holocron/plugins/kyberforge/.apm/skills/factory-audit/scripts/lib-checks-skill.sh

#!/usr/bin/env bash
# lib-checks-skill.sh — SOURCED, never executed.
#
# skill-audit's structural check suite: everything in its validate.sh that is
# NOT the ADR-0020 shared boundary resolver, lifted verbatim and split at the
# resolver's markers. validate.sh reassembles
#
#     $KYBERFORGE_SKILL_PREAMBLE_PY
#     $KYBERFORGE_RESOLVER_PY        (from lib-boundary-resolver.sh)
#     $KYBERFORGE_SKILL_BODY_PY
#
# in that order — the order the resolver block sat in the original file — and
# feeds the result to python3, so every check runs against the same names it
# always did.
#
# The dimension vocabulary, the message wording and the PASS/FAIL/SUGGESTION/
# INFO tiers here are skill-audit's and are deliberately NOT reconciled with
# lib-checks-agent.sh's. The two suites disagree on purpose: a skill body is
# loaded into the caller's context, an agent body becomes the system prompt of
# a fresh one, so ADR-0020 gives skills a body word budget and agents none.
#
# Consumed by: validate.sh, skill mode.
# shellcheck shell=bash
# shellcheck disable=SC2034

kyberforge_skill_preflight() {
  # PyYAML is a HARD dependency, not a nice-to-have. The description VALUE has to
  # be measured after YAML folding is resolved, and the hand-rolled reader that
  # used to stand in for PyYAML disagreed with it across the 400-character FAIL
  # boundary — same description, two verdicts, depending on which reader ran.
  # Refusing to start is the only honest option; the repo's jq / apm / vale
  # dependencies are declared the same way.
  # Check the interpreter separately from the library: `python3 -c` fails the same
  # way whether python3 is missing or PyYAML is, and reporting the wrong missing
  # dependency sends the reader to install the wrong thing.
  if ! command -v python3 > /dev/null 2>&1; then
    echo "Error: python3 is required but was not found on PATH." >&2
    echo "  Why: skipping the ADR-0020 description, body and boundary-target gates would be a vacuous pass." >&2
    echo "  Fix: install python3 (pre-commit itself is a Python application, so it is almost certainly already present)." >&2
    # Exit 2, the never-ran tier: no check ran, so this is not a findings result.
    # lib-provenance-*.sh has always exited 2 here; this matches it.
    exit 2
  fi

  if ! python3 -c 'import yaml' > /dev/null 2>&1; then
    echo "Error: PyYAML is required but is not importable by python3." >&2
    echo "  Why: skipping the ADR-0020 description, body and boundary-target gates would be a vacuous pass." >&2
    echo "  Fix: python3 -m pip install PyYAML   (or your distro's python3-yaml package)." >&2
    # Exit 2, the never-ran tier: a missing hard dependency is not a findings result.
    exit 2
  fi
}

IFS='' read -r -d '' KYBERFORGE_SKILL_PREAMBLE_PY <<'KYBERFORGE_SKILL_PREAMBLE' || true
import sys
import os
import re
import glob

import yaml

# Output is UTF-8 for the same reason input is: under LC_ALL=C the streams
# default to ASCII, and this script's own message text carries em dashes (the
# ADR-0020 boundary SUGGESTION is one). Pinning only the reads moved the crash
# from the read to the write — a UnicodeEncodeError raised while PRINTING, after
# every check has already run, which loses the whole report and (here) flips a
# clean exit 0 into a traceback and an exit 1. read_text() in the shared
# resolver block below pins the reads; this pins the writes.
#
# Deliberately OUTSIDE the ADR-0020 shared boundary resolver block: the two
# validate.sh copies print findings, skill-size-check.sh has its own top-level
# equivalent, and tests/test-adr0020-contract.sh hashes that block for
# byte-identity across all three.
for _stream in (sys.stdout, sys.stderr):
    try:
        _stream.reconfigure(encoding='utf-8')
    except AttributeError:  # pragma: no cover — Python < 3.7
        pass

skill_dir = os.path.abspath(sys.argv[1])
skill_md = os.path.join(skill_dir, "SKILL.md")

if not os.path.isfile(skill_md):
    print(f"Error: '{skill_md}' not found.", file=sys.stderr)
    sys.exit(1)

failed = False
suggestions = []

