
- Repository
- muratcankoylan/Agent-Skills-for-Context-Engineering (all skills from this repository)
- Path
- template/SKILL.md
- Branch
- main
- Updated
- 2026-09-19
Related skills
- context-compression — This skill should be used when long-running agent sessions need context compression, structured summarization, compaction, token-per-task optimization.
- expo-overview — Framework (OSS). Entry point and router for every Expo or EAS task.
- interpreting-culture-index — Interprets Culture Index (CI) surveys, behavioral profiles, and personality assessment data.
- seo-content-brief — Generate competitive SEO content briefs with per-section word counts, competitor scoring, keyword density guidance, and page-type templates.
- site-md — Analyze a project description or site requirements and synthesize a project constitution into SITE.md for the Stitch Build Loop
- bdi-mental-states — This skill should be used when modeling agent mental states with BDI concepts: beliefs, desires, intentions, RDF-to-belief transformations.