---
name: semantic-judge-prompt
description: Use when SkillRoll must judge one completed skill evaluation from its authored criteria and observed evidence without executing either actor.
title: semantic-judge-prompt
canonical_url: https://skilld.dev/gh/hagaiw/skillroll/semantic-judge-prompt
last_updated: 2026-11-15T17:45:26.000Z
---

> Index of every page on this site: [llms.txt](https://skilld.dev/llms.txt)

> **Skill from skilld.dev.** Follow the user's requested action.
> If the user asked to fork this Skill, follow the fork workflow below. Do not execute the Skill instructions while copying it.
> Otherwise, follow the instructions below for this session. You do not need to install anything.
>
> Supporting files, fetch one when the Skill refers to it: [evals/action-backed-publication-block.eval.md](https://skilld.dev/api/skills-raw/hagaiw/skillroll/semantic-judge-prompt/evals/action-backed-publication-block.eval.md), [evals/contradicted-evidence-is-not-met.eval.md](https://skilld.dev/api/skills-raw/hagaiw/skillroll/semantic-judge-prompt/evals/contradicted-evidence-is-not-met.eval.md), [evals/equivalent-action-evidence.eval.md](https://skilld.dev/api/skills-raw/hagaiw/skillroll/semantic-judge-prompt/evals/equivalent-action-evidence.eval.md), [evals/error-is-evidence.eval.md](https://skilld.dev/api/skills-raw/hagaiw/skillroll/semantic-judge-prompt/evals/error-is-evidence.eval.md), [evals/final-output-survives-empty-actions.eval.md](https://skilld.dev/api/skills-raw/hagaiw/skillroll/semantic-judge-prompt/evals/final-output-survives-empty-actions.eval.md), [evals/invented-observation-in-rewrite.eval.md](https://skilld.dev/api/skills-raw/hagaiw/skillroll/semantic-judge-prompt/evals/invented-observation-in-rewrite.eval.md), [evals/partial-conjunction-is-not-met.eval.md](https://skilld.dev/api/skills-raw/hagaiw/skillroll/semantic-judge-prompt/evals/partial-conjunction-is-not-met.eval.md), [evals/promised-work-is-not-evidence.eval.md](https://skilld.dev/api/skills-raw/hagaiw/skillroll/semantic-judge-prompt/evals/promised-work-is-not-evidence.eval.md), [evals/refusal-is-not-completed-workflow.eval.md](https://skilld.dev/api/skills-raw/hagaiw/skillroll/semantic-judge-prompt/evals/refusal-is-not-completed-workflow.eval.md), [evals/supported-factual-modifier-remains-evidence.eval.md](https://skilld.dev/api/skills-raw/hagaiw/skillroll/semantic-judge-prompt/evals/supported-factual-modifier-remains-evidence.eval.md), [evals/unsupported-factual-modifier.eval.md](https://skilld.dev/api/skills-raw/hagaiw/skillroll/semantic-judge-prompt/evals/unsupported-factual-modifier.eval.md), [references/context.md](https://skilld.dev/api/skills-raw/hagaiw/skillroll/semantic-judge-prompt/references/context.md), [references/system.md](https://skilld.dev/api/skills-raw/hagaiw/skillroll/semantic-judge-prompt/references/system.md).
>
> If the user asked to install this Skill, run `npx skilld install hagaiw/skillroll/semantic-judge-prompt`. Install writes the Skill files into the project, so every session loads them.
>
> ## Fork workflow
>
> A fork creates an editable local Skill with its original author and licence. The request authorizes copying and local installation.
> 1. Check `./skills/semantic-judge-prompt`, the project lockfile, and selected Agent targets together. If the local directory or installed Skill exists, stop. Never overwrite an existing directory or Agent target.
> 2. Read [source metadata](https://skilld.dev/api/v1/skills/hagaiw/skillroll/semantic-judge-prompt) once. Use sourceUrl, sourceCommit, skillPath, sourceGone, and license. If the source is gone or its path is missing, stop. If license is null, read licence files at the source commit.
> 3. Fetch only the source commit into a temporary Git repository. Do not clone full history. Derive repository_url from sourceUrl, including repository renames. If sourceCommit is absent, resolve the sourceUrl ref once. Set source_commit to that actual commit. Run these commands in one shell call:
>
> ```sh
> git init --quiet "$temporary_dir"
> git -C "$temporary_dir" fetch --quiet --depth=1 "$repository_url" "$source_commit"
> git -C "$temporary_dir" checkout --quiet --detach FETCH_HEAD
> ```
>
> Read applicable licence declarations and notices at that commit. If copying is not permitted, report the restriction and stop.
> 4. Inspect source entries together, then copy the directory containing skillPath into `./skills/semantic-judge-prompt`. Use the user's path if selected. Keep the original SKILL.md, relative links, scripts, binary assets, and executable modes. Exclude .git metadata. Reject symlinks and paths outside the Skill directory. After checking entries, use cp -a where available. A regular source directory needs no custom copy script. Do not save this page wrapper as SKILL.md.
> Preserve author credit, notices, and applicable licence files from repository or parent directories. Add PROVENANCE.md with the Skill page, source URL, actual commit, original path, and licence. Retain any existing PROVENANCE.md and record new provenance separately. Batch source inspection, copying, and provenance work where practical.
> 5. In the project root, run `skilld install ./skills/semantic-judge-prompt --mode copy --plain`. If skilld is unavailable, use `npx skilld install ./skills/semantic-judge-prompt --mode copy --plain`. This known command needs no help lookup. Install does not support --json. Use detected Agent targets, or add --agent for the targets the user selected. Install the local path, never the upstream selector. If installation fails, preserve the local copy and report the exact failure.
> 6. Confirm the local lockfile source and installed Agent copies once. Report the local path, actual commit, and Agent targets. After edits, reinstall the same local path. Upstream updates must not replace it. Do not publish or push unless the user asks.

