- verify:skills:cli — the authoritative validator is now a GUARANTEED step in `local:gate` and CI, not a best-effort hand-off. It resolves the CLI itself (an installed one at 2.1.233+, else a pinned `npx -y`), so both tiers run the same script and cannot drift. `verify:skills` keeps skipping when the CLI is absent, which is right for `validate`: fast, offline, no Claude Code required. - skill-manifest: the 1,536-char listing-entry cap covers `description` + `when_to_use` together; checking the description alone passed an over-cap entry. `when_to_use` is now parsed, validated and counted, with boundary tests at 1,536/1,537. - verify-skills: report the budget as *this repo's contribution*. The real listing budget is shared with bundled skills and the contributor's own ~/.claude/skills, none of which is visible from here, so the number was claiming more than it measured. - skill-eval: a negative case now means "no skill OF THIS REPO'S fired". It failed on any Skill invocation, so a contributor with an unrelated global skill got a false failure about their environment rather than these skills. - docs/architecture + local-dev: the Node backend runner gets its `@inspector/core` alias from `clients/web/tsup.runner.config.ts`, not from Vite. The old text sent runner work to the wrong config. - local-dev: the tarball does not ship "only each client's build/" — the allowlist also carries `clients/web/dist`, `clients/web/static` and the install helper. States the invariant that actually matters instead. - issue-triage: the test for needing triage is "no board card". Adding "and no milestone" would skip the approved-but-unboarded case the same section then handles. Also corrected the `$M` note: the lookup is `--state all`, so closed issues DO have entries — `isopen` is about the invariants, not the lookup. - issue-create: replaced "all five" with a per-version table. Steps 3 and 6 (milestone, Priority) do not exist for v1, so the old list opened with a rule the same skill later tells you to violate. Signed-off-by: cliffhall <cliff@futurescale.com>
176 lines
6.7 KiB
JavaScript
Executable file
176 lines
6.7 KiB
JavaScript
Executable file
#!/usr/bin/env node
|
|
// Durable guard for `.claude/skills/**/SKILL.md` (#2163).
|
|
//
|
|
// `AGENTS.md` is loaded in full on every turn, so its rules are unconditionally
|
|
// present. A skill is conditional — its body loads only when it is invoked — so
|
|
// if a skill stops being reachable we lose behavior SILENTLY, and nothing in the
|
|
// normal workflow surfaces that. This is the check that does.
|
|
//
|
|
// What it asserts, cheapest first:
|
|
// 1. Every SKILL.md's frontmatter parses the way Claude Code parses it. This
|
|
// is the whole-class failure: malformed YAML (or a fence that is not the
|
|
// first line) loads the body with EMPTY metadata, so `/name` still works —
|
|
// a manual spot check passes — while the description the model matches
|
|
// against is gone and the skill never auto-fires again.
|
|
// 2. Every skill declares its invocation mode explicitly, so the set that has
|
|
// to fire on its own is knowable by reading the files rather than inferred.
|
|
// 3. Every model-invoked skill has committed eval cases, including negatives.
|
|
// Cases are run by `npm run skills:eval`, which needs the Claude CLI and is
|
|
// therefore NOT in the gate; the cases existing is what this checks.
|
|
// 4. The skill LISTING stays inside its recorded character budget. Claude Code
|
|
// truncates the listing when it overflows, dropping the least-invoked
|
|
// entries first — which are exactly the model-invoked skills.
|
|
//
|
|
// It additionally runs `claude plugin validate` when that CLI is on PATH. That
|
|
// is the authoritative parse, but it cannot be a requirement: the CLI is absent
|
|
// in CI and on a contributor's machine, and a guard that skips itself wherever
|
|
// it actually runs is worse than one that reimplements the check.
|
|
|
|
import { readFileSync, readdirSync, existsSync, statSync } from "node:fs";
|
|
import { spawnSync } from "node:child_process";
|
|
import path from "node:path";
|
|
import { fileURLToPath } from "node:url";
|
|
import {
|
|
compareVersions,
|
|
parseClaudeVersion,
|
|
PLUGIN_VALIDATE_MIN_VERSION,
|
|
parseSkill,
|
|
validateEvalCases,
|
|
listingCost,
|
|
LISTING_BUDGET,
|
|
} from "./lib/skill-manifest.mjs";
|
|
|
|
const ROOT = path.resolve(path.dirname(fileURLToPath(import.meta.url)), "..");
|
|
const DEFAULT_SKILLS_DIR = path.join(ROOT, ".claude", "skills");
|
|
|
|
/** Directory names under `.claude/skills` that contain a SKILL.md. */
|
|
export function skillDirs(
|
|
dir,
|
|
{ readdir = readdirSync, stat = statSync } = {},
|
|
) {
|
|
return readdir(dir)
|
|
.filter((n) => !n.startsWith("."))
|
|
.filter((n) => stat(path.join(dir, n)).isDirectory())
|
|
.sort();
|
|
}
|
|
|
|
function main(argv = process.argv.slice(2)) {
|
|
// An explicit directory is the seam the fixture tests drive; without it this
|
|
// guard could only ever be exercised against the repo's own (green) skills,
|
|
// so it could stop enforcing anything while every unit test stayed green.
|
|
const override = argv[0];
|
|
const SKILLS_DIR = override ? path.resolve(override) : DEFAULT_SKILLS_DIR;
|
|
const failures = [];
|
|
|
|
if (!existsSync(SKILLS_DIR)) {
|
|
console.error(
|
|
`verify:skills — ${path.relative(ROOT, SKILLS_DIR)} does not exist.`,
|
|
);
|
|
process.exit(1);
|
|
}
|
|
|
|
const dirs = skillDirs(SKILLS_DIR);
|
|
if (dirs.length === 0) {
|
|
console.error("verify:skills — no skills found; the skill set is gone.");
|
|
process.exit(1);
|
|
}
|
|
|
|
const parsed = [];
|
|
for (const dir of dirs) {
|
|
const file = path.join(SKILLS_DIR, dir, "SKILL.md");
|
|
if (!existsSync(file)) {
|
|
failures.push(`${dir}: no SKILL.md`);
|
|
continue;
|
|
}
|
|
const skill = parseSkill(dir, readFileSync(file, "utf8"));
|
|
for (const e of skill.errors) failures.push(`${dir}/SKILL.md: ${e}`);
|
|
if (skill.errors.length > 0) continue;
|
|
parsed.push(skill);
|
|
|
|
if (skill.modelInvoked) {
|
|
const evalsFile = path.join(SKILLS_DIR, dir, "evals", "evals.json");
|
|
if (!existsSync(evalsFile)) {
|
|
failures.push(
|
|
`${dir}: model-invoked skills need committed eval cases at evals/evals.json`,
|
|
);
|
|
continue;
|
|
}
|
|
let cases;
|
|
try {
|
|
cases = JSON.parse(readFileSync(evalsFile, "utf8"));
|
|
} catch (e) {
|
|
failures.push(`${dir}/evals/evals.json: not valid JSON — ${e.message}`);
|
|
continue;
|
|
}
|
|
for (const e of validateEvalCases(dir, cases)) {
|
|
failures.push(`${dir}/evals/evals.json: ${e}`);
|
|
}
|
|
}
|
|
}
|
|
|
|
const cost = listingCost(parsed);
|
|
if (cost > LISTING_BUDGET) {
|
|
failures.push(
|
|
`this repo contributes ${cost} chars to the skill listing, over its recorded ` +
|
|
`budget of ${LISTING_BUDGET}. Tighten a description, or raise the budget ` +
|
|
"deliberately in scripts/lib/skill-manifest.mjs — but note the real listing " +
|
|
"budget is SHARED with bundled skills and the contributor's own " +
|
|
"~/.claude/skills, none of which is visible from here.",
|
|
);
|
|
}
|
|
|
|
if (failures.length > 0) {
|
|
console.error(`verify:skills — ${failures.length} problem(s):\n`);
|
|
for (const f of failures) console.error(" " + f);
|
|
console.error("\nSee AGENTS.md → Maintaining the skills.");
|
|
process.exit(1);
|
|
}
|
|
|
|
const modelInvoked = parsed.filter((s) => s.modelInvoked).map((s) => s.name);
|
|
console.log(
|
|
`verify:skills — OK: ${parsed.length} skills, ${modelInvoked.length} model-invoked ` +
|
|
`(${modelInvoked.join(", ")}); this repo's listing share ${cost}/${LISTING_BUDGET} chars.`,
|
|
);
|
|
|
|
if (override) return;
|
|
|
|
// The authoritative parse, when it is available — strictly a bonus. An older
|
|
// CLI does not have `plugin validate` and exits nonzero on it as an unknown
|
|
// command, which would fail the MANDATORY gate for a contributor whose only
|
|
// sin is not having upgraded (Copilot). So gate on the version that
|
|
// introduced it and skip below it, reserving a failure for a validator that
|
|
// actually rejected the skills.
|
|
const probe = spawnSync("claude", ["--version"], { encoding: "utf8" });
|
|
if (probe.error || probe.status !== 0) {
|
|
console.log(
|
|
"verify:skills — `claude` CLI not usable here; skipped `claude plugin validate`.",
|
|
);
|
|
return;
|
|
}
|
|
const version = parseClaudeVersion(probe.stdout ?? "");
|
|
if (
|
|
version === null ||
|
|
compareVersions(version, PLUGIN_VALIDATE_MIN_VERSION) < 0
|
|
) {
|
|
console.log(
|
|
`verify:skills — \`claude\` ${version?.join(".") ?? "(unreadable version)"} predates ` +
|
|
`${PLUGIN_VALIDATE_MIN_VERSION.join(".")}; skipped \`claude plugin validate\`.`,
|
|
);
|
|
return;
|
|
}
|
|
const res = spawnSync("claude", ["plugin", "validate", ".claude/skills"], {
|
|
cwd: ROOT,
|
|
stdio: "inherit",
|
|
});
|
|
if (res.status !== 0) {
|
|
console.error("\nverify:skills — `claude plugin validate` failed.");
|
|
process.exit(1);
|
|
}
|
|
}
|
|
|
|
if (
|
|
process.argv[1] &&
|
|
path.resolve(process.argv[1]) === fileURLToPath(import.meta.url)
|
|
) {
|
|
main();
|
|
}
|