Menu

Individual skill

octocode-graph-eval

0upvotes

Use when you need a measurable keep/discard loop — goal→KPI, baseline vs target, held-out checks, eval suites, or don't-stop-till-done against a runnable sensor. Not for ordinary ship checks where 'tests passed' is enough.

skills/octocode-graph-eval/SKILL.md

Read pinned source

Source commit c265e3f9413161c900cbf4aa70d451b8e6b3920a

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
No
Repository scan complete
No
Skill scan complete
No
Observed behavior
Not checked yet
Last checked
Nov 4, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
958
Repository last updated
Nov 6, 2026
License
MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt
# Octocode Graph Eval
Evaluate outcomes and run improvement loops with evidence, not vibes — for one loop or a graph of loops.
Flow: `ERROR-ANALYZE → FRAME(goal→KPI) → BASELINE → LOOP → JUDGE → CAPTURE → VERIFY → SUITE-EVOLVE`.
Modes: **ErrorAnalyze** · **Define** · **Run** · **Suite** · **Benchmark** · **Audit**.

## Lobby rules
- No goal→KPI link → STOP. No measurable primary → STOP. No runnable sensor → build one before looping.
- Narrative-only accept → REJECT. Editing harness/cases/graders to pass → REJECT.
- ACCEPT only if primary moves on held-out **and** guardrails hold.
- Prefer deterministic graders; binary/LLM next; humans calibrate. Grade outcomes over paths.
- **TDD for agents:** write or select a failing case / KPI check **before** mutating the subject; green only after the change (red → green → keep|discard).
- Public benches orient; private failure suites gate ships. Distrust saturated/contaminated boards.
- Freeze the harness during an experiment; evolve the suite only between experiments.
- **Graph check:** before evaluating a multi-agent workflow, run edge detection — if no two nodes are independent (every step reads the prior step's output), it is a loop, not a graph. Build a loop.
- **Goodhart guard:** every primary KPI must have a counter-metric guardrail the agent cannot tune. Primary improving + guardrail degrading → reframe the goal, not the loop.
Back to top