Structure GraphQL-oriented skills with clear activation criteria, references and explicit security-sensitive guidance.
Editorial review checked 2026-10-29 against this instruction snapshot. Supporting scripts and runtime behavior remain outside this editorial review.
This authoring guide describes frontmatter, naming, instruction organization and progressive loading of supporting references. It also covers how generated examples can introduce security risks. Its value is helping maintainers package a narrow repeatable workflow rather than collecting a large undifferentiated prompt.
Authors maintaining Apollo or GraphQL skills and teams documenting a specific internal agent workflow.
A well-formed skill is not automatically effective or safe. Broad activation descriptions can make it appear in unrelated tasks, and permission declarations do not guarantee enforcement by every consuming agent. Source instructions must remain subordinate to the user’s actual request.
Works with Claude Code and similar AI coding assistants that support Agent Skills.
Inspect the pinned source snapshot and its supporting files first. The command selects this skill through the open-source skills CLI. Node.js and agent-specific setup may be required. Installation can download code. Catalog ingestion never executes skill instructions or install scripts.
npx skills add https://github.com/apollographql/skills/tree/9dda1397730370aeb8df4ff8f2015c34c86b5003/skills/skill-creator --skill skill-creatorReview pinned skill folder ↗ · CLI documentation ↗
After source review, use npx skills check and npx skills update to inspect and apply upstream updates. Re-check changed instructions before running them.
Static review only. This is not a security audit or a guarantee of safety.
SKILL.md text only; scripts, dependencies and runtime behavior not audited.
Allowed tools declaration: Read Write Edit Glob Grep. Runtime permissions and network behavior: Unknown.
73/100 · Metadata coverage 100% · Model 1.0
Scores summarize observable discovery signals. Popularity and repository activity apply to the whole repository. Unknown runtime safety earns no certification.
Define the intended task and exclusions, write a concise activation description and separate essential steps from optional references. Add explicit prerequisites and warnings for consequential examples, then retain source links and a small set of representative evaluation prompts.
Validate the package format and referenced files, test activation on relevant and irrelevant prompts and inspect the resulting output against concrete acceptance criteria. Record the evaluated agent and version, and avoid presenting successful format validation as evidence of runtime compatibility.
Related by category; compare scope and dependencies before choosing an alternative.
Explore diagnosing superpowers as a automation & agents workflow from obra/superpowers. Compare its source, maintenance and review signals before choosing it for your agent.
Repository star change: +633 over 24.16 hours. 2026-11-01
Explore using superpowers as a automation & agents workflow from obra/superpowers. Compare its source, maintenance and review signals before choosing it for your agent.
Repository star change: +633 over 24.16 hours. 2026-11-01
Explore 10 andruia skill smith as a automation & agents workflow from sickn33/agentic-awesome-skills. Compare its source, maintenance and review signals before choosing it for your agent.
Repository star change: +68 over 24.16 hours. 2026-11-01
Integrate Apollo Client with React using framework-specific data loading and cache behavior.
Repository star change: +0 over 24.16 hours. 2026-11-01
Explore apollo connectors as a development workflow from apollographql/skills. Compare its source, maintenance and review signals before choosing it for your agent.
Repository star change: +0 over 24.16 hours. 2026-11-01
Model federated GraphQL entities and shared fields with explicit subgraph ownership and composition checks.
Repository star change: +0 over 24.16 hours. 2026-11-01