lore

Each tab says whether it installs commit d1b86cb, the one we checked, or the latest version.

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/specstoryai/getspecstory.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin d1b86cb09f87e6da1015af0213104504389bb198 &&
  git -C "$tmp" sparse-checkout set -- lore &&
  git -C "$tmp" checkout -q d1b86cb09f87e6da1015af0213104504389bb198 &&
  mkdir -p .claude/skills &&
  mkdir .claude/skills/lore &&
  cp -R "$tmp"/lore/. .claude/skills/lore/ &&
  rm -rf "$tmp"

claude plugin marketplace add specstoryai/getspecstory --scope project &&
  claude plugin install lore@specstory --scope project

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/specstoryai/getspecstory.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin d1b86cb09f87e6da1015af0213104504389bb198 &&
  git -C "$tmp" sparse-checkout set -- lore &&
  git -C "$tmp" checkout -q d1b86cb09f87e6da1015af0213104504389bb198 &&
  out="$(mktemp -d)" &&
  cp -R "$tmp"/lore "$out"/lore &&
  (cd "$out" && zip -qr - lore) > lore.zip &&
  rm -rf "$tmp" "$out"

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/specstoryai/getspecstory.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin d1b86cb09f87e6da1015af0213104504389bb198 &&
  git -C "$tmp" sparse-checkout set -- lore &&
  git -C "$tmp" checkout -q d1b86cb09f87e6da1015af0213104504389bb198 &&
  mkdir -p .agents/skills &&
  mkdir .agents/skills/lore &&
  cp -R "$tmp"/lore/. .agents/skills/lore/ &&
  rm -rf "$tmp"

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/specstoryai/getspecstory.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin d1b86cb09f87e6da1015af0213104504389bb198 &&
  git -C "$tmp" sparse-checkout set -- lore &&
  git -C "$tmp" checkout -q d1b86cb09f87e6da1015af0213104504389bb198 &&
  mkdir -p .cursor/skills &&
  mkdir .cursor/skills/lore &&
  cp -R "$tmp"/lore/. .cursor/skills/lore/ &&
  rm -rf "$tmp"

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/specstoryai/getspecstory.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin d1b86cb09f87e6da1015af0213104504389bb198 &&
  git -C "$tmp" sparse-checkout set -- lore &&
  git -C "$tmp" checkout -q d1b86cb09f87e6da1015af0213104504389bb198 &&
  mkdir -p .github/skills &&
  mkdir .github/skills/lore &&
  cp -R "$tmp"/lore/. .github/skills/lore/ &&
  rm -rf "$tmp"

gh skill install specstoryai/getspecstory lore/SKILL.md@d1b86cb09f87e6da1015af0213104504389bb198 --agent github-copilot --scope project

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/specstoryai/getspecstory.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin d1b86cb09f87e6da1015af0213104504389bb198 &&
  git -C "$tmp" sparse-checkout set -- lore &&
  git -C "$tmp" checkout -q d1b86cb09f87e6da1015af0213104504389bb198 &&
  mkdir -p .gemini/skills &&
  mkdir .gemini/skills/lore &&
  cp -R "$tmp"/lore/. .gemini/skills/lore/ &&
  rm -rf "$tmp"

gemini skills install https://github.com/specstoryai/getspecstory.git --path lore --scope workspace

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/specstoryai/getspecstory.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin d1b86cb09f87e6da1015af0213104504389bb198 &&
  git -C "$tmp" sparse-checkout set -- lore &&
  git -C "$tmp" checkout -q d1b86cb09f87e6da1015af0213104504389bb198 &&
  mkdir -p .agents/skills &&
  mkdir .agents/skills/lore &&
  cp -R "$tmp"/lore/. .agents/skills/lore/ &&
  rm -rf "$tmp"

npx skills@1.7.4 add specstoryai/getspecstory --skill lore

From the files and frontmatter at commit d1b86cb. This is how much a skill can do, not whether it is risky.

What it can touch: Shell, network or credentials

• Runs shell commands

  Its instructions or files give the agent commands to run on your computer.

• Reaches the network

  It sends or fetches data over the internet, for example with curl, an HTTP library or a package install.

• Names web addresses

  It mentions outside web addresses the agent may visit. We list them but don't follow them.

• Bundles scripts

  The folder holds code files the agent may run.

  tests/engine.test.mjs

• Pre-approves tools

  Its allowed-tools field lists tools the agent may use without asking you first, in agents that honour it.

  SKILL.md:5

• Adds hooks

  Its frontmatter registers commands that run automatically on agent events for the rest of the session.

  SKILL.md:7

• Touches credentials

  It reads, asks for or contains keys, tokens, passwords or similar secrets.

  scripts/lib/patterns.mjs:187 · tests/engine.test.mjs:586 · tests/engine.test.mjs:589 and 2 more

• Installs more skills

  It tells the agent to install other skills, plugins or tool servers.

  CONTRIBUTING.md:23

• Changes agent settings

  It writes to agent memory or settings files such as CLAUDE.md, AGENTS.md or .claude/settings.json.

  SKILL.md:237 · SKILL.md:458 · AS-BUILT-ARCHITECTURE.md:255

Pattern check: 1 item to review · commit d1b86cb · 27 Oct 2026

• R34 · HighBroad tools pre-approved in allowed-tools

  SKILL.md:5 (opens in a new tab)

  allowed-tools: Bash, Read, Write, AskUserQuestion

We checked every text file in this skill, at commit d1b86cb on 27 Oct 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.

How the check worksReport an incorrect finding

Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.

• Agent Skills specPasses with warnings

  The open format from agentskills.io, held to what the strictest agents enforce, so one folder loads everywhere.

  • Warning

    Fields outside the spec: argument-hint (read by Claude Code and VS Code) and hooks (read by Claude Code). Uploads to the Claude apps and API, and the spec's validator, reject the file; most agents ignore these fields. O1

    Fix: Delete them for a portable skill, or keep them if you only target the agents that read them.

  • Warning

    The body is 528 lines; the spec suggests under 500. B1

    Fix: Move detailed sections into reference files and link to them from SKILL.md.

  • Warning

    The body is about 8,152 tokens (approx.); the spec suggests under 5,000. B2

    Fix: Move detail into reference files that the agent reads only when needed.

  • Note

    The first sentence of the description is 297 characters. Agents shorten long descriptions, so lead with the main job. D8

    Fix: Start with one short sentence that names the job.

  • Note

    Reference files that SKILL.md doesn't link: AGENTS.md, AS-BUILT-ARCHITECTURE.md (linked only from HOW-IT-WORKS.md), CLAUDE.md, HOW-IT-WORKS.md, fixtures/golden/forge-plan.md and 13 more. Anthropic suggests linking every reference file directly from SKILL.md. B4

    Fix: Link each one from SKILL.md and say when to read it.

  • Note

    Reference files over 100 lines with no table of contents at the top: HOW-IT-WORKS.md (321 lines) and fixtures/projC/.specstory/history/2026-05-10_09-00-00Z-where-is-save-implemented.md (134 lines). B5

    Fix: Add a short list of the sections at the top of each.

• Claude CodePasses

  Claude Code reads its own extra fields, ignores unknown ones, and still loads a skill whose frontmatter is broken, without its fields.

  • Note

    The first sentence of the description is 297 characters. Agents shorten long descriptions, so lead with the main job. D8

    Fix: Start with one short sentence that names the job.

  • Note

    The body is 528 lines; the spec suggests under 500. Claude Code's docs say the same. B1

    Fix: Move detailed sections into reference files and link to them from SKILL.md.

  • Note

    The body is about 8,152 tokens (approx.); the spec suggests under 5,000. After compaction Claude Code keeps only the first 5,000 tokens of a skill. B2

    Fix: Move detail into reference files that the agent reads only when needed.

  • Note

    Reference files that SKILL.md doesn't link: AGENTS.md, AS-BUILT-ARCHITECTURE.md (linked only from HOW-IT-WORKS.md), CLAUDE.md, HOW-IT-WORKS.md, fixtures/golden/forge-plan.md and 13 more. Anthropic suggests linking every reference file directly from SKILL.md. B4

    Fix: Link each one from SKILL.md and say when to read it.

  • Note

    Reference files over 100 lines with no table of contents at the top: HOW-IT-WORKS.md (321 lines) and fixtures/projC/.specstory/history/2026-05-10_09-00-00Z-where-is-save-implemented.md (134 lines). B5

    Fix: Add a short list of the sections at the top of each.

• Claude apps & API uploadFails

  Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.

  • Error

    Upload and packaging fail on fields outside the spec: argument-hint and hooks. O1

    Fix: Delete them, and keep your own data under metadata as text values.

  • Note

    The description is 507 characters. The claude.ai Help Center says 200 at most, though Anthropic's API docs and validator allow 1,024. D4

    Fix: If the claude.ai upload refuses it, trim the description to 200 characters.

  • Note

    The body is 528 lines; the spec suggests under 500. Anthropic's guidance says the same. B1

    Fix: Move detailed sections into reference files and link to them from SKILL.md.

  • Note

    The body is about 8,152 tokens (approx.); the spec suggests under 5,000. Anthropic's guidance says the same. B2

    Fix: Move detail into reference files that the agent reads only when needed.

  • Note

    Reference files that SKILL.md doesn't link: AGENTS.md, AS-BUILT-ARCHITECTURE.md (linked only from HOW-IT-WORKS.md), CLAUDE.md, HOW-IT-WORKS.md, fixtures/golden/forge-plan.md and 13 more. Anthropic suggests linking every reference file directly from SKILL.md. B4

    Fix: Link each one from SKILL.md and say when to read it.

  • Note

    Reference files over 100 lines with no table of contents at the top: HOW-IT-WORKS.md (321 lines) and fixtures/projC/.specstory/history/2026-05-10_09-00-00Z-where-is-save-implemented.md (134 lines). B5

    Fix: Add a short list of the sections at the top of each.

• OpenAI (Codex & API)Passes with warnings

  Codex finds SKILL.md by its exact name and needs a description; OpenAI's Skills API checks the frontmatter against the spec and caps uploads.

  • Warning

    Fields outside the spec: argument-hint and hooks. Codex ignores them; OpenAI doesn't say whether its upload accepts them. O1

    Fix: Delete them, or move your own data under metadata as text values.

  • Note

    The first sentence of the description is 297 characters. Agents shorten long descriptions, so lead with the main job. D8

    Fix: Start with one short sentence that names the job.

• VS Code & CopilotPasses

  VS Code reads skills one folder below .github/skills, .claude/skills or .agents/skills and falls back to the folder name when the name is missing or differs; GitHub's Copilot docs require the exact name SKILL.md.

  • Note

    VS Code ignores fields it doesn't support: hooks. O1

    Fix: Delete them unless another agent you target reads them.

43 files