feat: add ponytail-playbook skill variant for TDD-aware projects#456
Closed
kevglynn wants to merge 1 commit into
Closed
feat: add ponytail-playbook skill variant for TDD-aware projects#456kevglynn wants to merge 1 commit into
kevglynn wants to merge 1 commit into
Conversation
New skill that inherits the 7-rung implementation ladder but defers test discipline to the host project's testing framework. On-demand activation only (no auto-activate). Supports defer: comment convention alongside ponytail:. Updates Hermes manifest, OpenClaw skills, and tests for the new skill. Co-authored-by: Cursor <cursoragent@cursor.com>
Closed
4 tasks
Author
|
Closing this one proactively — same issue as #451. This was designed for a specific integration need in a personal project (TDD-aware playbook with external test-policy deferral) and doesn't match how ponytail works as a project. The core skill's inline test philosophy is intentional, not a bug to work around. Apologies for the noise! #449 and #450 are cleaner contributions that actually improve existing skills without imposing a different usage model. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds
skills/ponytail-playbook/SKILL.md— a variant of the core ponytail skill that separates the implementation ladder from test policy.Motivation
The core ponytail skill prescribes "no frameworks, no fixtures, one assert" for testing. This conflicts with projects that have their own test-first discipline (AC-driven tests, bug reproduction tests, behavioral safety nets). The integration blocker was identified through a cross-pollination experiment between skeptic and advocate agents.
ponytail-playbook resolves this by:
defer:comment convention alongsideponytail:Changes
skills/ponytail-playbook/SKILL.mdplugin.yaml: Added ponytail-playbook to commands and skills lists__init__.py: Added ponytail-playbook to SKILL_COMMANDS dict.openclaw/skills/ponytail-playbook/SKILL.md: Generated via build-openclaw-skills.jstests/hermes-plugin.test.js: Updated expected skill listscripts/build-openclaw-skills.js: Added ponytail-playbook to build listNo changes to existing skills — this is purely additive.
Test plan
npm testpasses (71/72 — 1 pre-existing csv/pandas failure)check-rule-copies.jspasses/ponytail-playbook— verify ladder applies, test section defersMade with Cursor