3
0
Fork 0
mirror of https://github.com/Z3Prover/z3 synced 2026-06-10 19:07:18 +00:00
Commit graph

8 commits

Author SHA1 Message Date
Copilot
0cc04b53eb
[code-simplifier] Consolidate repo-root helpers and simplify skill script logic (#9772)
This change simplifies recently touched skill scripts by removing
duplicated repo-root discovery code, promoting shared root lookup to a
public API, and tightening small readability issues without changing
behavior. It keeps script semantics intact while making cross-skill
reuse explicit.

- **Shared API cleanup (`.github/skills/shared/z3db.py`)**
  - Promote `_find_repo_root` to public `find_repo_root`.
- Add `require_repo_root()` for scripts that should fail-fast when root
discovery fails.
  - Update library usage docstring to expose both helpers.
- Replace adjacent SQL string literals in `log()` with a single literal.

- **Deduplicate memory-safety root lookup
(`.github/skills/memory-safety/scripts/memory_safety.py`)**
  - Remove local `find_repo_root()` implementation.
  - Import and use shared `require_repo_root()` from `z3db`.

- **Simplify static-analysis label selection
(`.github/skills/static-analysis/scripts/static_analysis.py`)**
  - Replace two-step label assignment with a single expression:
    - `label = f["type"] or f["category"]`

```python
# before
label = f["category"]
if f["type"]:
    label = f["type"]

# after
label = f["type"] or f["category"]
```

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
2026-06-08 15:40:38 -07:00
Nikolaj Bjorner
59bb444694 include skills 2026-06-07 14:18:21 -07:00
Angelica Moreira
90a4cdf855 update skills readme to match current state 2026-03-11 21:53:32 +00:00
Angelica Moreira
ed5b1929f1 add dependency checks to memory-safety and static-analysis 2026-03-11 21:53:27 +00:00
Angelica Moreira
8eb35b3c46 remove deeptest skill (handled by external agent) 2026-03-11 21:53:16 +00:00
Angelica Moreira
621638abb9 run black and ruff on all skill scripts 2026-03-11 21:53:10 +00:00
Angelica Moreira
9d674404c8 Add action/expectation/result structure to all skill definitions
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>
2026-03-11 19:51:59 +00:00
Angelica Moreira
d349b93d1d Add Copilot skill architecture with 10 skills, 2 agents, and shared infra
Introduce .github/skills/ with solve, prove, optimize, simplify,
encode, explain, benchmark, memory-safety, static-analysis, and
deeptest skills. Each skill follows a SKILL.md + scripts/ pattern
with Python scripts backed by a shared SQLite logging library
(z3db.py). Two orchestrator agents (z3-solver, z3-verifier) route
requests to the appropriate skills.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-11 17:41:29 +00:00