Is the Agent Wiki Summarize skill free?

Yes. The skill itself is free from AgentToolkit/altk-evolve. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Agent Wiki Summarize SkillProof Score?

8.8/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.

How do I install Agent Wiki Summarize?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Agent Wiki Summarize with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Agent Wiki Summarize

Turns saved Claude Code trajectory JSON into scored episodic wiki summaries automatically.

by AgentToolkit · AgentToolkit/altk-evolve

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 8.8/10
Tested: Jul 13, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · f560599

Fed it a fake trajectory where the agent read a refund-idempotency guideline and applied it; it correctly pulled the 12-hex guideline id out of the filename and classified it 'followed' with a verbatim evidence quote, something a plain summary never surfaces. The catch: the helper script it pipes to (build_agent_wiki.py) lives in a sibling scripts/ folder outside the skill's own directory, so a plain cp of the skill folder silently breaks it.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 4/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 5/5

What Agent Wiki Summarize does

Reads a normalized Claude Code trajectory JSON (or a folder of them) and writes a per-session wiki page: a short narrative, 3-6 key turns, and a followed/ignored/harmful/contradicted classification for every guideline the agent recalled, each with a verbatim evidence quote. Trigger it when you have saved agent sessions and want them turned into a browsable, indexed knowledge base rather than read once and discarded. Best fit for teams already running the broader agent-wiki toolchain (build_agent_wiki.py, wiki-twobatch/ layout), not as a drop-in generic summarizer.

How to install Agent Wiki Summarize

git clone https://github.com/AgentToolkit/altk-evolve
cd altk-evolve
mkdir -p ~/.claude/skills
cp -r explorations/agent-wiki/skills/agent-wiki-summarize ~/.claude/skills/agent-wiki-summarize

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Agent Wiki Summarize

/agent-wiki-summarize Turns saved Claude Code trajectory JSON into scored episodic wiki summaries automatically.

It also activates on plain-language prompts like these:

Summarize my saved Claude Code sessions into a wiki
Turn my agent trajectory logs into scored summaries
Build a knowledge base from my agent session JSON

Frequently asked questions

Is the Agent Wiki Summarize skill free?: Yes. The skill itself is free from AgentToolkit/altk-evolve. SkillProof publishes the install command and an independent test verdict at no cost.
Does Agent Wiki Summarize work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 13, 2026. Verdict: Works with setup. Fed it a fake trajectory where the agent read a refund-idempotency guideline and applied it; it correctly pulled the 12-hex guideline id out of the filename and classified it 'followed' with a verbatim evidence quote, something a plain summary never surfaces. The catch: the helper script it pipes to (build_agent_wiki.py) lives in a sibling scripts/ folder outside the skill's own directory, so a plain cp of the skill folder silently breaks it.
What is the Agent Wiki Summarize SkillProof Score?: 8.8/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
How do I install Agent Wiki Summarize?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Agent Wiki Summarize with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.