voyage/lib/skills/skill-lint.mjs

#!/usr/bin/env node
// lib/skills/skill-lint.mjs
// The skill form check (contract S1). Model-free; `npm test` runs it over
// every skills/<name>/SKILL.md through tests/lib/skill-lint.test.mjs.
//
// It follows Claude Code's own skill fields (code.claude.com/docs/en/skills.md,
// "Frontmatter reference"), not the narrower portable spec: Voyage needs
// fields such as `user-invocable` that the portable spec rejects.
//
// Rules (error codes):
//   SKILL_NO_FRONTMATTER            no leading --- block
//   SKILL_YAML_HAZARD               a line real YAML would misread (unquoted ": ",
//                                   " #", tab, unclosed quote, leading indicator)
//   SKILL_UNKNOWN_FIELD             a field Claude Code does not know (it would be
//                                   ignored silently)
//   SKILL_NAME_MISMATCH / _FORM     name = directory name; kebab-case, <= 64,
//                                   no "anthropic" / "claude"
//   SKILL_DESC_MISSING / _TOO_LONG  description present, <= 1 024 characters
//   SKILL_DESC_NO_USE_WHEN          the description says "Use when ..."
//   SKILL_DESC_NOT_THIRD_PERSON     no I / we / you in the description
//   SKILL_MODEL_INVOCATION_DISABLED disable-model-invocation set true: the skill
//                                   could not be preloaded into a helper nor
//                                   called by a command ("commands are the trunk")
//   SKILL_TOO_LONG                  SKILL.md is 500 lines or more
//   SKILL_MISSING_HEADING / _ORDER  the fixed headings, in order
//   SKILL_ENFORCED_BY_VAGUE         each "Enforced by" bullet names a check
//                                   (a backticked path) or says "prose only"
//   SKILL_REF_MISSING               a linked or backticked file does not exist
//   SKILL_SHELL_INJECTION           !`cmd` or a ```! block: Voyage advises users
//                                   to switch skill shell execution off
//   SKILL_SELF_EXEMPTION            a skill that exempts itself
//
// Exemptions live in EXEMPTIONS below, with a reason, never in a skill.
//
// CLI: node lib/skills/skill-lint.mjs [--root <plugin root>] [--json]
//   exit 0 = every skill passes · 1 = findings · 2 = could not run
//
// Adapted from addyosmani/agent-skills @9d0c60d, scripts/lib/skill-lint.js
// (rules, held-in-the-linter exemptions, fenced-code stripping) and
// docs/skill-anatomy.md - MIT, Copyright (c) 2025 Addy Osmani. Reimplemented,
// no code copied.

import { existsSync, readdirSync, readFileSync, statSync } from 'node:fs';
import { dirname, join, resolve } from 'node:path';
import { fileURLToPath } from 'node:url';
import { readFrontmatterFields, splitFile } from './skill-frontmatter.mjs';
import { isMain } from '../util/is-main.mjs';

/** Claude Code's skill frontmatter fields (skills.md, Frontmatter reference). */
export const KNOWN_FIELDS = new Set([
  'name', 'description', 'when_to_use', 'argument-hint', 'arguments',
  'disable-model-invocation', 'user-invocable', 'allowed-tools', 'disallowed-tools',
  'model', 'effort', 'context', 'agent', 'background', 'hooks', 'paths', 'shell',
  'metadata', 'license', 'compatibility',
]);

/** The fixed headings of a Voyage skill (S1), in this order. */
export const REQUIRED_HEADINGS = ['Overview', 'When to use', 'Process', 'Red flags', 'Enforced by', 'Credits'];

export const MAX_DESCRIPTION = 1024;
export const MAX_LINES = 500;

