Skip to content

praneybehl/llm-wiki-plugin / skills/llm-wiki

llm-wiki

Verified

Build and maintain an LLM-curated knowledge base from papers, articles, transcripts, notes and project findings. Ingest sources into linked Markdown, answer questions with citations, lint or upgrade a wiki, and preserve useful synthesis across sessions and agents. Also capture verified task experience, consolidate success/failure patterns, and propose, evaluate, apply or roll back evidence-linked skill improvements. Trigger on "add this to my wiki", "what does the wiki say", "learn from this task", "improve this procedure", /wiki:learn or /wiki:evolve. Works on a local folder or a hosted wiki URL (MCP). Use index-first navigation, atomic pages and hybrid search.

FileKindSize
SKILL.mdskill md24.6 KB
assets/SCHEMA.md.templateother7.4 KB
assets/decision-questions.jsonconfig3.1 KB
assets/evolution_README.md.templateother2.3 KB
assets/experience.json.templateother660 B
assets/graph_README.md.templateother2.0 KB
assets/graph_gitignore.templateother27 B
assets/index.md.templateother775 B
assets/log.md.templateother499 B
assets/ontology.yaml.templateother3.2 KB
assets/page.md.templateother805 B
assets/pattern.md.templateother839 B
assets/wiki-cache_gitignore.templateother14 B
references/agent-memory-integration.mdmarkdown7.5 KB
references/architecture.mdmarkdown9.6 KB
references/decision-models.mdmarkdown6.5 KB
references/evolution-workflow.mdmarkdown19.7 KB
references/graph-workflow.mdmarkdown7.1 KB
references/hosted-mode.mdmarkdown11.4 KB
references/ingest-workflow.mdmarkdown11.1 KB
references/lint-workflow.mdmarkdown8.3 KB
references/page-conventions.mdmarkdown5.8 KB
references/query-workflow.mdmarkdown8.6 KB
references/retrieval-setup.mdmarkdown5.6 KB
references/scaling-playbook.mdmarkdown6.8 KB
scripts/init_wiki.pyscript9.5 KB
scripts/setup_wiki.pyexecutablescript2.5 KB
scripts/test_link_resolution.pyscript6.2 KB
scripts/wiki_decide.pyexecutablescript31.6 KB
scripts/wiki_evolve.pyscript29.1 KB
scripts/wiki_evolve_agent.pyscript15.1 KB
scripts/wiki_evolve_api.pyscript7.0 KB
scripts/wiki_evolve_claude.pyscript2.4 KB
scripts/wiki_evolve_loop.pyscript43.4 KB
scripts/wiki_evolve_stream.pyscript13.0 KB
scripts/wiki_graph_extract.pyscript21.0 KB
scripts/wiki_graph_lint.pyscript22.0 KB
scripts/wiki_graph_query.pyscript9.3 KB
scripts/wiki_lint.pyscript14.5 KB
scripts/wiki_remote.pyexecutablescript76.6 KB
scripts/wiki_search.pyscript35.9 KB
scripts/wiki_stats.pyscript5.9 KB

scripts/wiki_stats.py

View on GitHub
#!/usr/bin/env python3
"""
wiki_stats.py — Quick summary of wiki size, shape, and link density.

Useful for deciding when to shard the index or split pages.

Usage:
    python wiki_stats.py [<wiki-dir>]

Example:
    python wiki_stats.py wiki/
"""

import argparse
import re
import sys
from collections import Counter
from pathlib import Path


WIKILINK_RE = re.compile(r"\[\[([^\]|]+)(?:\|[^\]]+)?\]\]")
FRONTMATTER_RE = re.compile(r"^---\s*\n(.*?)\n---\s*\n", re.DOTALL)


def link_stem(link: str) -> str:
    """Reduce a wikilink to the page stem it names, for popularity counting.

    Bare ([[kalman-filter]]), path-qualified ([[entities/kalman-filter]]),
    anchored, and .md-suffixed forms all name the same page. Counting raw link
    text splits one page's inbound total across those forms and understates
    hubs.

    NOTE: unlike wiki_lint / wiki_search, this does NOT verify that the target
    resolves — a link to an out-of-tree path such as [[raw/foo]] is counted
    under the stem "foo". That is acceptable here because these are popularity
    counts, not a correctness gate; do not reuse this function to decide
    whether a link is broken.
    """
    target = link.split("|", 1)[0]      # drop a display alias, if any
    target = target.split("#", 1)[0]    # drop a heading anchor
    target = target.replace("\\", "/").strip().strip("/")
    target = target.rsplit("/", 1)[-1]  # drop any directory prefix
    if target.lower().endswith(".md"):
        target = target[:-3]
    return target.strip()


SKIP_TOP_LEVEL_FILES = {"SCHEMA.md", "log.md", "README.md"}
SKIP_TOP_LEVEL_DIRS = {"indexes", "graph", "raw", ".evolution"}


def parse_type(text: str) -> str | None:
    m = FRONTMATTER_RE.match(text)
    if not m:
        return None
    fm = m.group(1)
    for line in fm.split("\n"):
        kv = re.match(r"^type:\s*(.*)$", line)
        if kv:
            return kv.group(1).strip().strip('"').strip("'")
    return None


def main():
    parser = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
    parser.add_argument("wiki", nargs="?", type=Path, default=Path("wiki"))
    args = parser.parse_args()

    if not args.wiki.exists():
        print(f"Wiki directory not found: {args.wiki}", file=sys.stderr)
        sys.exit(1)

    total_pages = 0
    total_lines = 0
    total_words = 0
    total_links = 0
    pages_by_type = Counter()
    pages_by_dir = Counter()
    largest = []
    most_linked_in = Counter()
    index_lines = 0

    for md_path in args.wiki.rglob("*.md"):
        rel = md_path.relative_to(args.wiki)
        try:
            text = md_path.read_text(encoding="utf-8")
        except (UnicodeDecodeError, OSError):
            continue

        if rel.name == "index.md" and len(rel.parts) == 1:
            index_lines = text.count("\n") + 1
            continue
        if rel.parts[0] in SKIP_TOP_LEVEL_FILES:
            continue
        if rel.parts[0] in SKIP_TOP_LEVEL_DIRS:
            continue
        if rel.name.startswith("."):
            continue

        total_pages += 1
        line_count = text.count("\n") + 1
        word_count = len(text.split())
        total_lines += line_count
        total_words += word_count
        # Strip frontmatter before counting wikilinks; frontmatter uses bare slugs.
        body = FRONTMATTER_RE.sub("", text, count=1) if text.startswith("---") else text
        links = WIKILINK_RE.findall(body)
        total_links += len(links)
        for link in links:
            most_linked_in[link_stem(link)] += 1
        page_type = parse_type(text) or "(none)"
        pages_by_type[page_type] += 1
        if len(rel.parts) > 1:
            pages_by_dir[rel.parts[0]] += 1
        else:
            pages_by_dir["(root)"] += 1
        largest.append((line_count, str(rel)))

    largest.sort(reverse=True)

    print("=" * 60)
    print(f"Wiki Stats: {args.wiki}")
    print("=" * 60)
    print(f"Pages:         {total_pages}")
    print(f"Total lines:   {total_lines:,}")
    print(f"Total words:   {total_words:,}")
    print(f"Total links:   {total_links:,}")
    if total_pages:
        print(f"Avg page:      {total_lines // total_pages} lines / {total_words // total_pages} words")
        print(f"Link density:  {total_links / total_pages:.1f} links per page")
    print(f"index.md:      {index_lines} lines" + ("  ← shard recommended (>300)" if index_lines > 300 else ""))
    print()

    print("Pages by type:")
    for t, n in pages_by_type.most_common():
        print(f"  {t:15s} {n}")
    print()

    print("Pages by directory:")
    for d, n in pages_by_dir.most_common():
        print(f"  {d:15s} {n}")
    print()

    if largest:
        print("Largest pages:")
        for lines, path in largest[:10]:
            warn = ""
            if lines > 800:
                warn = "  ← OVER HARD CAP"
            elif lines > 400:
                warn = "  ← over soft cap"
            print(f"  {lines:5d}  {path}{warn}")
        print()

    if most_linked_in:
        print("Most-linked-to pages (hubs):")
        for slug, count in most_linked_in.most_common(10):
            print(f"  {count:4d}  [[{slug}]]")
        print()

    # Scaling recommendations
    print("Scaling thresholds:")
    if total_pages < 50:
        print("  → Below first threshold. Flat structure is fine.")
    elif total_pages < 150 and index_lines < 300:
        print("  → Below shard threshold. Continue with single index.md.")
    elif (total_pages >= 150 or index_lines >= 300) and not (args.wiki / "indexes").exists():
        print("  → AT SHARD THRESHOLD. Consider sharding index.md into wiki/indexes/<type>.md.")
        print("    See references/scaling-playbook.md.")
    elif total_pages >= 300:
        print("  → Past 300 pages. Use scripts/wiki_search.py as a routine fallback.")
    if total_pages >= 500:
        print("  → Past 500 pages. Run lint weekly or per-N-ingests.")


if __name__ == "__main__":
    main()
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall