Conversation
There was a problem hiding this comment.
Pull request overview
Updates the quality-playbook skill to v1.2.0 by expanding its guidance around regression-test generation from review findings, and adding new analysis areas (state machine completeness + missing safeguards) to improve defect discovery during quality playbook generation.
Changes:
- Adds a “Phase 2” protocol for writing regression tests that confirm BUG findings.
- Adds references for state machine tracing patterns and missing safeguard detection.
- Bumps the skill version to 1.2.0 and updates the skills index entry accordingly.
Reviewed changes
Copilot reviewed 4 out of 4 changed files in this pull request and generated 3 comments.
| File | Description |
|---|---|
| skills/quality-playbook/references/review_protocols.md | Adds regression-test generation protocol after code review findings. |
| skills/quality-playbook/references/defensive_patterns.md | Adds state machine patterns + missing safeguard patterns to the defensive patterns reference. |
| skills/quality-playbook/SKILL.md | Updates skill description/version and adds step 5a + regression-test phase reference. |
| docs/README.skills.md | Updates the quality-playbook row description to mention regression-test generation. |
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
aaronpowell
left a comment
There was a problem hiding this comment.
Can you re-run the script to generate the README as something doesn't look right - the PR is removing the skill from the README
Thanks, Aaron. I reran the script, hopefully it all looks okay now. |
| --- | ||
| name: quality-playbook | ||
| description: "Explore any codebase from scratch and generate six quality artifacts: a quality constitution (QUALITY.md), spec-traced functional tests, a code review protocol with regression test generation, an integration testing protocol, a multi-model spec audit (Council of Three), and an AI bootstrap file (AGENTS.md). Works with any language (Python, Java, Scala, TypeScript, Go, Rust, etc.). Use this skill whenever the user asks to set up a quality playbook, generate functional tests from specifications, create a quality constitution, build testing protocols, audit code against specs, or establish a repeatable quality system for a project. Also trigger when the user mentions 'quality playbook', 'spec audit', 'Council of Three', 'fitness-to-purpose', 'coverage theater', or wants to go beyond basic test generation to build a full quality system grounded in their actual codebase." | ||
| description: 'Explore any codebase from scratch and generate six quality artifacts: a quality constitution (QUALITY.md), spec-traced functional tests, a code review protocol with regression test generation, an integration testing protocol, a multi-model spec audit (Council of Three), and an AI bootstrap file (AGENTS.md). Includes state machine completeness analysis and missing safeguard detection. Works with any language (Python, Java, Scala, TypeScript, Go, Rust, etc.). Use this skill whenever the user asks to set up a quality playbook, generate functional tests from specifications, create a quality constitution, build testing protocols, audit code against specs, or establish a repeatable quality system for a project. Also trigger when the user mentions 'quality playbook', 'spec audit', 'Council of Three', 'fitness-to-purpose', 'coverage theater', or wants to go beyond basic test generation to build a full quality system grounded in their actual codebase.' |
There was a problem hiding this comment.
Just figured out why it's been dropped from the README, it's failing to parse the frontmatter because it's now using ' not " and then it's not escaping parts of the description.
Can you ensure things like 'quality playbook' are properly escaped so that it will generate the entry in the readme (I'll see if I can improve the scripts to surface that error up)
|
Thanks for following up on this. The branch got into a bad state from a
messy rebase, I'll open a clean PR from a fresh branch and then close this
PR once the new one is open.
…On Mon, Mar 30, 2026 at 7:43 PM Aaron Powell ***@***.***> wrote:
***@***.**** requested changes on this pull request.
------------------------------
In skills/quality-playbook/SKILL.md
<#1212?email_source=notifications&email_token=ABZLBCNRDFC6LG2N64WWWU34TMBDDA5CNFSNUABKM5UWIORPF5TWS5BNNB2WEL2QOVWGYUTFOF2WK43UKJSXM2LFO4XTIMBTGM4DGMBZGA3KM4TFMFZW63VGMF2XI2DPOKSWK5TFNZ2K64DSL5ZGK5TJMV3V6Y3MNFRWW#discussion_r3012708951>
:
> @@ -1,9 +1,9 @@
---
name: quality-playbook
-description: "Explore any codebase from scratch and generate six quality artifacts: a quality constitution (QUALITY.md), spec-traced functional tests, a code review protocol with regression test generation, an integration testing protocol, a multi-model spec audit (Council of Three), and an AI bootstrap file (AGENTS.md). Works with any language (Python, Java, Scala, TypeScript, Go, Rust, etc.). Use this skill whenever the user asks to set up a quality playbook, generate functional tests from specifications, create a quality constitution, build testing protocols, audit code against specs, or establish a repeatable quality system for a project. Also trigger when the user mentions 'quality playbook', 'spec audit', 'Council of Three', 'fitness-to-purpose', 'coverage theater', or wants to go beyond basic test generation to build a full quality system grounded in their actual codebase."
+description: 'Explore any codebase from scratch and generate six quality artifacts: a quality constitution (QUALITY.md), spec-traced functional tests, a code review protocol with regression test generation, an integration testing protocol, a multi-model spec audit (Council of Three), and an AI bootstrap file (AGENTS.md). Includes state machine completeness analysis and missing safeguard detection. Works with any language (Python, Java, Scala, TypeScript, Go, Rust, etc.). Use this skill whenever the user asks to set up a quality playbook, generate functional tests from specifications, create a quality constitution, build testing protocols, audit code against specs, or establish a repeatable quality system for a project. Also trigger when the user mentions 'quality playbook', 'spec audit', 'Council of Three', 'fitness-to-purpose', 'coverage theater', or wants to go beyond basic test generation to build a full quality system grounded in their actual codebase.'
Just figured out why it's been dropped from the README, it's failing to
parse the frontmatter because it's now using ' not " and then it's not
escaping parts of the description.
Can you ensure things like 'quality playbook' are properly escaped so
that it will generate the entry in the readme (I'll see if I can improve
the scripts to surface that error up)
—
Reply to this email directly, view it on GitHub
<#1212?email_source=notifications&email_token=ABZLBCNQJIERLCNFTT37D3D4TMBDDA5CNFSNUABKM5UWIORPF5TWS5BNNB2WEL2QOVWGYUTFOF2WK43UKJSXM2LFO4XTIMBTGM4DGMBZGA3KM4TFMFZW63VGMF2XI2DPOKSWK5TFNZ2L24DSL5ZGK5TJMV3V63TPORUWM2LDMF2GS33OONPWG3DJMNVQ#pullrequestreview-4033830906>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/ABZLBCM7LMEUKA5L66YJJWD4TMBDDAVCNFSM6AAAAACXDUPWJWVHI2DSMVQWIX3LMV43YUDVNRWFEZLROVSXG5CSMV3GSZLXHM2DAMZTHAZTAOJQGY>
.
You are receiving this because you authored the thread.Message ID:
***@***.***>
|
|
Closing in favor of #1238 (clean branch, single commit). |
Summary
What's included
skills/quality-playbook/SKILL.md— main skill definitionskills/quality-playbook/references/— defensive patterns reference, test patterns referenceskills/quality-playbook/LICENSE.txt— license