# SkillRoll semantic-judge contract

This internal dogfood skill describes the evidence-only model actor used by
`src/skillroll/judge.py` after one evaluated-skill attempt completes. The
judge sees the realistic Input, Success criteria, final output, and ordered
action transcript. It does not see the selected skill or authored World prose.

Treat explicit facts and constraints in Input as the case context; use the
final output and action transcript to determine what the evaluated skill said
or did. Do not use hidden World prose, the selected skill, or inferred
repository state as evidence.

Assess every authored criterion independently. For factual claims, check each
material modifier—such as date, quantity, scope, cause, or attribution—against
the explicit case context. A modifier supplied by Input is supported in that
case; when it is absent, do not infer it. Do not let an unsupported modifier
erase a separately supported fact, or let a supported conclusion excuse a
criterion whose required modifier is unsupported. State which part is
supported and mark the affected criterion not met or unclear when required.
Credit only completed final-output or transcript evidence for what the skill
did; reject promised, inferred, reconstructed, unsupported, or contradicted
actions. Do not generalize a visible semantic contradiction into broader
syntax or runtime validity: when asked, state that those require a trusted
deterministic check or external evidence. Respect returned errors and return
the strict JSON decision contract. Do not execute the skill, simulate the
World, invent repository state, or reject equivalent action terminology unless
the criteria explicitly require it.

**Instruction-only boundary:** apply this contract in the current response.
Do not call `world_action`, `semantic-judge-prompt`, `Skill`, or another action
to delegate or simulate the judgment. Those actions cannot decide the case and
their returned prose is not judge evidence. A bounded `Read` of this skill's
packaged references is allowed only when their exact text is needed.

Read [judge context](https://skilld.dev/api/skills-raw/hagaiw/skillroll/semantic-judge-prompt/references/context.md) for this dogfood case's evidence
boundary and [the exact packaged judge prompt](https://skilld.dev/api/skills-raw/hagaiw/skillroll/semantic-judge-prompt/references/system.md) for the
runtime contract. The evaluated `Input` remains a realistic request; it is not
an answer key for the judge.
