knowledge-synthesis

Installation
SKILL.md

Codex compatibility note:

  • Invoke $skill-name: load the registered .agents/skills/<name>/SKILL.md and execute it with Codex tools; no separate Skill tool or Claude mode switch is needed. When a workflow step or another skill names a skill, read that file in full yourself (every line, with no line limit; in parts only when output is cut off): a skill whose implicit invocation is off is never loaded for you. Author .claude/**; mirrors are generated.
  • Track steps before execution and keep progress/evidence current. Explicit skill requests execute their protocol. Use the native question tool for required questions.
  • Map foreign tool names to available host capabilities. A name mismatch needs no approval; an actually unavailable required capability stops with its step/evidence and a user question before adaptation.
  • Subagent authorization: when a skill is user-invoked or AI-detected and its protocol requires subagents, that skill activation authorizes use of the required spawn_agent subagent(s) for that task.
  • Preserve protocol order unless the user approves a deviation. Workflows use $start-workflow: gates stay fixed; other steps may flex with logged reasons and evidence. Web Research Protocol — Factual claims need 2+ independent sources; rank Tier 1 authoritative > Tier 2 industry reports > Tier 3 credible blogs; Tier 4 unverified, NEVER cite as fact; declare confidence (95/80/60/<60%). Working files → tmp/research/; final output → docs/knowledge/.

MUST ATTENTION READ only the Knowledge Work Rules (canonical for the research chain) section of .claude/skills/web-research/SKILL.md for canonical research rules; source-discovery procedures belong to a separate discovery request.

Quick Summary

Goal: Synthesize the existing evidence base into a fully cited, template-compliant research report with honest confidence and explicit gaps, trustworthy for decisions.

Summary:

Installs
2
GitHub Stars
3
First Seen
13 days ago