GodModeAI2025/SkillSafeWerkstatt / query-llm-wiki
query-llm-wiki
UnverifiedSearch, filter, inventory, and answer from a verified SkillSafeWerkstatt release with claim-level source locators and read-only quality assessment. Use whenever the user asks about this wiki, requests original sources or citations, compares current and historical claims, filters metadata, inspects schema drift, or checks wiki quality without modifying it in Claude Code, Claude Cowork, or Codex.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 18.2 KB |
| evals/evals.json | config | 19.1 KB |
| references/answer-contract.md | markdown | 46.1 KB |
| references/query-filters.md | markdown | 2.6 KB |
| scripts/assess_quality.py | script | 1.8 KB |
| scripts/bm25.py | script | 8.2 KB |
| scripts/describe_actions.py | script | 4.4 KB |
| scripts/freshness.py | script | 3.6 KB |
| scripts/frontmatter_contract.py | script | 10.0 KB |
| scripts/identity_status.py | script | 6.0 KB |
| scripts/inventory_wiki.py | script | 6.5 KB |
| scripts/quality_core.py | script | 15.9 KB |
| scripts/search_core.py | script | 221.1 KB |
| scripts/search_wiki.py | script | 4.8 KB |
| scripts/sync_artifacts.py | script | 14.2 KB |
| scripts/trust_contract.py | script | 5.2 KB |
| scripts/verify_release.py | script | 12.1 KB |
| scripts/wiki_filters.py | script | 6.6 KB |
| scripts/wordforms.py | script | 56.0 KB |
scripts/describe_actions.py
View on GitHub#!/usr/bin/env python3
"""Return the machine-readable, strictly read-only query action catalog."""
from __future__ import annotations
import json
import sys
CATALOG = {
"format": "lmwiki-action-catalog/1",
"skill": "query-llm-wiki",
"read_only": True,
"selector": {
"types": ["all", "paths", "filter"],
"operators": ["exists", "not_exists", "equals", "not_equals", "contains", "not_contains", "starts_with", "ends_with", "is_empty", "is_not_empty", "is_list", "is_string", "in_path"],
"virtual_properties": ["__path", "__folder", "__filename", "__extension"],
"combinators": ["AND", "OR"],
},
"actions": [
{"id": "verify-release", "helper": "verify_release.py", "description": "Verify release hashes and lock-free snapshot stability.", "writes": False, "destructive": False, "parameters": [{"name": "expect_manifest_sha256", "type": "sha256", "required": False}]},
{"id": "inspect-identity", "helper": "identity_status.py", "description": "Validate and return only the allowlisted confirmed SOUL and content-policy fields.", "writes": False, "destructive": False, "parameters": []},
{"id": "assess-quality", "helper": "assess_quality.py", "description": "Assess technical state, review freshness, open questions, snapshot age, the trust-tier distribution, and pages past their own end date.", "writes": False, "destructive": False, "parameters": [{"name": "expect_manifest_sha256", "type": "sha256", "required": False}]},
{"id": "inventory-frontmatter", "helper": "inventory_wiki.py", "description": "Return property counts, observed types, samples, and schema drift from a verified release.", "writes": False, "destructive": False, "parameters": [{"name": "expect_manifest_sha256", "type": "sha256", "required": False}]},
{
"id": "search",
"helper": "search_wiki.py",
"description": "Search claims and sources with concept expansion, word forms and disclosed irregular-form, compound, quantity and typo heuristics (match_rules per result), optional agent reformulations searched in the same call (pages only they return come back separately in reformulation_results; each result names the searches that found it in found_by), and an optional validated metadata selector; a coverage block counts truncated matches, withheld claims, word forms, and unmatched terms per search; with exhaustive, the same call also ranks sources and scans every passage of the wiki pages, meta/questions.md and the source Markdown within a fixed 100,000-character evidence budget, and every report carries absence_check (complete, reasons, next_steps) and search_record.",
"writes": False,
"destructive": False,
"requires_one_of": ["query", "request"],
"parameters": [
{"name": "query", "type": "string", "required": False, "exclusive_with": ["request"]},
{"name": "also", "type": "string, repeatable, at most 4, each at most 200 characters", "required": False, "exclusive_with": ["request"]},
{"name": "request", "type": "'-': one JSON object {query, also?, filter?} on standard input; filter replaces filter_json", "required": False, "exclusive_with": ["query", "also"]},
{"name": "limit", "type": "integer 1-100 (caps results and reformulation_results separately)", "required": False},
{"name": "filter_json", "type": "selector", "required": False},
{"name": "include_sources", "type": "boolean", "required": False},
{"name": "include_history", "type": "boolean", "required": False},
{"name": "exhaustive", "type": "boolean; also ranks sources and scans every passage of the wiki pages, meta/questions.md and the source Markdown (with include_history also the snapshots) for all words of all searches (at most 100,000 printed characters of hits); required before stating that the wiki holds nothing on a question", "required": False},
{"name": "expect_manifest_sha256", "type": "sha256", "required": False},
],
},
],
}
if __name__ == "__main__":
# Windows pipes default to the ANSI code page; output is UTF-8 everywhere.
for _stream in (sys.stdout, sys.stderr):
if hasattr(_stream, "reconfigure"):
_stream.reconfigure(encoding="utf-8", errors=_stream.errors)
print(json.dumps(CATALOG, ensure_ascii=False, indent=2))
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 472k | Updated | Claude CodeCodex | Verified | Install |
| 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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 available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |