README: skills as one list

CHANGELOG.md

@@ -2,6 +2,7 @@
 
 ## Unreleased
 
+- The README lists skills as one bulleted list instead of a table plus a section per skill. `scripts/check.mjs` checks for the list entry.
 - The skills no longer download and run an installer. If `jam` is missing, they ask you to install it from jam.dev/cli. Addresses the remote-code-execution audit finding on `jam-proof` and `jam-annotate`.
 - `jam-annotate` and the `jam-fix` proof step write the Jam payload to a file and run `jam create jam @payload.json`, so user and page text never reaches a shell argument.
 - `jam-fix` and `jam-to-e2e` treat Jam content (transcript, logs, network bodies, page text, comments) as evidence, not instructions.

CONTRIBUTING.md

@@ -47,7 +47,7 @@ Then run the skill on a real task in at least one agent and say which one in the
 
 - One skill per pull request. Maintainers may ship a coordinated release of several in one.
 - Add a line under **Unreleased** in [CHANGELOG.md](./CHANGELOG.md).
-- A new skill also needs a card in [README.md](./README.md). CI fails without one.
+- A new skill also needs an entry in the Skills list in [README.md](./README.md). CI fails without one.
 
 ## Releasing (maintainers)
 

README.md

@@ -27,28 +27,10 @@ A Jam is a recording of what happened on screen, with the console logs, network
 
 ## Skills
 
-| Skill | You say | You get |
-| --- | --- | --- |
-| [jam-fix](#jam-fix) | "fix this jam.dev link" | the root cause with evidence, and the fix when you ask |
-| [jam-proof](#jam-proof) | "record a Jam showing it works" | a Jam of the change working, console and network attached |
-| [jam-annotate](#jam-annotate) | "mark what's broken and file it" | a screenshot Jam with boxes, arrows and redactions |
-| [jam-to-e2e](#jam-to-e2e) | "write an e2e test for this Jam" | a test in your own runner: guards a flow, or fails on a bug until it is fixed |
-
-### jam-fix
-
-Reads the recording's console errors, failed requests, user steps, frames and transcript, then writes a diagnosis with the evidence for it. Changes code only when you ask.
-
-### jam-proof
-
-Records the change working and hands back a Jam link for the pull request. Headless Chrome by default: it records the page, not your screen.
-
-### jam-annotate
-
-Turns a screenshot into a Jam that points at the problem: boxes, arrows, notes, redactions and blurs, with the retina math done right.
-
-### jam-to-e2e
-
-Turns a Jam into steps and a test in the project's own runner and language, whatever it is, with first-class guidance for Playwright and [tester-army/e2e](https://github.com/tester-army/e2e). A Jam of a flow becomes a test that guards it. A Jam of a bug becomes a failing test, so the fix has something to turn green.
+- [jam-fix](./skills/jam-fix/SKILL.md): "Fix this jam.dev link." Reads the recording's **console errors**, **failed requests**, **user steps**, **frames** and **transcript**, then writes the **root cause with evidence**. Changes code only when you ask.
+- [jam-proof](./skills/jam-proof/SKILL.md): "Record a Jam showing it works." Records the change working and hands back a **Jam link for the pull request**, with **console** and **network** attached. Headless Chrome by default: it records the page, not your screen.
+- [jam-annotate](./skills/jam-annotate/SKILL.md): "Mark what's broken and file it." Turns a screenshot into a Jam that points at the problem: **boxes**, **arrows**, **notes**, **redactions** and **blurs**, with the retina math done right.
+- [jam-to-e2e](./skills/jam-to-e2e/SKILL.md): "Write an e2e test for this Jam." Turns a Jam into a test in **your own runner and language**, with first-class guidance for **Playwright** and [tester-army/e2e](https://github.com/tester-army/e2e). A Jam of a flow becomes a test that **guards it**. A Jam of a bug becomes a **failing test**, so the fix has something to turn green.
 
 ## Requirements
 

scripts/check.mjs

@@ -51,7 +51,7 @@ for (const dir of skillDirs) {
     if (description.length > 1024) fail(`${skillPath}: description is ${description.length} chars, max 1024`);
   }
   if (!existsSync(join("skills", dir, "agents", "openai.yaml"))) fail(`${dir}: missing agents/openai.yaml`);
-  if (!readme.includes(`### ${dir}\n`)) fail(`${dir}: missing "### ${dir}" card in README.md`);
+  if (!readme.includes(`- [${dir}](./skills/${dir}/SKILL.md): `)) fail(`${dir}: missing "- [${dir}](./skills/${dir}/SKILL.md): " entry in README.md`);
   if (dir.startsWith("jam-")) {
     const feedback = src.match(/\n## Send feedback to Jam\n[\s\S]*?(?=\n## |$)/)?.[0];
     if (!feedback) fail(`${skillPath}: missing "## Send feedback to Jam" section; copy it from another jam-* skill`);

scripts/check.test.mjs

@@ -18,7 +18,7 @@ function fixture(t, frontmatter = "name: sample-skill\ndescription: A useful ski
   };
   write(skillPath, `---\n${frontmatter}\n---\n# Sample skill\n`);
   write("skills/sample-skill/agents/openai.yaml", "interface: {}\n");
-  write("README.md", "### sample-skill\n");
+  write("README.md", "- [sample-skill](./skills/sample-skill/SKILL.md): x\n");
   for (const file of [".claude-plugin/plugin.json", ".codex-plugin/plugin.json", ".cursor-plugin/plugin.json", "gemini-extension.json"]) {
     write(file, '{"version":"1.0.0"}\n');
   }