/**
 * Exemptions, held here and only here: skill name -> { codes, reason }.
 * Empty by design; an entry needs a reason a reviewer can judge.
 * @type {Map<string, {codes: string[], reason: string}>}
 */
export const EXEMPTIONS = new Map();

const TRUE_WORDS = /^(true|yes|on|1)$/i;
const FIRST_SECOND_PERSON = /\b(you|your|yours|you're|we|we're|our|ours|us|me|my|mine)\b/i;
const FIRST_PERSON_I = /(^|[^A-Za-z.])(I|I'm|I'll|I've)(?![A-Za-z.])/;
const PATH_PREFIXES = ['lib/', 'hooks/', 'agents/', 'commands/', 'templates/', 'docs/', 'skills/', 'scripts/'];

function err(code, message, line) { return { code, message, ...(line ? { line } : {}) }; }

/** Body lines with fenced code blocks blanked (their headings and links do not count). */
function unfenced(body) {
  let inFence = false;
  return body.split('\n').map((l) => {
    if (/^\s*(```|~~~)/.test(l)) { inFence = !inFence; return ''; }
    return inFence ? '' : l;
  });
}

/** The lines under one `## heading`, up to the next `## `. */
function section(lines, heading) {
  const start = lines.findIndex((l) => l.trim() === `## ${heading}`);
  if (start < 0) return null;
  const out = [];
  for (let i = start + 1; i < lines.length && !/^##\s/.test(lines[i]); i++) out.push(lines[i]);
  return out;
}

/**
 * Lint one skill directory.
 * @param {string} skillDir   path to skills/<name>
 * @param {{pluginRoot?: string}} [opts]  root that backticked plugin paths resolve against
 * @returns {{ name: string, errors: object[], warnings: object[] }}
 */
export function lintSkill(skillDir, opts = {}) {
  const dirName = skillDir.split(/[\\/]/).filter(Boolean).pop();
  const pluginRoot = opts.pluginRoot || resolve(skillDir, '..', '..');
  const file = join(skillDir, 'SKILL.md');
  const errors = [];
  const warnings = [];
  if (!existsSync(file)) return { name: dirName, errors: [err('SKILL_NO_FRONTMATTER', 'SKILL.md is missing')], warnings };
  const text = readFileSync(file, 'utf8');

  // Frontmatter
  const fm = readFrontmatterFields(text);
  if (fm.error) errors.push(err('SKILL_NO_FRONTMATTER', fm.error, 1));
  for (const h of fm.hazards) errors.push(err('SKILL_YAML_HAZARD', h.message, h.line));
  const f = fm.fields;
  for (const [key, v] of Object.entries(f)) {
    if (!KNOWN_FIELDS.has(key)) errors.push(err('SKILL_UNKNOWN_FIELD', `"${key}" is not a Claude Code skill field; it would be ignored`, v.line));
  }

  // Name
  const name = f.name ? String(f.name.value) : dirName;
  if (f.name && name !== dirName) errors.push(err('SKILL_NAME_MISMATCH', `name "${name}" must equal the directory name "${dirName}"`, f.name.line));
  if (!/^[a-z0-9]+(-[a-z0-9]+)*$/.test(name) || name.length > 64 || /anthropic|claude/.test(name)) {
    errors.push(err('SKILL_NAME_FORM', `name "${name}": kebab-case, at most 64 characters, without "anthropic" or "claude"`, f.name && f.name.line));
  }

  // Description
  const d = f.description;
  const desc = d ? String(Array.isArray(d.value) ? d.value.join(' ') : d.value).trim() : '';
  if (!desc) errors.push(err('SKILL_DESC_MISSING', 'a description is required: it is how Claude decides to use the skill'));
  else {
    if (desc.length > MAX_DESCRIPTION) errors.push(err('SKILL_DESC_TOO_LONG', `description is ${desc.length} characters (max ${MAX_DESCRIPTION})`, d.line));
    if (!/\bUse when\b/.test(desc)) errors.push(err('SKILL_DESC_NO_USE_WHEN', 'the description must say when to use the skill: "Use when ..."', d.line));
    if (FIRST_SECOND_PERSON.test(desc) || FIRST_PERSON_I.test(desc)) {
      errors.push(err('SKILL_DESC_NOT_THIRD_PERSON', 'write the description in the third person (no I / we / you)', d.line));
    }
  }

