Report
Read-only evo run report: terminal score scatter + best/frontier summary from recorded state
Test report
- Verdict
- Works with setup
- Score
- Tested
- Jul 20, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · 56cea46
Fetched the repo tree via gh (GitHub REST rate-limited) and read plugins/evo/skills/report/SKILL.md (canonical source; an identical mirror sits under npm/skills/report) plus report.py, which implements the described terminal scatter renderer. Frontmatter parses with name+description+evo_version; no relative links/scripts to break; SKILL.md is tightly scoped, honest, and explicitly forbids reruns/edits. Security scan clean — no URLs, base64, secrets, or hidden instructions. OUTPUT not measured (needs the external `evo` binary + a recorded workspace) — not a measured loss; docked 1 install point because the copied skill is inert without the CLI.
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 3/10
- Docs & honesty 5/5
What Report does
Read-only reporting skill for the evo optimization tool: renders the run's score scatter plot as a colored terminal block and summarizes best/frontier candidates and score deltas from recorded state. Triggers on /evo:report, "what happened overnight", "what improved", "best candidates", or "quick score chart".
How to install Report
Ships inside the evo plugin (evo-hq/evo). Requires the `evo` CLI/Python package installed and an `.evo/` workspace with recorded run state; the SKILL.md alone is inert without the binary.
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Report
-
/reportRead-only evo run report: terminal score scatter + best/frontier summary from recorded state
It also activates on plain-language prompts like these:
-
Tell me what improved in evo overnight -
Show me the best candidates from the last run -
Give me a quick score chart for this evo run
Frequently asked questions
- Is the Report skill free?
- Yes. The skill itself is free from evo-hq/evo. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Report work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 20, 2026. Verdict: Works with setup. Fetched the repo tree via gh (GitHub REST rate-limited) and read plugins/evo/skills/report/SKILL.md (canonical source; an identical mirror sits under npm/skills/report) plus report.py, which implements the described terminal scatter renderer. Frontmatter parses with name+description+evo_version; no relative links/scripts to break; SKILL.md is tightly scoped, honest, and explicitly forbids reruns/edits. Security scan clean — no URLs, base64, secrets, or hidden instructions. OUTPUT not measured (needs the external `evo` binary + a recorded workspace) — not a measured loss; docked 1 install point because the copied skill is inert without the CLI.
- What is the Report SkillProof Score?
- 6.8/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 3/10, docs & honesty 5/5.
- How do I install Report?
- 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 Report 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.