mirrors/z3
3
0
Fork 0
mirror of https://github.com/Z3Prover/z3 synced 2026-03-17 10:33:48 +00:00
Code Activity

Add action/expectation/result structure to all skill definitions

Browse source 
Each step in every SKILL.md now carries labeled Action, Expectation,
and Result blocks so the agent can mechanically execute, verify, and
branch at each stage. Format chosen after comparing three variants
(indented blocks, inline keywords, tables) on a prove-validity
simulation; indented blocks scored highest on routing completeness
and checkability.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
Angelica Moreira 2026-03-11 19:51:59 +00:00
parent d349b93d1d
commit 9d674404c8
10 changed files with 364 additions and 48 deletions
Download patch file Download diff file Expand all files Collapse all files

35
.github/skills/explain/SKILL.md vendored
View file

@ -7,6 +7,17 @@ Given raw Z3 output (from the **solve**, **prove**, **optimize**, or **benchmark
# Step 1: Identify the output type
Action:
Determine the category of Z3 output to explain: model, core,
statistics, error, or proof.
Expectation:
The output type maps to one of the recognized formats in the table below.
Result:
If the type is ambiguous, use `--type auto` and let the script detect it.
Proceed to Step 2.
| Output contains | Explanation type |
|----------------|-----------------|
| `(define-fun ...)` blocks | model explanation |
@ -17,16 +28,36 @@ Given raw Z3 output (from the **solve**, **prove**, **optimize**, or **benchmark
# Step 2: Run the explainer
Action:
Invoke explain.py with the output file or stdin.
Expectation:
The script auto-detects the output type and produces a structured
plain-language summary.
Result:
A formatted explanation is printed. If detection fails, re-run with
an explicit `--type` flag.
```bash
python3 scripts/explain.py --file output.txt
python3 scripts/explain.py --stdin < output.txt
python3 scripts/explain.py --file output.txt --debug
```
The script auto-detects the output type and produces a structured summary.
# Step 3: Interpret the explanation
Action:
Review the structured explanation for accuracy and completeness.
Expectation:
Models list each variable with its value and sort. Cores list
conflicting assertions. Statistics show time and memory breakdowns.
Result:
Use the explanation to answer the user query or to guide the next
skill invocation.
For models:
- Each variable is listed with its value and sort
- Array and function interpretations are expanded