Home / agenttoolkit / altk-evolve · explorations/agent-wiki/skills/agent-wiki-compare-outcomes/SKILL.md · GitHub

agent-wiki-compare-outcomes skillA

agent-wiki-compare-outcomes is agent-read markdown (skill) from agenttoolkit/altk-evolve: Compare successful and failed normalized agent trajectories to derive evidence-backed agent-wiki guidelines. Use when Codex has multiple runs for the same or similar task, evaluator outcomes, failed/successful variants, benchmark trajectories, or wants to learn rules from contrasts rather than from one trajectory alone..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Agent Wiki — Compare Outcomes

## Overview

Use this pass after summarize/extract/synthesize when there are multiple
trajectories that can be judged as successful or failed. It can judge
outcomes with an LLM from the normalized transcript, so it does not need to
depend on benchmark-specific success/failure labels. It derives
**contrastive guidelines**: rules that are supported by a failed path, a
successful path, and concrete evidence from task wording, tool/API
documentation, tool/API calls, transcript evidence, optional failure snippets,
and optionally an LLM success/failure judgment.

This pass exists to avoid hand-authored domain knowledge. Do not write a rule
just because you know the benchmark or application. Write a rule only when the
input trajectories contain the evidence.

## Workflow

### Step 1: Build an Evidence Pack

Run the bundled script over normalized trajectory JSON files:

```bash
uv run python explorations/agent-wiki/skills/agent-wiki-compare-outcomes/scripts/compare_outcomes.py \
  --input <normalized-dir-or-json> \
  --out-json <analysis.json> \
  --out-md <analysis.md> \
  --judge-outcomes always
```
…

Read the whole file at its exact version.

How to install

Latest version
mdr add agenttoolkit/altk-evolve/agent-wiki-compare-outcomes@git:20260921.bc25f93
Exact content
mdr add agenttoolkit/altk-evolve/agent-wiki-compare-outcomes@sha256:93894472b8c65463

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_qwsl46qczq32gbxa.svg)](https://markdownregistry.com/a/art_qwsl46qczq32gbxa)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260921.bc25f93 latest2026-09-21 bc25f93 6,616 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (6616 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

agenttoolkit/altk-evolve · 116 stars · license Apache-2.0 · pushed 2026-09-22 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_qwsl46qczq32gbxa
GET https://markdownregistry.com/api/v1/resolve?ref=agenttoolkit/altk-evolve/agent-wiki-compare-outcomes
GET https://markdownregistry.com/api/v1/blob/93894472b8c65463e8300b31a56e2374d1162550c777c4c4ccaf6766f668cad8

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from agenttoolkit/altk-evolve

AGENTS.md agents
agenttoolkit/altk-evolve · AGENTS.md
git:20260425.68cbfbf · audit A · 116 stars
CLAUDE.md@demo/workdir claude
agenttoolkit/altk-evolve · demo/workdir/CLAUDE.md
git:20260114.19bba88 · audit A · 116 stars
agent-wiki-consolidate-guidelines skill
agenttoolkit/altk-evolve · explorations/agent-wiki/skills/agent-wiki-consolidate-guidelines/SKILL.md · Read all atomic guidelines in wiki-twobatch/guidelines/ and propose themed clusters that group near-duplicates. Writes…
git:20260610.3e26154 · audit A · 116 stars
agent-wiki-consult skill
agenttoolkit/altk-evolve · explorations/agent-wiki/skills/agent-wiki-consult/SKILL.md · Consult an agent-wiki for guidelines relevant to the task at hand. The wiki itself documents how to retrieve from it…
git:20260610.3e26154 · audit A · 116 stars
agent-wiki-extract-guidelines skill
agenttoolkit/altk-evolve · explorations/agent-wiki/skills/agent-wiki-extract-guidelines/SKILL.md · Read a normalized Claude Code trajectory JSON and extract reusable guidelines into wiki-twobatch/guidelines/. Use when…
git:20260610.3e26154 · audit A · 116 stars
agent-wiki-ingest skill
agenttoolkit/altk-evolve · explorations/agent-wiki/skills/agent-wiki-ingest/SKILL.md · Ingest one or more agent trajectories (raw bob/claude traces or normalized JSON) into an agent-wiki end-to-end —…
git:20260921.bc25f93 · audit A · 116 stars
agent-wiki-summarize skill
agenttoolkit/altk-evolve · explorations/agent-wiki/skills/agent-wiki-summarize/SKILL.md · Read a normalized Claude Code trajectory JSON and write an episodic summary page to wiki-twobatch/summaries/. Use when…
git:20260610.3e26154 · audit A · 116 stars
agent-wiki-synthesize-skill skill
agenttoolkit/altk-evolve · explorations/agent-wiki/skills/agent-wiki-synthesize-skill/SKILL.md · Read a normalized Claude Code trajectory JSON and produce a wiki-resident SKILL.md page that future agents can invoke…
git:20260610.3e26154 · audit A · 116 stars
agent-wiki-tasks skill
agenttoolkit/altk-evolve · explorations/agent-wiki/skills/agent-wiki-tasks/SKILL.md · Discover task families across summaries and write per-family comparison pages with findings narrative. Updates…
git:20260610.3e26154 · audit A · 116 stars
evolve-lite:adapt-memory skill
agenttoolkit/altk-evolve · platform-integrations/bob/evolve-lite/skills/evolve-lite-adapt-memory/SKILL.md · Mirror a just-saved native memory into the shared evolve store so it becomes shareable and auditable
git:20260625.6f2bfc0 · audit A · 116 stars
evolve-lite:provenance skill
agenttoolkit/altk-evolve · platform-integrations/bob/evolve-lite/skills/evolve-lite-provenance/SKILL.md · Analyze saved trajectories and recall audit events offline to record whether recalled guidelines influenced completed…
git:20260625.6f2bfc0 · audit A · 116 stars
evolve-lite:publish skill
agenttoolkit/altk-evolve · platform-integrations/bob/evolve-lite/skills/evolve-lite-publish/SKILL.md · Publish a private guideline to a configured write-scope repo.
git:20260504.09b173d · audit A · 116 stars

Every file in agenttoolkit/altk-evolve

Browse by kind, by grade A, or by owner.