bamr87

Deploy Barodybroject to Azure Container Apps with azd and Bicep. Use when: Azure deployment, azd up, azd provision, azd deploy, Container Apps, Bicep infrastructure, production environment variables, smoke tests, or deployment troubleshooting.

Load IT-Journey brand context (values, voice, style, section guide) before drafting or editing a post or muse. Use when writing a new article, writing a short-form devops-news muse, rewriting for voice/tone, or checking that content matches a section's brand profile.

Run one incremental pass of the IT-Journey content-improvement loop. Use when asked to curate/improve content, run the daily CMS loop, work the .cms worklist, fix frontmatter/SEO/freshness across pages, or group content improvements into a PR.

Run one agentic, on-brand content-improvement pass for a single IT-Journey collection and open one gated PR. The Lane B (substantive) executor that wires the cms-curator loop to the brand-voice system. Use when asked to "improve a collection", "run the content factory", or driven by content-factory.yml in CI.

PostHog integration for any Ruby application using the Ruby SDK

Run ONE incremental pass of the IT-Journey issue autopilot — analyze open issues, group them into PR-sized batches, then either route/triage them (close stale bot-noise, decompose epics, flag for a human) or resolve one batch into a single grouped PR. Use when asked to triage issues, work the issue queue, run the issue-autopilot loop, or drive the issue-triager / issue-resolver agents. Mirrors the cms-curator loop idiom.

Consume ONE walkthrough's verified evidence and apply the smallest content-only edits that fix its VERIFIED issues, under a deterministic keep/revert gate. The fix-lane inverse of quest-walkthrough — the walker plays a slice and witnesses where it breaks; this skill repairs exactly what it witnessed, proving each edit helped with a deterministic signal (never the model's own grade). Use when asked to "fix a walked quest", run the quest fix lane, or driven by the fix arm of the quest-perfection loop. Writes only quest content; never branches, commits, or merges.

Forge a "quest-forge proposal" GitHub issue into a complete, validated epic-quest campaign in pages/_quests/codex/ and open one gated PR. Use when asked to "forge a quest from an issue", turn an epic-quest proposal into content, or driven by quest-forge.yml in CI. Composes the deterministic collector (forge_issue.py) + quest.instructions + brand-voice.

The autopilot engine for lifehacker.dev. Use when asked to "grow the site", "run the autopilot", "publish the next thing", "do an autopilot run", or to produce a new hack / tool review / field note. Reads the brand + backlog, drafts on-voice content with screenshots, files upstream bugs, and opens a PR for human review. Never pushes to main, never self-merges.

The repeatable flow for importing and REWRITING external/legacy articles into on-voice lifehacker.dev content. Use when asked to "import these posts", "rewrite the it-journey import", "bring in content from <source>", or to process a bulk-import PR (like #55) article-by-article. Triages every source file, routes it to the right collection, rewrites it through the content agents (never by hand), reuses preview images, preserves it-journey quest links, verifies with the harness, and opens ONE PR per collection in batches of 10. Never merges, never self-approves.

Reviews and improves a content pull request for lifehacker.dev. Use on a bot-authored content PR (hack/tool/post/doc) to analyze quality, completeness, and accuracy against the brand and the Prime Directive, apply small improvements directly to the PR, and backlog any larger ideas or follow-ups it surfaces. Comment-only on judgment calls; never merges, never self-approves.

The sister-site idea scout for lifehacker.dev. Use to "scout it-journey for ideas", "crawl the sister site for topics", "refill the content backlog from it-journey", or on a schedule before the content factory. Crawls a configured source site (it-journey.dev by default) along a seeded plan, reads pages via WebFetch, and — with no hand-picked topic — decides what fits the lifehacker.dev brand, proposing those topics into _data/backlog.yml each pinned to the source it-journey.dev page. Read-only on the source; opens ONE PR; never merges.

Turn a finished Claude Code thread into one honest, on-voice Field Note for the site — the narrative, the hard-won lessons, the durable concepts — then record it in the ledger. Reads the transcript, redacts every secret, opens one content PR, never merges.

Find theme UI/UX + accessibility issues and upstreamable local fixes in lifehacker.dev, and file deduped issues upstream to bamr87/zer0-mistakes so the site can focus on content.

The routine for reviewing + evaluating the repo's agents and skills — quality, consistency, least-privilege tools, overlap, and drift vs the workflows — and opening one focused improvement PR.

The DevOps manager for lifehacker.dev's CI/CD. Use when asked to "audit the pipeline", "review the CI/CD", "optimize the build", "improve throughput", "why is CI slow", or to maintain the workflows. Audits the whole pipeline for correctness, guardrail integrity, and throughput; analyzes run timings; proposes and applies improvements (tiering, caching, dedup, artifact handoff); and opens ONE pull request. Never merges, never weakens a guardrail without a dated colophon line.

Deep-analyze a GitHub issue into a client-engagement estimate — classify scope, refine the plan (approach/deliverables/acceptance), and record an agent-refined estimate in _data/engagements.yml. Use when asked to "estimate", "quote", "scope", or "price" an issue or a repo's backlog, or to review/refine a draft the estimator produced.