  // Invocation: no Voyage skill is closed to the model.
  const dmi = f['disable-model-invocation'];
  if (dmi && TRUE_WORDS.test(String(dmi.value).trim())) {
    errors.push(err('SKILL_MODEL_INVOCATION_DISABLED',
      'disable-model-invocation is true: no helper could preload the skill and no command could call it', dmi.line));
  }

  // Self-declared exemption (frontmatter or body)
  if (/lint-exempt/i.test(text)) errors.push(err('SKILL_SELF_EXEMPTION', 'a skill may not exempt itself; exemptions live in EXEMPTIONS in lib/skills/skill-lint.mjs'));

  // Size
  // A file that ends in a newline has no line after it (findings-schema counts the same way).
  const lineCount = text.endsWith('\n') ? text.split('\n').length - 1 : text.split('\n').length;
  if (lineCount >= MAX_LINES) errors.push(err('SKILL_TOO_LONG', `SKILL.md has ${lineCount} lines (must stay under ${MAX_LINES}); move detail to a linked file`));

  // Body: headings, enforcement, references, shell injection
  const split = splitFile(text);
  const bodyLines = unfenced(split.ok ? split.body : text);
  const headings = bodyLines.filter((l) => /^##\s/.test(l)).map((l) => l.replace(/^##\s+/, '').trim());
  const positions = [];
  for (const h of REQUIRED_HEADINGS) {
    const at = headings.indexOf(h);
    if (at < 0) errors.push(err('SKILL_MISSING_HEADING', `missing "## ${h}"`));
    else positions.push(at);
  }
  if (positions.some((p, i) => i > 0 && p < positions[i - 1])) {
    errors.push(err('SKILL_HEADING_ORDER', `the headings must come in this order: ${REQUIRED_HEADINGS.join(', ')}`));
  }

  const enforced = section(bodyLines, 'Enforced by');
  if (enforced) {
    const bullets = enforced.filter((l) => /^\s*[-*]\s/.test(l));
    if (bullets.length === 0) errors.push(err('SKILL_ENFORCED_BY_VAGUE', '"Enforced by" lists no check: name one, or say "prose only"'));
    for (const b of bullets) {
      if (!/`[^`]+`/.test(b) && !/prose only/i.test(b)) {
        errors.push(err('SKILL_ENFORCED_BY_VAGUE', `"${b.trim().slice(0, 70)}": name the check (a backticked path) or say "prose only"`));
      }
    }
  }

  const fullBody = split.ok ? split.body : text;
  if (/!`[^`]+`/.test(fullBody) || /^\s*```!/m.test(fullBody)) {
    errors.push(err('SKILL_SHELL_INJECTION', 'shell injection (!`cmd` or a ```! block) runs on load; Voyage advises users to turn it off, so a skill may not depend on it'));
  }

  // A credit bullet that names another repository at a commit ("owner/repo
  // @abc1234, `skills/tdd/SKILL.md`") cites a path in THAT repository; its
  // backticked paths are not looked up here. Every other line is.
  const external = new Set();
  for (let i = 0; i < bodyLines.length; i++) {
    if (!/^\s*[-*]\s/.test(bodyLines[i])) continue;
    let j = i + 1;
    while (j < bodyLines.length && /^\s{2,}\S/.test(bodyLines[j]) && !/^\s*[-*]\s/.test(bodyLines[j])) j++;
    if (/[\w.-]+\/[\w.-]+ @[0-9a-f]{7,40}\b/.test(bodyLines.slice(i, j).join(' '))) for (let k = i; k < j; k++) external.add(k);
  }
  const refs = new Set();
  for (const [i, l] of bodyLines.entries()) {
    for (const m of l.matchAll(/\]\(([^)\s#]+)(#[^)]*)?\)/g)) {
      if (!/^[a-z]+:/.test(m[1])) refs.add(JSON.stringify(['skill', m[1]]));
    }
    if (external.has(i)) continue;
    for (const m of l.matchAll(/`([^`\s]+)`/g)) {
      const p = m[1].replace(/^\$\{CLAUDE_PLUGIN_ROOT\}\//, '');
      if (PATH_PREFIXES.some((x) => p.startsWith(x)) && /\.[a-z]+$/.test(p) && !/[{}*<>]/.test(p)) refs.add(JSON.stringify(['plugin', p]));
    }
  }
  for (const r of refs) {
    const [base, p] = JSON.parse(r);
    const abs = base === 'skill' ? join(skillDir, p) : join(pluginRoot, p);
    if (!existsSync(abs)) errors.push(err('SKILL_REF_MISSING', `${p} does not exist (${base === 'skill' ? 'relative to the skill' : 'relative to the plugin root'})`));
  }