def ok(msg):
    print(f"PASS  {msg}")

def fail(msg):
    # stderr, matching scripts/skill-size-check.sh's ERROR routing. All three
    # scripts in the ADR-0020 family now agree: findings that fail the run go to
    # stderr, everything advisory (PASS / SUGGESTION / INFO) goes to stdout.
    # Both repo callers capture `2>&1`, so nothing a human reads moves.
    global failed
    print(f"FAIL  {msg}", file=sys.stderr)
    failed = True

def suggest(msg):
    # SUGGESTIONs are printed after every check and NEVER touch the exit code.
    # factory-audit's SKILL.md Step 4 report counts them into its
    # `PASS (N suggestions)` result line, which is what makes the ADR-0020 SUGGESTION tier visible
    # rather than another silently-ignored warning (ADR-0013).
    suggestions.append(msg)

def info(msg):
    # A check that DECLINED to run says so out loud, rather than passing
    # silently. Silence is what let a whole gate family go missing unnoticed.
    print(f"INFO  {msg}")


KYBERFORGE_SKILL_PREAMBLE
KYBERFORGE_SKILL_PREAMBLE_PY="${KYBERFORGE_SKILL_PREAMBLE_PY%$'\n'}"

IFS='' read -r -d '' KYBERFORGE_SKILL_BODY_PY <<'KYBERFORGE_SKILL_BODY' || true


# A leading BOM is stripped before anything is parsed or counted. It changes
# neither count below — it is not a line separator and str.split() does not
# treat it as whitespace — but it did defeat the frontmatter match.
try:
    content = strip_bom(read_text(skill_md))
except EncodingError as exc:
    fail(f"SKILL.md is {exc}. Nothing downstream can be measured, so this is a "
         f"hard failure, not a skip")
    print("One or more checks failed.")
    sys.exit(1)

# --- Parse frontmatter ---
fm_match = FRONTMATTER_RE.match(content)
if not fm_match:
    fail("No parseable YAML frontmatter block found. Expected a `---` line, the "
         "fields, then a closing `---` line (a BOM, leading blank lines, trailing "
         "spaces after either marker and CRLF endings are all tolerated). Nothing "
         "downstream can be measured, so this is a hard failure, not a skip")
    print("One or more checks failed.")
    sys.exit(1)

fm = fm_match.group(1)
body_start = fm_match.end()

# Extract name. The character class is `[ \t]`, never `\s`: under re.MULTILINE
# a `\s*` after the colon crosses the newline, so a valueless `name:` followed
# by `description: ...` captured the NEXT KEY as the name and reported a
# mismatch instead of an absence. Same class of bug as the `description:` one
# the shared resolver's description_value() docstring records.
name_m = re.search(r'^name:[ \t]*(\S+)', fm, re.MULTILINE)
name = name_m.group(1).strip('"\'') if name_m else ""

# Extract description — the VALUE, with YAML folding resolved. Most of this
# corpus writes descriptions as `>`-folded block scalars, so the raw lines
# carry indentation and newlines that are not part of the value: every length
# measurement below is wrong unless the scalar is folded first.
try:
    desc = description_value(fm)
except FrontmatterError as exc:
    # `exc` carries the whole clause — invalid YAML, a non-mapping block, or a
    # description of the wrong type. Do not prefix a diagnosis here; the last
    # one named a syntax error for two failures that have none.
    fail(f"{exc}. Nothing downstream can be measured, so this is a hard "
         f"failure, not a skip")
    print("One or more checks failed.")
    sys.exit(1)

dir_name = os.path.basename(skill_dir)

# ADR-0020's hand-invocation carve-out (issue #108). `disable-model-invocation:
# true` takes the skill out of the model-visible listing entirely, so the
# trigger/capability/boundary rules and the 250-character routing target do not
# apply to it — the audit's own references/skill-description-quality.md Step 0 says
# so, and until this line existed no check here knew the field existed. What the
# flag does NOT lift: the body word budget and the 400-character description
# ceiling. See the shared resolver's hand_invoked().
by_hand = hand_invoked(fm)

# --- Checks ---

# name present
if name:
    ok(f"name present: '{name}'")
else:
    fail("name field is missing or empty")

# name matches directory
if name and dir_name:
    if name == dir_name:
        ok(f"name '{name}' matches directory '{dir_name}'")
    else:
        fail(f"name '{name}' does not match directory '{dir_name}'")

# name length
if name:
    if len(name) <= 64:
        ok(f"name length {len(name)} chars (limit: 64)")
    else:
        fail(f"name '{name}' is {len(name)} chars — exceeds 64-character limit")

# name format
if name:
    if re.match(r'^[a-z0-9]+(-[a-z0-9]+)*$', name):
        ok("name format valid (kebab-case)")
    else:
        fail(f"name '{name}' is invalid — use lowercase letters, numbers, and hyphens only; no leading, trailing, or consecutive hyphens")

# description present
if desc:
    ok("description present")
else:
    fail("description field is missing or empty")

# description length — agentskills.io spec backstop. UNCHANGED by ADR-0020:
# 1024 is the specification's hard limit, and the ADR-0020 budget gate below
# sits underneath it rather than replacing it.
if desc:
    dlen = len(desc)
    if dlen <= 1024:
        ok(f"description length {dlen} chars (agentskills.io spec limit: 1024)")
    else:
        fail(f"description length {dlen} chars — exceeds 1024-character limit")

# Unfilled placeholder detection — matches FILL IN: followed by actual content,
# but not backtick-quoted references like `FILL IN:` used in instructions.
PLACEHOLDER_RE = re.compile(r'(?<!`)FILL IN:[^`\n]')

# description contains unfilled placeholder
if desc and PLACEHOLDER_RE.search(desc):
    fail("description still contains 'FILL IN:' placeholder — replace before shipping")
else:
    if desc:
        ok("description has no unfilled placeholders")

# --- ADR-0022: metadata.version is mandatory -------------------------------
# FAIL, not SUGGESTION, and the tier is set by the gate rather than by taste.
# `.pre-commit-config.yaml`'s `skill-size-check` hook REJECTS a SKILL.md with
# no `metadata.version`, and rejects a value that is not three-part semver.
# skill-author's Step 4 says to run this audit and "resolve every FAIL", so any
# tier below FAIL lets that step report done on a skill the commit gate then
# refuses — the same audit-disagrees-with-the-gate failure the MAX_LINES note
# below warns about, arrived at from the other direction. Verified before this
# check existed: a SKILL.md with no `metadata:` block at all reported "All
# checks passed".
#
# The rule is DUPLICATED from that hook for the same cache-isolation reason as
# every other constant here — an installed plugin's scripts cannot read the
# repo-root config. Keep the two in step: this check must accept exactly what
# the hook accepts.
SEMVER_RE = re.compile(r'^\d+\.\d+\.\d+$')

try:
    fm_data = yaml.safe_load(fm)
except Exception:
    # Unreachable in practice: description_value() above parses the same text
    # and hard-exits on a YAML error, so anything arriving here already parsed.
    fm_data = None
metadata_block = fm_data.get('metadata') if isinstance(fm_data, dict) else None

if not isinstance(metadata_block, dict) or metadata_block.get('version') is None:
    fail("frontmatter has no metadata.version — ADR-0022 makes it mandatory for "
         "every skill, and the skill-size-check pre-commit hook rejects the file "
         "without it. Add `metadata:` / `  version: \"1.0.0\"` (new skills start "
         "at \"0.1.0\")")
else:
    version_value = metadata_block['version']
    # NOT str()-coerced blind: `version: 1.0` is a YAML float, and its "1.0"
    # spelling is exactly the two-part value the hook rejects — coercing and
    # then matching keeps this check and the hook agreeing on that case.
    version_text = version_value if isinstance(version_value, str) else str(version_value)
    version_text = version_text.strip()
    if SEMVER_RE.match(version_text):
        ok(f"metadata.version present: '{version_text}' (ADR-0022)")
    else:
        fail(f"metadata.version '{version_text}' is not three-part semver — the "
             f"skill-size-check pre-commit hook rejects it. Use MAJOR.MINOR.PATCH, "
             f"e.g. \"1.0.0\"")

# SKILL.md size ceilings (agentskills.io skill-authoring.md: 500 lines,
# ~5,000 tokens). Both constants are DUPLICATED from the repo-root pre-commit
# hook scripts/skill-size-check.sh — a plugin skill's scripts cannot read files
# outside the plugin directory once the plugin is cache-installed, so there is
# no single source to share. Keep the two in sync by hand: if they drift, this
# audit will report a skill ready to ship that the commit hook then rejects.
MAX_LINES = 500
# Word-count proxy for the ~5,000-token ceiling, calibrated to the densest
# prose in the corpus (7.22 chars/word): 2770 words is ~20,000 characters,
# ~5,000 tokens at 4 characters per token. See skill-size-check.sh's header
# for the full measurement.
MAX_WORDS = 2770

# ADR-0020 context-budget gates. DUPLICATED from scripts/skill-size-check.sh
# for exactly the same cache-isolation reason as MAX_LINES/MAX_WORDS above, and
# carrying the same warning — tests/test-skill-size-check.sh asserts the copies
# agree, so drift fails CI instead of shipping an audit that disagrees with the
# commit hook. lib-checks-agent.sh, beside this file, holds a third copy of the
# two description constants; per ADR-0020 agents take the description gates and
# deliberately take NO body word gate, because an agent body becomes the system
# prompt of a fresh context rather than competing with a live conversation.
#
# These are NOT the same measurements as MAX_LINES/MAX_WORDS and must not be
# unified with them: MAX_WORDS counts the WHOLE FILE including frontmatter and
# is a spec-conformance backstop; BODY_MAX_WORDS counts the body ONLY and is a
# quality gate. Likewise the 1024-character description limit above is the
# agentskills.io spec ceiling and stays exactly as it is — DESC_MAX_CHARS sits
# underneath it.
DESC_SUGGEST_CHARS = 250
DESC_MAX_CHARS = 400
BODY_SUGGEST_WORDS = 600
BODY_MAX_WORDS = 900

line_count = len(content.splitlines())
if line_count <= MAX_LINES:
    ok(f"SKILL.md line count {line_count} (limit: {MAX_LINES})")
else:
    fail(f"SKILL.md line count {line_count} — exceeds {MAX_LINES}-line limit")

# str.split() with no argument splits on runs of whitespace, matching the
# `wc -w` the hook uses, and counts the whole file including frontmatter.
word_count = len(content.split())
if word_count <= MAX_WORDS:
    ok(f"SKILL.md word count {word_count} (limit: {MAX_WORDS}, proxy for ~5,000 tokens)")
else:
    fail(f"SKILL.md word count {word_count} — exceeds {MAX_WORDS}-word limit (proxy for ~5,000 tokens)")

body = content[body_start:]

# --- ADR-0020: description budget -----------------------------------------
if desc:
    dlen = len(desc)
    if dlen > DESC_MAX_CHARS:
        fail(f"description is {dlen} chars — exceeds the {DESC_MAX_CHARS}-character "
             f"ADR-0020 ceiling. It is preloaded into every session whether or not the "
             f"skill is invoked. Keep a trigger clause, at most one capability clause, "
             f"and a boundary clause; move capability enumeration, output-format detail, "
             f"composition notes and implementation detail to the body or README.md")
    elif dlen > DESC_SUGGEST_CHARS and not by_hand:
        suggest(f"description is {dlen} chars — over the {DESC_SUGGEST_CHARS}-character "
                f"ADR-0020 target (hard fail at {DESC_MAX_CHARS}). The SUGGESTION tier is "
                f"what moves the corpus average; the FAIL tier only stops outliers")
    elif by_hand:
        ok(f"description length {dlen} chars (hand-invoked: the {DESC_SUGGEST_CHARS}-character "
           f"routing target does not apply, the {DESC_MAX_CHARS}-character ceiling still does)")
    else:
        ok(f"description length {dlen} chars (ADR-0020 target: {DESC_SUGGEST_CHARS})")

# --- ADR-0020: body budget -------------------------------------------------
# Counts the BODY ONLY — everything after the closing --- of the frontmatter.
# This is a different measurement from MAX_WORDS above, which counts the whole
# file including frontmatter as a spec-conformance backstop. Both are reported.
body_word_count = len(body.split())
if body_word_count > BODY_MAX_WORDS:
    fail(f"SKILL.md body is {body_word_count} words — exceeds the {BODY_MAX_WORDS}-word "
         f"ADR-0020 ceiling (body only; separate from the {MAX_WORDS}-word whole-file "
         f"limit above). Move lookup tables, spec restatements, output schemas, templates "
         f"and rationale prose to references/ behind an explicit "
         f"\"If X, read `references/file.md`\" trigger. At two or more mutually exclusive "
         f"flows, dispatch is mandatory: the body carries the dispatch table and the gates "
         f"common to every branch, each flow gets its own self-contained references/ file")
elif body_word_count > BODY_SUGGEST_WORDS:
    suggest(f"SKILL.md body is {body_word_count} words — over the {BODY_SUGGEST_WORDS}-word "
            f"ADR-0020 target (hard fail at {BODY_MAX_WORDS})")
else:
    ok(f"SKILL.md body word count {body_word_count} (ADR-0020 target: {BODY_SUGGEST_WORDS})")

# --- Reference pointers must exist -----------------------------------------
# FAIL, not SUGGESTION: a dispatch table naming a references/ file that is not
# on disk is a hard break, and until this check existed nothing in the
# gate/audit/vale stack noticed it — all three exited 0.
missing_refs = missing_reference_pointers(body, skill_dir)
for ref in missing_refs:
    fail(f"SKILL.md body points at {ref}, which does not exist on disk — a dispatch "
         f"table or \"read X\" trigger naming a missing file sends the agent nowhere")
if not missing_refs:
    ok("all referenced references/ files exist")

# --- Gotchas discipline -----------------------------------------------------
# SUGGESTION on both counts: the measurement is deterministic, but whether a
# given gotcha earns its place in the body is the auditor's judgment.
gotchas = gotcha_stats(body)
if gotchas is not None:
    gotcha_entries, gotcha_words = gotchas
    if gotcha_entries > GOTCHA_MAX_ENTRIES:
        suggest(f"Gotchas section has {gotcha_entries} entries — over the "
                f"{GOTCHA_MAX_ENTRIES}-entry guideline. A list that long is usually a "
                f"missing references/ file or a design problem written up as a warning")
    if body_word_count and gotcha_words > body_word_count * GOTCHA_MAX_BODY_FRACTION:
        suggest(f"Gotchas section is {gotcha_words} of {body_word_count} body words "
                f"({round(100.0 * gotcha_words / body_word_count)}%) — over the "
                f"{round(100.0 * GOTCHA_MAX_BODY_FRACTION)}% guideline. Move the durable "
                f"parts to references/ and keep the section for live traps")

# --- ADR-0020: boundary clause present -------------------------------------
# SUGGESTION, not FAIL: detecting the absence is deterministic, but whether
# this particular skill warrants a boundary clause is judgment. Both accepted
# shapes count — the prose markers and the compressed `Not <thing> -> <name>`.
#
# THREE outcomes, not two: "no boundary clause" and "boundary clause I could not
# parse" are different findings, and reporting the first for the second sends
# the author hunting for a problem that is not there (issue #110).
#
# Skipped entirely for a hand-invoked skill — the contract gives it one plain
# sentence with no boundary clause, so the finding would be wrong and its remedy
# names a router that cannot see the skill (issue #108).
if desc and by_hand:
    ok("hand-invoked (disable-model-invocation) — the boundary-clause and trigger "
       "rules do not apply; audited as one plain human-facing sentence")
elif desc:
    status = boundary_clause_status(desc)
    if status == 'present':
        ok("description has a boundary clause")
    elif status == 'absent':
        suggest("description has no boundary clause — add the prose form (\"Do not use "
                "for X — use `y` instead\") or ADR-0020's compressed form (\"Not X -> y\") "
                "so the router knows where NOT to send this skill")
    else:
        suggest("description has an arrow boundary clause (\"Not X -> y\") from which no "
                "target could be read, so the dangling-target check did not run on it — "
                "the clause is PRESENT and unparsed, not missing. Most often the target is "
                "a single word, which is deliberately not matchable bare because "
                "`research`, `triage` and `forge` are all ordinary English: write it as "
                "`name` or /name")
    # One arrow, one target. A second name after the same arrow is resolved by
    # nothing and reported by nothing, so the clause claims coverage it does not
    # have and this script printed "1 of 1 boundary target(s) resolve" on a
    # clause naming two (issue #107).
    for first, second in multi_target_arrow_clauses(desc):
        suggest(f"an arrow boundary clause names more than one target ('{first}', then "
                f"'{second}') and only the first is resolved — the second is checked by "
                f"nothing. Split it into one arrow per target: \"Not X -> {first}. "
                f"Not Y -> {second}.\"")

# --- ADR-0020: resolvable boundary targets ---------------------------------
# The resolution universe comes from the SKILL's own location: the authoring
# root above it (every sibling plugin in the monorepo), its own apm package, and
# the packages that package declares in apm.yml dependencies.apm. It is never
# derived from this script's own path, and — when an authoring root exists — it
# never reads a deployed .claude/ tree, so a fresh clone and a machine that has
# run `apm install` return the same verdict. See the shared resolver's header.
if desc:
    routing_targets = boundary_targets(desc)
    known = known_targets(skill_dir) if routing_targets else set()
    if routing_targets and not known:
        info(f"boundary-target resolution DID NOT RUN — no skill universe could be "
             f"determined for this path (no authoring root above it, no apm package "
             f"root, no declared apm dependencies, no deployed .claude/ or .agents/ "
             f"tree). Unchecked target(s): {', '.join(routing_targets)}")
    elif routing_targets:
        # blocking vs reported: a target only earns a FAIL when it is written in
        # route notation or its own sentence corroborates it by naming another
        # target that resolves. See the shared resolver's CORROBORATION note.
        unresolved, soft = unresolved_targets(desc, known)
        for target in unresolved:
            fail(f"description routes to '{target}', which resolves to no skill or agent "
                 f"in this monorepo, in this package, or in a package it declares in "
                 f"apm.yml dependencies.apm — a boundary clause naming a non-existent "
                 f"target sends the router nowhere")
        for target in soft:
            suggest(f"description routes to '{target}', which resolves to no skill or agent "
                    f"in this monorepo, in this package, or in a package it declares in "
                    f"apm.yml dependencies.apm — SUGGESTION rather than FAIL because nothing "
                    f"else in that sentence resolves, so it is equally likely to be a tool, a "
                    f"file format or an English compound. If it IS a route, write it as "
                    f"`/{target}` or `-> {target}` and it will be checked properly")
        if not unresolved:
            # Counts the targets that ACTUALLY resolve, not every target found:
            # a confirm-only target (one used attributively — see the resolver's
            # ATTRIBUTIVE USE note) is exempt from the failure above, so
            # reporting it as resolved would be a false claim.
            resolved = [t for t in routing_targets if normalize_target(t) in known]
            ok(f"{len(resolved)} of {len(routing_targets)} boundary target(s) resolve: "
               f"{', '.join(resolved) if resolved else '(none)'}")

# Body unfilled placeholders
fill_matches = PLACEHOLDER_RE.findall(body)
if fill_matches:
    fail(f"SKILL.md body contains {len(fill_matches)} unfilled 'FILL IN:' placeholder(s)")
else:
    ok("SKILL.md body has no unfilled placeholders")

# Interactive prompt heuristic.
#
# A line-initial `read` only blocks an agent when its stdin is the terminal.
# These forms never touch a TTY and are ordinary data plumbing, so flagging
# them is a false positive — one that has already cost two authors a
# contorted rewrite of working source:
#
#     read -r MODE ROOT <<< "$WALK_OUTPUT"   here-string
#     read -r X <<EOF                        here-doc
#     read -r line < "$file"                 redirect from a file
#     printf '%s' "$v" |                     piped stdin — the pipe ends the
#       read -r X                            PREVIOUS line, not this one
#
# So a `read` is reported only when it has neither a stdin redirection on its
# own line nor a pipe terminating the previous logical line. `read -r ANSWER`,
# `read -p "..." X` and a bare `read` still fail, which is the case the check
# exists for.
def stdin_redirected(line, prev_line):
    # Quoted spans are stripped first so a `<` inside a prompt string is not
    # mistaken for a redirect: `read -p "enter <name>: " X` is interactive and
    # must still fail.
    unquoted = re.sub(r'"[^"]*"|\'[^\']*\'', '', line)
    return '<' in unquoted or prev_line.rstrip().endswith('|')

