agents: add premium-analytics implement/verify/regression skills + governance#49083
Open
dognose24 wants to merge 1 commit into
Open
agents: add premium-analytics implement/verify/regression skills + governance#49083dognose24 wants to merge 1 commit into
dognose24 wants to merge 1 commit into
Conversation
…vernance Adds the agent skill files that drive end-to-end task implementation against the premium-analytics package, plus minimal governance: .agents/skills/ (skill definitions, Anthropic-style flat md): * premium-analytics-implement-task.md — Step-by-step orchestrator: pre-flight, branch, implement, build, UI verify, regression-inject, commit, push, open PR, kick off review-cycle, Step 10 invariant capture. Accepts a local scratch md path or a Linear issue id (the latter is a Phase-2 forward target documented in the skill). * premium-analytics-verify-ui.md — wp-verify Playwright verification flow (default backend for Step 4 above). Host- and container-runnable; WP_VERIFY_INSTANCE-aware for parallel agent workspaces. * regression-injection.md — generic regression-injection skill (Step 5 above). Backend-agnostic via BUILD_COMMAND / VERIFY_COMMAND env vars. .claude/commands/ — four single-line slash-command bindings that point Claude Code's command surface at the skill files above. Governance: * .agents/SKILL-NAMING.md — naming convention for skills (<package-or-area>-<verb> noun) and pointers to the canonical skill directory. * .agents/check-skill-registration.sh — pre-merge lint that ensures every .agents/skills/*.md has a matching .claude/commands/*.md binding, so a renamed skill can't silently drop its slash command. References tools/ai-sandbox/ from inside skill bodies (verify-ui's wp- verify orchestrator, regression-injection's BUILD_COMMAND default). That subsystem ships as a parallel PR — see "Related PRs" in body. 🤖 Generated with [Claude Code](https://claude.com/claude-code)
This was referenced May 22, 2026
Contributor
|
Thank you for your PR! When contributing to Jetpack, we have a few suggestions that can help us test and review your patch:
This comment will be updated as you work on your PR and make changes. If you think that some of those checks are not needed for your PR, please explain why you think so. Thanks for cooperation 🤖 |
github-actions
Bot
added
the
OSS Citizen
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.
Proposed changes
Adds the agent skill definitions that drive end-to-end task implementation against the premium-analytics package, plus minimal governance to keep the skill set discoverable.
Skills (
.agents/skills/, Anthropic-style flat md)premium-analytics-implement-task.md— orchestrator: pre-flight checks, branch fromfork/trunk, implement, build, UI verify, regression-inject, commit, push, open PR, kick off review-cycle, Step-10 invariant capture. Accepts either a local scratch md path (current) or a Linear issue identifier (target state).premium-analytics-verify-ui.md— wp-verify Playwright verification flow (default backend for Step 4 of the orchestrator). Host- and container-runnable;WP_VERIFY_INSTANCE-aware so multiple parallel agent workspaces can coexist on one host.regression-injection.md— generic regression-injection skill (Step 5 of the orchestrator). Backend-agnostic viaBUILD_COMMAND/VERIFY_COMMANDenv vars; the orchestrator passes wp-verify-flavored defaults when unset.Slash-command bindings (
.claude/commands/)Four single-line bindings pointing Claude Code's slash-command surface at the skill files above:
premium-analytics-implement-task.mdpremium-analytics-verify-ui.mdregression-injection.mdjetpack-pr-review-cycle.mdGovernance (
.agents/)SKILL-NAMING.md— naming convention (<package-or-area>-<verb>-<noun>) and canonical directory pointer, so future skill additions stay discoverable.check-skill-registration.sh— pre-merge lint enforcing that every.agents/skills/*.mdhas a matching.claude/commands/*.mdbinding. A renamed-or-removed skill can't silently lose its slash command.What this PR is / isn't
Why parallel batch
This is one of 4 PRs upstreaming accumulated work from
dognose24/jetpack:tools/ai-sandbox/subsystem (Docker + wp-verify).agents/skills/+.claude/commands/agent skills + governance.github/workflows/pr-review-cycle.ymlauto-triggered review workflowThe skills reference paths in PR #B (verify-ui dispatches
wp-verify.sh; regression-injection's defaults point at the wp-verify Playwright config). These references are runtime: with PR #B not merged, an agent running the skill would not find the wp-verify orchestrator and would error informatively at Step 4. Recommended merge order: B then C. (Practically: both PRs can be reviewed in parallel and merged in any order; the failure mode if C lands first is just an error message until B lands.)Does this pull request change what data or activity we track or use?
No. Skill files are read by AI agents at session time; nothing is shipped to any Jetpack runtime.
Testing instructions
.agents/SKILL-NAMING.md— should be self-explanatory.bash .agents/check-skill-registration.shfrom the repo root — should exit 0 (every.agents/skills/*.mdhas a matching.claude/commands/*.md)..agents/skills/*.md— confirm the Step structure is comprehensible and the env-var contracts (WP_BASE,BUILD_COMMAND,VERIFY_COMMAND,VERIFY_SKILL,WP_VERIFY_INSTANCE) are documented.🤖 Generated with Claude Code