Read the Monitor board health data, explain why each repo needs attention, and propose the next concrete action per repo. Use to turn monitoring signals into action, or as the input step of the self-evolution loop.

Read the committed Actions analytics (_data/actions_usage.yml), explain the worst workflows (cost, effectiveness, waste), and drive the next action — dispatch the actions-review issue-filer or fix a workflow directly. Use when asked "where are Actions minutes going" or after the daily actions-usage refresh.

Run the dash drift gate and explain every failure in plain language with the exact fix. Use when CI drift-check fails or before opening a PR.

Run a focused improvement pass on a single project (code quality, docs, tests, error handling) using the matching .github/agents persona. Use when a repo needs maintenance attention or as the action step of the evolution loop.

Scaffold a new project and register it in the dash. Use when starting a new repo/app that should appear in the portfolio.

Adopt (or remove) a project directory that exists on disk under projects/ but is in neither .gitmodules nor the registry. Use when the drift gate flags a stray/unregistered project dir.

Regenerate the dash's monitoring data and the profile README project list from the registry. Use after editing _data/projects.yml or when the portfolio/README looks stale.

Add one or more topics to this knowledge-base repository. Use when: adding a new item (event, person, work, discovery, etc.) within the repo concept; unsure whether a topic deserves a knowledge-table row or a full dedicated article; bulk-adding multiple topics at once; auto-discovering coverage gaps across the concept's categories. Concept-agnostic — reads subject/taxonomy from seed.md. Orchestrates research, format selection, file creation, README linking, and session logging.

Generate and refresh the structural artifacts of this knowledge base — category index pages, a timeline, a master index/TOC, and cross-reference links. Use when: new topic files were added and indices need updating; building out repository structure beyond flat content; running a structure item from the roadmap. Concept-agnostic and idempotent — derives everything from the concept and existing content; only rewrites generated regions.

Decide what this knowledge base should grow next and update ROADMAP.md. Use when: starting a growth tick and need to choose the next 1–3 items; the backlog is low and needs refilling; reconciling completed work into Done. Concept-agnostic — reads the concept and current state from seed.md and the repo. Reads/writes ROADMAP.md only.

Publish the current working session for this repository. Use when: finishing a session and ready to commit and push changes; wanting to log session work to seed.md before committing; pushing new topics, articles, README updates, or instruction changes to GitHub. Concept-agnostic. Runs encode-seed → git status review → commit → push in one orchestrated flow.

Research a topic within this repository's concept and return structured findings. Use when: looking up items (events, people, works, discoveries, etc.) within the concept; crawling authoritative sources; verifying facts and attribution; gathering facts before deciding whether to create a knowledge-table row or a dedicated file. Concept-agnostic — reads subject/scope/source_strategy from seed.md. Does NOT write files on its own — use add-topic for that.

Keep seed.md (the repository DNA) in sync with the actual repo state. Use when: ending a growth tick; after adding content or structure; whenever the seed's inventories may have drifted from reality. Concept-agnostic. Regenerates seed.md sections 1–7 from the live repo; never touches the Evolution Log (section 8).

Generate and refresh the structural artifacts of this knowledge base — category index pages, a timeline, a master index/TOC, and cross-reference links. Use when new topic files were added and indices need updating, when building repository structure beyond flat content, or when running a structure item from the roadmap. Concept-agnostic and idempotent — derives everything from the concept and existing content; only rewrites generated regions.

Decide what this knowledge base should grow next and update ROADMAP.md. Use when starting a growth tick and needing to choose the next 1–3 items, when the backlog is low and needs refilling, or when reconciling completed work into Done. Concept-agnostic — reads the concept and current state from seed.md and the repo. Reads/writes ROADMAP.md only.

Run one incremental pass of the IT-Journey content-improvement loop. Use when asked to curate/improve content, run the daily CMS loop, work the .cms worklist, fix frontmatter/SEO/freshness across pages, or group content improvements into a PR.

Run one agentic, on-brand content-improvement pass for a single IT-Journey collection and open one gated PR. The Lane B (substantive) executor that wires the cms-curator loop to the brand-voice system. Use when asked to "improve a collection", "run the content factory", or driven by content-factory.yml in CI.

Consume ONE walkthrough's verified evidence and apply the smallest content-only edits that fix its VERIFIED issues, under a deterministic keep/revert gate. The fix-lane inverse of quest-walkthrough — the walker plays a slice and witnesses where it breaks; this skill repairs exactly what it witnessed, proving each edit helped with a deterministic signal (never the model's own grade). Use when asked to "fix a walked quest", run the quest fix lane, or driven by the fix arm of the quest-perfection loop. Writes only quest content; never branches, commits, or merges.

