feat(ponytail): playbook skill + review scoping

[getappz]

• Add ponytail-playbook skill (TDD-aware, red-green-refactor)
• Register playbook in sub_skills, switcher, and config VALID_MODES
• Review scope section: default uncommitted, optional branch/range
• Closes ponytail PR audit tickets [ponytail#456] Extensible skill variants: ponytail-playbook for TDD projects #73, [ponytail#524] Review scoping: uncommitted changes, branch, or commit range #65

Summary by CodeRabbit

• New Features
  • Added a new playbook mode alongside the existing command modes.
  • Added a dedicated playbook guide describing a TDD-aware workflow, rules, and how to return to normal mode.
• Bug Fixes
  • Improved mode detection and configuration normalization so playbook is handled consistently across commands and settings.
• Documentation
  • Expanded review guidance with a clearer default diff scope and options to override it.
• Tests
  • Added coverage to verify playbook detection and routing.

[coderabbitai]

Warning

Review limit reached

@getappz, you've reached your PR review limit, so we couldn't start this review.

Next review available in: 3 minutes

Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available.
You're only billed for reviews past your plan's rate limits ($0.25/file).

How can I continue?

After more reviews become available, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews.

How do review limits work?

CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability.

For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window.

Please refer docs for additional details.

Review details

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro Plus

Run ID: c52d69d3-ce9c-45c8-ab53-7f74bdb0ebef

📥 Commits

Reviewing files that changed from the base of the PR and between c7e7ab8 and 82dde97.

📒 Files selected for processing (1)

• crates/ponytail/src/skill-review.md

📝 Walkthrough

Walkthrough

This PR adds a new "playbook" sub-skill mode to ponytail. It introduces a skill-playbook.md document, exposes it via a SKILL_PLAYBOOK constant, extends config validation and command switching to recognize "playbook", and adds a Scope section to skill-review.md.

Changes

Playbook sub-skill addition

Layer / File(s)	Summary
Playbook document and content constant crates/ponytail/src/skill-playbook.md, crates/ponytail/src/sub_skills.rs	New skill-playbook.md defines TDD-focused persona/rules/output format; SKILL_PLAYBOOK constant is added and returned by get("playbook").
Config validation and command switching crates/ponytail/src/config.rs, crates/ponytail/src/switcher.rs	VALID_MODES now includes "playbook"; detect() prefix matching and /ponytail <sub> handling route "playbook" to SwitchAction::SetMode, with a new unit test.
Review skill scope docs crates/ponytail/src/skill-review.md	Adds a Scope section describing default diff behavior and how to specify branch or explicit base/head ranges.

Estimated code review effort: 2 (Simple) | ~10 minutes

Sequence Diagram(s)

sequenceDiagram
    participant User
    participant Switcher
    participant SubSkills
    participant Config

    User->>Switcher: "/ponytail-playbook"
    Switcher->>Switcher: match prefix in sub-skill list
    Switcher->>Config: normalize_config_mode("playbook")
    Config-->>Switcher: validated mode "playbook"
    Switcher-->>User: SwitchAction::SetMode("playbook")
    User->>SubSkills: get("playbook")
    SubSkills-->>User: SKILL_PLAYBOOK content

Loading

Possibly related issues

• [ponytail#456] Extensible skill variants: ponytail-playbook for TDD projects #73: Adds the same "playbook"/"ponytail-playbook" sub-skill wiring in sub_skills.rs and switcher.rs.
• [ponytail#295] Extensible skill system — ponytail-review-uncommitted as sub-skill #55: Extends the same sub-skill/mode dispatch path in sub_skills.rs and switcher.rs by adding a new skill.

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The description is on-topic but missing the required Summary, Test plan, and Notes for reviewers sections.	Rewrite it to match the template with those three sections and include concrete test results, risk areas, and backward-compatibility notes.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title accurately summarizes the new playbook skill and review scoping changes.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch feat/playbook-and-scope

---

_{Comment @coderabbitai help to get the list of available commands.}

[getappz]

@coderabbitai review

[coderabbitai]

✅ Action performed

Review finished.

Note: CodeRabbit is an incremental review system and does not re-review already reviewed commits. This command is applicable only when automatic reviews are paused.

[coderabbitai]

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@crates/ponytail/src/skill-review.md`:
- Around line 18-22: The default review scope in the skill-review guidance
currently misses brand-new untracked files because it relies on git diff HEAD
and git ls-files; update the default scope text in the skill-review document to
explicitly include untracked files. Adjust the wording near the “Default” scope
so it instructs reviewers to consider both tracked changes and new files not yet
added, while keeping the alternate branch/range/repo guidance intact.

🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

• Push a commit to this branch (recommended)
• Create a new PR with the fixes

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro Plus

Run ID: 3e07f8d4-6c7a-47e6-ae9c-d09fa87c1eab

📥 Commits

Reviewing files that changed from the base of the PR and between 05263fa and c7e7ab8.

📒 Files selected for processing (5)

• crates/ponytail/src/config.rs
• crates/ponytail/src/skill-playbook.md
• crates/ponytail/src/skill-review.md
• crates/ponytail/src/sub_skills.rs
• crates/ponytail/src/switcher.rs

[getappz]

@coderabbitai review

[coderabbitai]

✅ Action performed

Review finished.

Note: CodeRabbit is an incremental review system and does not re-review already reviewed commits. This command is applicable only when automatic reviews are paused.