What does this skill do, and when should you use it?
This skill is the entrypoint to the Agnostic Prompt Standard (APS) v1.0, whose normative content lives in eight documents under references/ (structure, vocabulary, linting, agentic control, schemas, grammar, logging/privacy, and error taxonomy). Beyond the spec, it ships reusable format and constants examples, a minimal scaffolding template for new skills, and platform adapters covering Claude Code, VS Code + GitHub Copilot, OpenCode, and a generic MCP tool layer. It is essentially a pure-Markdown specification intended to be consumed by both humans and LSP/linter tools, with no runtime dependencies of its own.
- Provides the APS v1.0 normative spec defining structure, vocabulary, grammar, and error taxonomy
- Defines linting and formatting rules that an LSP/linter tool should ingest
- Ships ten example format blocks plus constants examples (JSON, text, CSV) ready to copy and reuse
- Supplies a minimal skill skeleton via the _template/ directory for scaffolding new skills
- Documents platform constants, tool registries, and format contracts for Claude Code, VS Code Copilot, OpenCode, and generic/MCP adapters
- Provides process documents such as build-skill.md for constructing new APS-compliant skills
- A skill author who wants to write portable, cross-platform prompts organized to a consistent structural standard
- A team that wants lint rules and an error taxonomy for prompts so tooling can automatically check prompt quality
- A developer reusing the same prompt spec across Claude Code and VS Code Copilot who needs platform-specific adapter mappings
- An engineer building an MCP tool bridge or subagent architecture who can follow the bundled guides for coordinator/worker interfaces
- Anyone who wants to bootstrap a new spec-compliant skill quickly starting from the _template/ skeleton
- Users who want to install the repo's devcontainer features (bat, flux, gitleaks, etc.) into a container — those are unrelated to this skill
- Users expecting an executable linter or CLI tool bundled with the skill — the scripts/ directory is empty by default; only the specification is provided
How do you install this skill?
- Authorship metadata (Christopher Buckley / chris-buckley repo) conflicts with the host repository jsburckhardt/devcontainer-features, and last_updated is a future date (2026-03-12); verify the true origin before use.
- The normative core references/ documents and lint scripts are absent from evidence or empty placeholders; as shipped, the skill is effectively an entry index and its conformance-checking capability is unproven.
- Repository CI only tests devcontainer features, not this skill; there are no APS-specific tests or third-party execution evidence.
- No declared Chinese-language support or trigger boundaries; semantic invocation may misfire.
- Local filesystem
No install commands are documented for this skill — the host repo README only describes devcontainer features installation, which is unrelated, and says nothing about installing skills under .github/skills/. Reasonable routes are copying the skill directory into your platform's skills folder, or visiting the upstream spec repository at https://github.com/chris-buckley/agnostic-prompt-standard for releases.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/jsburckhardt/devcontainer-features.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/.github/skills/agnostic-prompt-standard" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
Once installed, send your agent any of these to trigger it:
- Rewrite this requirements description into an APS v1.0-conformant prompt using the structure spec and the format-code-changes-full example output
- Check my prompt against the 02-linting-and-formatting spec and list any vocabulary or formatting violations
- Scaffold a new skill for me from the _template/ skeleton that complies with the APS spec
- I'm on VS Code + GitHub Copilot — map the tool names in this prompt per platforms/vscode-copilot/adaptor.md
SKILL.md serves as the entrypoint and is loaded as context: references/ holds the normative spec, assets/ provides reusable format and constants examples, and platforms/ carries non-normative adapter docs. You reference the relevant spec sections (structure, vocabulary, linting) when drafting prompts, copy patterns from the assets examples to produce APS v1.0-conformant output, and for building new skills follow processes/build-skill.md starting from the _template/ scaffold.
What are this skill's strengths and limitations?
- Pure-Markdown spec with no runtime dependencies — any file-reading agent can use it
- Clearly separates normative documents from supporting material, making it suitable as LSP/linter input
- Covers adapters for multiple major platforms (Claude Code, VS Code Copilot, OpenCode, generic/MCP)
- Rich examples: ten format blocks, three constants examples, composites, and authoring guides
- The scripts/ directory is empty — no actual runnable lint or compile tooling is included
- The upstream spec repo (chris-buckley/agnostic-prompt-standard) is separate from the host repo (jsburckhardt/devcontainer-features); version alignment must be checked manually
- No test suite or user-validation evidence; real-world viability of each platform adapter is not proven by the source
- No documented install or usage commands — onboarding requires reading the full spec
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| Agnostic Prompt Standard (APS) v1.0 Skill this page | 46 · Use with care | ★ 38 | 19d ago | MIT |
| Skill Creator | 70 · Strongly recommended | ★ 2.2k | 12d ago | MIT |
| Create New Skills (Meta-Skill) | 62 · Recommended | ★ 1.5k | 8mo ago | — |
| Loki Prompt Optimization Skill | 60 · Recommended | ★ 1.1k | 17d ago | NOASSERTION |
| DeepTutor Skill Creator | 57 · Use with care | ★ 41k | 18d ago | Apache-2.0 |
How did FollowSkills review this skill?
Purely documentation-based skill: no script execution, no external side effects, no sensitive-data handling demands, MIT licensed. However, metadata attributes authorship to Christopher Buckley and points to chris-buckley/agnostic-prompt-standard while the host repo is jsburckhardt's fork; the provenance chain is unverified, and the publisher is unverified. The normative references/ documents were not provided in evidence, so the actual content of 06-logging-and-privacy cannot be confirmed. Deducted for unverifiable attribution and missing core normative material.
SKILL.md is a structurally self-consistent entry document; assets (constant blocks, format contracts) are syntactically uniform and consistently named. But claimed lint/compile capability depends on scripts/ (declared empty by default), the core references/ documents are absent from evidence, and the repository CI tests cover devcontainer features, not this skill. Deducted for missing key-path material and no executable failure-feedback path.
Target scenario is clear (generate, compile, lint APS v1.0-conformant prompts); the entry doc distinguishes normative vs non-normative material and provides multi-platform adapters and a scaffold template. However, trigger conditions, non-fit boundaries, and Chinese-language support are undeclared, and usability depends on references/ content not supplied. Deducted for limited evidence on boundaries and trigger precision.
Good layered information architecture (entry → spec → assets → processes → guides → platform adapters), version metadata (spec_version, framework_revision), template skeleton, and license declared. But last_updated is a future date (2026-03-12), authorship metadata conflicts with the host repository, there is no CHANGELOG or maintenance-responsibility statement, and scripts/ is an empty placeholder. Deducted for metadata credibility flaws and incomplete versioning/governance.
As a prompt-standard framework, its value lies in consistent prompt structure and format contracts; the rich assets of format and constant examples have direct reference value. But it cannot be statically verified that prompts generated under this standard outperform hand-written ones, the normative core (references/) is absent, and output usability is unconfirmed. Deducted for unverifiable core value claim and unproven comparative benefit.
Only internal consistency is checkable (asset naming, version numbers, layout claims match). The spec documents are missing, there are no tests, no third-party execution evidence, and the README badge pointing to external releases cannot be corroborated. Deducted because key claims (spec content, lint capability) are independently unverifiable and evidence types are thin.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →