docs: ensure manual tests use local specify (#2020)

* docs: ensure manual tests use local specify

* docs: mention venv activation before editable install

* docs: clarify Windows venv activation commands

TESTING.md

@@ -1,8 +1,59 @@
-# Manual Testing Guide
+# Testing Guide
+
+This document is the detailed testing companion to [`CONTRIBUTING.md`](./CONTRIBUTING.md).
+
+Use it for three things:
+
+1. running quick automated checks before manual testing,
+2. manually testing affected slash commands through an AI agent, and
+3. capturing the results in a PR-friendly format.
 
 Any change that affects a slash command's behavior requires manually testing that command through an AI agent and submitting results with the PR.
 
-## Process
+## Recommended order
+
+1. **Sync your environment** — install the project and test dependencies.
+2. **Run focused automated checks** — especially for packaging, scaffolding, agent config, and generated-file changes.
+3. **Run manual agent tests** — for any affected slash commands.
+4. **Paste results into your PR** — include both command-selection reasoning and manual test results.
+
+## Quick automated checks
+
+Run these before manual testing when your change affects packaging, scaffolding, templates, release artifacts, or agent wiring.
+
+### Environment setup
+
+```bash
+cd <spec-kit-repo>
+uv sync --extra test
+source .venv/bin/activate  # On Windows (CMD): .venv\Scripts\activate  |  (PowerShell): .venv\Scripts\Activate.ps1
+```
+
+### Generated package structure and content
+
+```bash
+uv run python -m pytest tests/test_core_pack_scaffold.py -q
+```
+
+This validates the generated files that CI-style packaging depends on, including directory layout, file names, frontmatter/TOML validity, placeholder replacement, `.specify/` path rewrites, and parity with `create-release-packages.sh`.
+
+### Agent configuration and release wiring consistency
+
+```bash
+uv run python -m pytest tests/test_agent_config_consistency.py -q
+```
+
+Run this when you change agent metadata, release scripts, context update scripts, or artifact naming.
+
+### Optional single-agent packaging spot check
+
+```bash
+AGENTS=copilot SCRIPTS=sh ./.github/workflows/scripts/create-release-packages.sh v1.0.0
+```
+
+Inspect `.genreleases/sdd-copilot-package-sh/` and the matching ZIP in `.genreleases/` when you want to review the exact packaged output for one agent/script combination.
+
+## Manual testing process
 
 1. **Identify affected commands** — use the [prompt below](#determining-which-tests-to-run) to have your agent analyze your changed files and determine which commands need testing.
 2. **Set up a test project** — scaffold from your local branch (see [Setup](#setup)).
@@ -13,19 +64,22 @@ Any change that affects a slash command's behavior requires manually testing tha
 ## Setup
 
 ```bash
-# Install the CLI from your local branch
+# Install the project and test dependencies from your local branch
 cd <spec-kit-repo>
-uv venv .venv
-source .venv/bin/activate  # On Windows: .venv\Scripts\activate
+uv sync --extra test
+source .venv/bin/activate  # On Windows (CMD): .venv\Scripts\activate  |  (PowerShell): .venv\Scripts\Activate.ps1
 uv pip install -e .
+# Ensure the `specify` binary in this environment points at your working tree so the agent runs the branch you're testing.
 
 # Initialize a test project using your local changes
-specify init /tmp/speckit-test --ai <agent> --offline
+uv run specify init /tmp/speckit-test --ai <agent> --offline
 cd /tmp/speckit-test
 
 # Open in your agent
 ```
 
+If you are testing the packaged output rather than the live source tree, create a local release package first as described in [`CONTRIBUTING.md`](./CONTRIBUTING.md).
+
 ## Reporting results
 
 Paste this into your PR: