SamuelBostic29
- 20 skills
- 0 followers
- 15 hours ago last updated
- ▌
- ▌ AI Next · samuelbostic29 bundleWork the next open item in a review triage list produced by /ai-comments or /hum-comments: present the finding, implement the proposed fix, answer the question, or record a deliberate defer/decline with its rationale, mark the checkpoint in the state file, and stop. One item per invocation. Use when the user says "/ai-next", "next review comment", or "keep working the review list".
- ▌ AI Post · samuelbostic29 bundleFinish a review cycle: gate on the service's unit tests + lint, post the reviewed draft replies to the PR (inline replies to Copilot and human reviewers, quote-replies to the Claude bot's Code Review header), then watch the PR's CI — diagnosing any red run, and after the user approves a fix, committing, pushing, and re-watching until everything is green. Use when the user says "/ai-post", "post the replies", or "ship the review responses".
- ▌ Jira Dc · samuelbostic29 bundleUse whenever the user names a Jira ticket on a self-hosted Jira Data Center instance — a bare key like PROJ-123, "fetch / pull / show PROJ-123", or a browse URL on the configured Jira host — or asks to "comment on / assign / progress / transition a ticket", "set a field on a ticket", or "create a Jira issue". Operates on a single ticket over the Data Center REST API (/rest/api/2, Bearer PAT — NOT Atlassian Cloud). Authenticates with a per-user Personal Access Token in a gitignored file (your home by default, or the repo when provisioned); reads run freely, writes are drafted and confirmed first.
- ▌ AI Draft · samuelbostic29 bundleDraft the 1–2 sentence PR replies for review items already worked to a checkpoint by /ai-next — both the AI queue and the human queue: one reply per resolved item, written in the PR author's voice from the item's Resolution line, saved into the state file for review — never posted. Use when the user says "/ai-draft", "draft the replies", or "write up the responses to the review comments".
- ▌ Draft Pr · samuelbostic29 bundleFinish a unit of work into a draft PR: stage only the files changed in this session, commit, push, write a description from a configurable template, and open it as a draft. Use when asked to draft/open a PR or write up changes for review after finishing work on a branch.
- ▌ Pr Stats · samuelbostic29 bundleSummarize a GitHub user's pull-request activity over a time window into one markdown report — per-PR metadata, lines/files/commits, human-reviewer-comment counts (bots filtered), a summary of each linked GitHub issue, and (when configured) a link to each PR's external-tracker ticket. Use when asked for "PR stats", a "PR report", "summarize my GitHub work", "what did I ship in the last X", or given a PR number/URL for a single-PR writeup. Defaults the author to the authed gh account and the window to the last 14 days.
- ▌ Plan Next · samuelbostic29 bundleContinue executing the next phase of a saved plan file. Use when asked to "continue the plan", "do the next phase", "pick up where we left off" against a markdown plan containing "## Implementation phases" (commonly *plan*.md) — typically at the start of a fresh session. Finds the first phase not marked COMPLETED, implements exactly that one, records an Implemented summary, marks it COMPLETED, and stops.
- ▌ Plan Save · samuelbostic29 bundleSave and structure a plan for iterative execution across sessions. Use right after plan mode (or a planning conversation) produces a plan worth executing over multiple sessions — "save this plan", "write the plan to a file", "make this plan trackable/persistent". Restructures the plan into a persistent markdown file with a Context section and phase headings that plan-next executes one at a time; asks where to save, preserves every technical detail.
- ▌ Call Trace · samuelbostic29 bundleTrace the full call chain in both directions — callers (upstream) and callees (downstream) — around a target piece of code, reading whole method bodies for deep context. Use when asked to "get a full/complete understanding", to trace callers, assess blast radius, or understand how something is used before changing shared or foundational code, or when working through PR review feedback.
- ▌ AI Comments · samuelbostic29 bundlePull the AI reviewer comments (GitHub Copilot inline comments + Claude review-bot comments) from a pull request and triage them into a worked list: categorize each finding as SHOULD FIX or NITPICK with a confidence rating, ask about anything under 85% confidence, and save the list to a local state file for /ai-next to work through. Use when the user says "pull the AI comments", "triage the copilot/claude comments", "/ai-comments", or pastes a PR link asking to go through the AI review feedback.
- ▌ Dto Mapping · samuelbostic29 bundleGenerate a family of DTOs and hand-written mapping methods for a .NET entity — detail/list/reference read DTOs, create/update input DTOs, and ToDto()-style mappers. Use when asked to add DTOs for an entity, build a DTO layer, expose an EF Core / domain model through an API surface, or write manual entity↔DTO mapping. Reads the model first, recommends only the variants that fit, and follows the conventions the codebase already uses instead of imposing its own.
- ▌ Plan Review · samuelbostic29 bundleReview a saved plan with convergence-oriented discipline — verdict first, blockers capped, "I don't understand" converted to questions instead of findings. Use when asked to "review the plan", "sanity-check the plan", or for a fresh-eyes second opinion on a saved plan file before executing it; reads prior review entries so repeated rounds converge instead of re-litigating. Designed to avoid the fresh-eyes nit-list pattern where every review produces 6-8 items regardless of plan maturity.
- ▌ Pr Comments · samuelbostic29 bundleTriage the review feedback on a pull request — human reviewers and AI/bot reviewers alike — into a judged task list. Use when asked to "pull the comments from my PR", "look at the review feedback", "work through the PR comments", or after opening a PR that receives an automatic AI review. Collects every unresolved comment, judges each against repo facts, and verdicts it ACT / DISMISS / HUMAN with cited evidence. It does not reply on GitHub and does not apply fixes.
- ▌ Hum Comments · samuelbostic29 bundlePull the HUMAN reviewer comments from a pull request and triage them into a worked list: categorize each as SHOULD FIX, NITPICK, or QUESTION with a confidence rating, ask about anything under 85% confidence, and save the list to the human-review state file for /ai-next to work through. Use when the user says "pull the human comments", "triage the reviewer feedback", "/hum-comments", or pastes a PR link asking to work through what human reviewers said.
- ▌ Skill Builder · samuelbostic29 bundleTurn a brief problem statement plus optional repo context into a complete, repo-quality skill scaffolded from the template. Use when asked to build, create, or scaffold a new skill, or when someone describes a recurring task they want handled as a reusable skill. Researches the repo, scopes to one job, fills every template layer, scaffolds evals — then stops for review.
- ▌ Review Session · samuelbostic29 bundleSpin up a fresh, INTERACTIVE Claude Code session in a separate terminal to review the whole branch's changes vs the base (every commit over the base plus uncommitted edits) with zero context from the work that produced them. Use when asked to "review my changes in a fresh/separate session", "cold review before I open the PR", "spin up another Claude to review this", or "get an unbiased second pair of eyes on this branch". Hands the reviewer the exact diff automatically; the review happens in the new window, not here.
- ▌ Meeting Summary · samuelbostic29 bundleUse when the user provides a meeting reference — a SharePoint recording URL, a Teams meeting/join link, or a meeting named by title or date — and wants it summarized, or asks to "summarize the meeting", extract decisions, or pull action items from a recorded meeting. Fetches the calendar event and transcript via the Microsoft 365 MCP tools and writes structured markdown notes (one meeting note plus per-project docs) into the meetings notes repo, organized by meeting series then date. Transcript-grounded only — never summarizes a meeting it could not fetch a transcript for.
- ▌ Plan From Issue · samuelbostic29 bundleTurn a GitHub issue (plus an optional story ticket) into a saved, phase-structured implementation plan: fetch the issue, synthesize the ask, ground it in the codebase via the call-trace skill, then persist the plan via plan-save. Use when given an issue URL or repo + issue number and asked to "gather context for this issue", "start/build a plan for this ticket", "get this story ready to implement", or "/plan-from-issue". Stops once the plan is saved — execution belongs to plan-next.
- ▌ Validator Generator · samuelbostic29 bundleGenerate a FluentValidation validator for a .NET DTO or command — create, update, delete, shared-save, or import variant — with rules grounded in the DTO's real properties and the repo's existing validator conventions. Uniqueness and dependency checks go through an adopter-owned abstraction, so FluentValidation stays the only named third-party dependency. Use when asked to write/generate/add a validator or "add validation for <DTO>".