AI Agent Workflow Collection

The artifact schema contract for docs/plans/ / — the artifact inventory, the YAML frontmatter schema and phase enum, the repos.md and prd.md schemas, the topic-consistency invariant, ticketId scope, and the design-review record mechanics. Load when authoring or validating a pipeline artifact's frontmatter, checking the design-review verdict, or writing repos.md or prd.md.

Design-document authoring procedure for the design-author agent — the repo-scope confirmation flow, the autonomous open-questions resolution rule, and the design.md document template. Loaded when a design document is drafted or revised for the adversarial design review.

Format review and feedback comments using the Conventional Comments standard. The goal is comments that are easy to understand and act on, with a collaborative tone. Use whenever the user asks for a review, critique, or feedback on anything — code, docs, RFCs, designs, drafts, PRs, or any other artifact — including indirect prompts like "thoughts on this" or "what could be better?". Defines comment format and tone, not review content, structure, or length. Labels and decorations in English; subject and discussion in the user's language.

Authoring guide for creating a new skill in this plugin, matching the conventions the existing skills already use. Establishes the three decisions every skill must make before any prose is written: how it is invoked (entry point vs building block), how it acquires its input, and how it manages the context window. Proactively invoke this skill (do NOT hand-write a SKILL.md directly) when the user asks to "create a skill", "add a new skill", "scaffold a skill", "write a SKILL.md", or describes new skill functionality they want to build.

Artifact templates and decomposition procedure for the questioner agent — the task.md and questions.md body templates, the topic-slug rules, and the multi-repo detection flow. Loaded when a user's task description is decomposed into intent and neutral research questions.

Architecture Decision Record format — capturing the context, decision, alternatives considered, and consequences of a significant technical choice. Load when recording an architectural decision or writing an ADR.

Adversarially review a technical design document with fresh context. Dispatches the built-in read-only Explore subagent (clean context, no shared history with the design-author) against docs/plans/ /design.md and presents its verdict — APPROVE, REQUEST CHANGES, or COMMENT. The Review brief doubles as the pipeline's DESIGN review gate; standalone use remains. Trigger on "review the design doc", "audit design.md", "is this design ready", or /eng-design-doc-review.

File-location search strategy for the file-finder agent — glob by naming convention, content search, import tracing, directory exploration, and manifest checks, scoped to the vocabulary in questions.md. Loaded when files relevant to an area under investigation need to be found.

Slice-by-slice execution procedure for the implementer agent — dispatch modes (initial and review-fix), the slice-execution loop, TDD discipline, blocker handling, and the scope fence. Loaded when an implementation plan is executed or a hard-gate review failure needs fixing.

Guardrails for spawning nested sub-agents from inside a Team pipeline agent (Claude Code >= 2.1.172) — loaded by researcher, implementer, code-reviewer, and security-reviewer. Nested dispatch is a context-economy optimization, never a dependency.

Tactical planning methodology for the planner agent — the plan.md document template that expands each vertical slice into file-level steps, and the tactical rules that keep the plan scannable and scoped. Loaded when a structure is translated into the implementer's playbook.

Arm a reviewer-side bounded watch loop on a pull request you are reviewing: poll GitHub in ~31-minute cycles for up to 24 hours until every review thread you opened is resolved, then cast one attributed, SHA-cited approval on your behalf and stop. The approval is the only write action — it never resolves threads, never replies, never edits code, never merges. Trigger on "approve the PR when my comments are resolved", "watch and approve", or "/pr-approve-watch" — user-invoked only; model invocation is disabled because an approval can transitively trigger an auto-merge.

Tear down local and remote branch state after a pull request is finished, in one of two modes. Mode A (merged): verify the PR actually merged, remove the branch's worktree, resync the default branch, and delete the local branch. Mode B (closed / abandoned): close the PR(s), then delete every trace — worktree, local and remote branches, planning scratch. Mode B runs ONLY on an explicit user request to abandon the work — the user says "close the PR", "abandon this", "scrap it". Never infer abandon intent from a PR merely being stale, red, or unreviewed. Trigger on "the PR was merged", "clean up the branch", "delete the merged branch", "close those PRs", or "/pr-cleanup".

Fetch every unresolved review thread on a pull request, verify each comment against the current code, and rate confidence in one recommendation per item. An item rated above 90% confidence that passes every hard rule is applied, pushed, replied to, and resolved automatically; every other item lands on a globally numbered punch list that presents and stops until the user picks actions. Explicit user authorization applies the whole batch regardless of confidence. Trigger on "address PR comments", "triage PR feedback", "handle the comments", "unresolved review comments", or "/pr-open-comments".

Verify a pull request's test plan with evidence-rated verdicts: extract every test-plan item, classify each by verification strategy, collect cited evidence per item (PASS / FAIL / PARTIAL at HIGH / MEDIUM / LOW confidence), and report a READY / NEEDS ATTENTION / NOT READY final verdict with follow-up recommendations. Read-only — it verifies claims and changes nothing. Trigger on "verify the test plan", "check the PR items", "is this PR ready", or "/pr-verify".

Optional PRD methodology — loaded by the questioner agent when a feature request is vague or complex enough to warrant a structured product spec alongside task.md. Produces a PRD artifact that downstream design-author work can ground decisions in.

Product-need reasoning lens for "make something people want" — loaded by questioner, design-author, and structure-planner to validate user demand while framing, designing, and slicing…

Todo-first progress convention for multi-step procedures — loaded by every multi-step agent to track its own steps without…

Worktree-Question-Research-Design-Structure-Plan-Implement-PR phase discipline with gate enforcement — loaded by orchestrator to govern pipeline phase transitions, artifact conventions, and…

Fowler's refactoring methodology — loaded by the implementer agent when working with existing code to recognize code smells and apply proven…

Codebase research procedure for the researcher agent — the investigation method (trace, pattern recognition, constraint discovery) and the compressed research-report output format. Loaded when neutral research questions need factual, file-referenced answers.

The authoritative severity-tier map for aggregating reviewer verdicts — gate types by reviewer, the Blocking/Major/Minor tiers with the auto-fix boundary, the no-consult rule, and the 5-round terminal cap. Load when aggregating review findings, deciding a pipeline gate, or sorting a finding into a severity tier.

Documentation-gap review methodology — applying prose-quality principles to reviews, the diff-to-docs review process (inventory, impact analysis, cross-reference), and the REQUIRED/RECOMMENDED doc-change classification. Load when reviewing a diff for documentation gaps, assessing existing docs against changed code, or classifying a documentation finding.

Security review methodology — attack-surface identification, OWASP Top 10 checks, additional vulnerability checks, and the CRITICAL/HIGH/MEDIUM/LOW severity classification ladder. Load when reviewing a diff for security vulnerabilities, auditing code for injection/XSS/secrets, or classifying a security finding's severity.