wehub-resource-sync
9201ef759e
CI / lint (push) Waiting to run
CI / mypy (push) Waiting to run
CI / docs (push) Waiting to run
CI / test on 3.10 (standard) (push) Waiting to run
CI / test on 3.11 (standard) (push) Waiting to run
CI / test on 3.12 (standard) (push) Waiting to run
CI / test on 3.10 (all-extras) (push) Waiting to run
CI / test on 3.11 (all-extras) (push) Waiting to run
CI / test on 3.12 (all-extras) (push) Waiting to run
CI / test on 3.13 (all-extras) (push) Waiting to run
CI / test on 3.14 (pydantic-evals) (push) Waiting to run
CI / test on 3.13 (standard) (push) Waiting to run
CI / test on 3.14 (standard) (push) Waiting to run
CI / test on 3.14 (all-extras) (push) Waiting to run
CI / test on 3.10 (pydantic-ai-slim) (push) Waiting to run
CI / test on 3.11 (pydantic-ai-slim) (push) Waiting to run
CI / test on 3.12 (pydantic-ai-slim) (push) Waiting to run
CI / test on 3.13 (pydantic-ai-slim) (push) Waiting to run
CI / test on 3.14 (pydantic-ai-slim) (push) Waiting to run
CI / test on 3.10 (pydantic-evals) (push) Waiting to run
CI / test on 3.11 (pydantic-evals) (push) Waiting to run
CI / test on 3.12 (pydantic-evals) (push) Waiting to run
CI / test on 3.13 (pydantic-evals) (push) Waiting to run
CI / test on 3.10 (lowest-versions) (push) Waiting to run
CI / test on 3.11 (lowest-versions) (push) Waiting to run
CI / test on 3.12 (lowest-versions) (push) Waiting to run
CI / test on 3.13 (lowest-versions) (push) Waiting to run
CI / test on 3.14 (lowest-versions) (push) Waiting to run
CI / test examples on 3.11 (push) Waiting to run
CI / test examples on 3.12 (push) Waiting to run
CI / test examples on 3.13 (push) Waiting to run
CI / test examples on 3.14 (push) Waiting to run
CI / coverage (push) Blocked by required conditions
CI / check (push) Blocked by required conditions
CI / deploy-docs (push) Blocked by required conditions
CI / deploy-docs-preview (push) Blocked by required conditions
CI / build release artifacts (push) Blocked by required conditions
CI / publish to PyPI (push) Blocked by required conditions
CI / Send tweet (push) Blocked by required conditions
Harness Compat / harness compat (push) Failing after 0s
26 lines
1.0 KiB
Markdown
26 lines
1.0 KiB
Markdown
---
|
|
# Shared evidence and accuracy bar for gh-aw prompts.
|
|
# gh-aw imports this file; the markdown below (after the closing ---) is
|
|
# appended to the agent's task prompt at runtime via {{#runtime-import}}.
|
|
---
|
|
|
|
## Rigor
|
|
|
|
- Prefer concrete evidence over speculation. Ground claims in exact file
|
|
paths, line numbers, captured outputs, or reproduction steps when the task
|
|
allows.
|
|
- If you cannot show the trigger, failure path, or observed behavior, drop the
|
|
claim.
|
|
- "I don't know" beats a wrong answer. `mcp__safeoutputs__noop` beats a weak
|
|
or speculative issue or review.
|
|
- If you need to hedge with "might", "could", or "possibly", it is not
|
|
ready.
|
|
|
|
## Adversarial self-review
|
|
|
|
- Before emitting any issue, discussion, or review, switch sides: assume your
|
|
finding is WRONG and try your hardest to refute it. Emit it only if it
|
|
survives your own strongest counter-argument.
|
|
- A false or by-design report costs maintainers more than a missed one.
|
|
Precision beats recall — when in doubt, `mcp__safeoutputs__noop`.
|