  // Exemptions held in the check
  const ex = EXEMPTIONS.get(name);
  const kept = ex ? errors.filter((e) => !ex.codes.includes(e.code)) : errors;
  return { name, errors: kept, warnings };
}

/** Lint every skills/<name>/ under a plugin root. */
export function lintSkillsRoot(pluginRoot) {
  const dir = join(pluginRoot, 'skills');
  const skills = {};
  if (!existsSync(dir)) return { skills };
  for (const name of readdirSync(dir).sort()) {
    const p = join(dir, name);
    if (!statSync(p).isDirectory()) continue;
    skills[name] = lintSkill(p, { pluginRoot });
  }
  return { skills };
}

// ---- CLI ----

if (isMain(import.meta.url)) {
  const args = process.argv.slice(2);
  const at = args.indexOf('--root');
  const root = resolve(at >= 0 ? args[at + 1] || '' : join(dirname(fileURLToPath(import.meta.url)), '..', '..'));
  const json = args.includes('--json');
  if (!existsSync(root) || !existsSync(join(root, 'skills'))) {
    process.stderr.write(`skill-lint: not measured: no skills/ directory under ${root}\n`);
    process.exit(2);
  }
  const r = lintSkillsRoot(root);
  const bad = Object.values(r.skills).filter((s) => s.errors.length);
  if (json) process.stdout.write(`${JSON.stringify(r, null, 2)}\n`);
  else {
    for (const s of Object.values(r.skills)) {
      process.stdout.write(`${s.errors.length ? 'FAIL' : 'ok  '} ${s.name}\n`);
      for (const e of s.errors) process.stdout.write(`     ${e.code}${e.line ? ` (line ${e.line})` : ''}: ${e.message}\n`);
    }
    process.stdout.write(`${Object.keys(r.skills).length} skill(s), ${bad.length} with findings\n`);
  }
  process.exit(bad.length ? 1 : 0);
}


/**
 * Which commands and agents ask for each skill ("the commands are the trunk").
 * Asked for = an agent's `skills:` list holds `voyage:<name>` or `<name>`, or a
 * command or agent file names `voyage:<name>` in its text. A bare word in prose
 * is not a request. Returns { <skill>: ['agents/x.md', 'commands/y.md', ...] }.
 */
export function findSkillUsers(pluginRoot) {
  const dir = join(pluginRoot, 'skills');
  const names = existsSync(dir) ? readdirSync(dir).filter((n) => existsSync(join(dir, n, 'SKILL.md'))).sort() : [];
  const users = Object.fromEntries(names.map((n) => [n, []]));
  for (const sub of ['agents', 'commands']) {
    const d = join(pluginRoot, sub);
    if (!existsSync(d)) continue;
    for (const f of readdirSync(d).filter((x) => x.endsWith('.md')).sort()) {
      const text = readFileSync(join(d, f), 'utf8');
      const listed = readFrontmatterFields(text).fields.skills;
      const preload = listed && Array.isArray(listed.value) ? listed.value.map((v) => String(v).replace(/^voyage:/, '')) : [];
      for (const n of names) {
        const named = new RegExp(`(^|[^A-Za-z0-9_-])voyage:${n}(?![A-Za-z0-9_-])`).test(text);
        if (preload.includes(n) || named) users[n].push(`${sub}/${f}`);
      }
    }
  }
  return users;
}