# A here-doc body is DATA, not command position. Every script in this corpus
# carries a `usage() { cat <<EOF ... EOF; }`, and prose wrapped inside one puts
# ordinary English at the start of a line — "read is reported as an INFO ..."
# in this skill's own validate-provenance.sh, which made the skill audit
# hard-FAIL on its own script. Reflowing that one sentence would have cleared the finding
# and left the cause: every future usage text is one wrap away from the same
# false positive, and the remedy an author reaches for is contorting working
# source, which the note above records has already happened twice.
#
# Detection is deliberately conservative in the direction that matters. A
# here-doc body is skipped only when its terminator is actually found further
# down the file; an opener with no terminator — the shape a stray `<<` inside a
# string would produce — is ignored rather than allowed to swallow the tail,
# because swallowing the tail is a false NEGATIVE and this check exists to fail
# closed. `<<<` here-strings open nothing and are excluded by the lookbehind.
HEREDOC_START_RE = re.compile(r'(?<!<)<<-?\s*(["\']?)([A-Za-z_][A-Za-z0-9_]*)\1')


def heredoc_delimiter(line):
    """The here-doc terminator this line opens, or None."""
    m = HEREDOC_START_RE.search(line)
    return m.group(2) if m else None


def heredoc_body_indices(lines):
    """Line indices that are here-doc BODY (plus its terminator), not code."""
    skip = set()
    i, n = 0, len(lines)
    while i < n:
        stripped = lines[i].strip()
        delim = None if stripped.startswith('#') else heredoc_delimiter(lines[i])
        if delim:
            # `<<-` allows an indented terminator, so compare stripped.
            for j in range(i + 1, n):
                if lines[j].strip() == delim:
                    skip.update(range(i + 1, j + 1))
                    i = j
                    break
        i += 1
    return skip


# The here-doc exemption applies to the `read` heuristic ONLY, and the
# asymmetry is the point. `read` is an ordinary English verb, so any prose a
# script prints is one line-wrap away from opening with it. `input(` is not a
# word — a line beginning `input(` inside a here-doc is an embedded Python
# program pausing for a keypress, which is exactly what this check is for, and
# these scripts embed Python in a here-doc as a matter of course. Exempting the
# whole body would have disarmed the check across every script in the corpus.
def interactive_reads(source):
    hits = []
    prev_line = ''
    lines = source.splitlines()
    in_heredoc = heredoc_body_indices(lines)
    for idx, line in enumerate(lines):
        stripped = line.strip()
        if idx in in_heredoc:
            if re.match(r'input\(', stripped):
                hits.append(stripped)
            continue
        if re.match(r'read(\s|$)', stripped):
            if not stdin_redirected(line, prev_line):
                hits.append(stripped)
        elif re.match(r'input\(', stripped):
            hits.append(stripped)
        # Blank lines and comments cannot carry the pipe that feeds a
        # following `read`, so they never displace the previous line.
        if stripped and not stripped.startswith('#'):
            prev_line = line
    return hits

# Scripts checks
scripts_dir = os.path.join(skill_dir, "scripts")
if os.path.isdir(scripts_dir):
    scripts = [f for f in os.listdir(scripts_dir)
               if os.path.isfile(os.path.join(scripts_dir, f)) and not f.endswith('.md')]
    for fname in scripts:
        fpath = os.path.join(scripts_dir, fname)
        try:
            sc = read_text(fpath)
        except EncodingError as exc:
            # The executable-bit check below still runs — one unreadable byte
            # must not silently drop a second, independent check.
            sc = None
            fail(f"scripts/{fname}: {exc} — it could not be scanned for "
                 f"interactive prompts")
        interactive = interactive_reads(sc) if sc is not None else []
        if interactive:
            fail(f"scripts/{fname}: may use interactive input "
                 f"(read/input from a terminal detected): {interactive[0]}")
        elif sc is not None:
            ok(f"scripts/{fname}: no interactive prompts detected")
        # Executable bit
        if os.access(fpath, os.X_OK):
            ok(f"scripts/{fname}: is executable")
        else:
            fail(f"scripts/{fname}: not executable — run: chmod +x {fpath}")

# Summary
print()
for s in suggestions:
    print(f"SUGGESTION  {s}")
if suggestions:
    print()
if not failed:
    if suggestions:
        # Feeds SKILL.md Step 4's `PASS (N suggestions)` result line. A
        # SUGGESTION never changes the exit code — only a FAIL does.
        print(f"All checks passed ({len(suggestions)} suggestion(s)).")
    else:
        print("All checks passed.")
    sys.exit(0)
else:
    print("One or more checks failed.")
    sys.exit(1)
KYBERFORGE_SKILL_BODY
KYBERFORGE_SKILL_BODY_PY="${KYBERFORGE_SKILL_BODY_PY%$'\n'}"