Forge a "quest-forge proposal" GitHub issue into a complete, validated epic-quest campaign in pages/_quests/codex/ and open one gated PR. Use when asked to "forge a quest from an issue", turn an epic-quest proposal into content, or driven by quest-forge.yml in CI. Composes the deterministic collector (forge_issue.py) + quest.instructions + brand-voice.

PostHog integration for any Ruby application using the Ruby SDK

Load IT-Journey brand context (values, voice, style, section guide) before drafting or editing a post or muse. Use when writing a new article, writing a short-form devops-news muse, rewriting for voice/tone, or checking that content matches a section's brand profile.

Run ONE incremental pass of the IT-Journey issue autopilot — analyze open issues, group them into PR-sized batches, then either route/triage them (close stale bot-noise, decompose epics, flag for a human) or resolve one batch into a single grouped PR. Use when asked to triage issues, work the issue queue, run the issue-autopilot loop, or drive the issue-triager / issue-resolver agents. Mirrors the cms-curator loop idiom.

Play a linked set of quests for one character + level end-to-end in an isolated sandbox, as if you were a learner, and write ONE evidence-based session report. Use when asked to "walk a quest", "validate a quest as an end user", "run the daily quest walkthrough", or driven by quest-walkthrough.yml in CI. Composes the deterministic planner (walkthrough_plan.py) + the agentic execute engine (agentic_validate.py) + the quest validation rubric.

Run ONE incremental pass of the zer0-mistakes issue autopilot — analyze open issues, group them into batches, then route/triage them (apply area:*/priority:* labels, flag stale bot-noise, decompose epics, leave backlog-synced issues alone) or resolve one docs batch into a single grouped PR. Use when asked to triage issues, work the issue queue, run the issue-autopilot loop, or drive the issue-triager / issue-resolver agents.

Build, launch, serve, and screenshot the zer0-mistakes Jekyll theme site locally. Use when asked to run/start/serve/preview the site or theme, take a screenshot of a page, smoke-test routes, or confirm a layout/include/sass change renders in the real running site (not just tests). Drives the live Jekyll server at localhost:4000 with a headless Chromium driver.

**WORKFLOW SKILL** — The standard branch → commit → PR flow for ANY change to Zer0-Mistakes. USE FOR: starting any code/content/docs/config change, deciding how to split mixed work, naming branches/commits, keeping generated & lock files out of feature PRs, opening a PR correctly so release tooling computes the right version bump. INVOKES: git (switch/worktree/add/commit/push), gh pr create, and the validate-build skill. DO NOT USE FOR: cutting an actual release (use the commit-publish prompt) or pure read-only investigation.

**WORKFLOW SKILL** — How the /issue-plan committee fans out four read-only lenses over the open backlog and synthesizes an ORDER-ONLY plan deterministically. USE WHEN running /issue-plan or building the planning step. INVOKES: the plan-lens-* agents (or inline personas), scripts/sync-plan.rb. DO NOT USE FOR implementing tasks (use /issue-implement) or filing them (use /repo-audit intake).

**WORKFLOW SKILL** — Review new/changed Jekyll content (Markdown under pages/**) for SEO, consistency, polish, accessibility, and technical accuracy, using PER-COLLECTION thresholds. USE FOR: reviewing a content PR before merge, auditing a post/doc/quickstart/note you just wrote, pre-publish SEO + style checks, resolving AI-content-review feedback. INVOKES: scripts/content-review.rb (deterministic tier), the content-reviewer Claude Code agent, .github/config/content_review.yml, the per-collection .github/instructions/*.instructions.md. DO NOT USE FOR: code/theme review (use /code-review), bulk front-matter-only normalization (use /frontmatter-maintainer), or releases (use commit-publish).

**WORKFLOW SKILL** — Read, draft, and post the GitHub Discussions that back the site's Giscus comment threads, so Claude Code can build conversations from page comments. USE FOR: reading the comment thread on a page, summarizing reader feedback, drafting a maintainer reply, replying to a specific comment, or seeding a discussion for a page that has none yet. INVOKES: scripts/bin/giscus-discussions (gh GraphQL engine), _config.yml (giscus.* config), pages/_docs/features/giscus-comments.md. DO NOT USE FOR: enabling/configuring the widget (edit _config.yml + see the feature doc), code/theme review (use /code-review), or content editing (use /content-review).

**WORKFLOW SKILL** — The standard for proving a UI/behavioural change works: a regression test + before/after visual evidence, attached to the PR and surfaced in release notes. USE FOR: any change under _sass/ _includes/ _layouts/ assets/ (or any user-visible behaviour); after a bug fix that changed rendering; before adding the `auto-merge` label to a fix. INVOKES: test/visual/evidence-kit.mjs, Playwright, the validate-build skill. DO NOT USE FOR: pure docs/data/config edits with no visual or behavioural effect (label the PR `skip-evidence`).

**WORKFLOW SKILL** — Validate a Zer0-Mistakes change before commit/release. USE FOR: pre-commit checks, pre-PR verification, debugging a broken build, confirming theme/include/layout/Sass/Obsidian changes work end-to-end, smoke-testing the gem, reproducing CI failures locally. INVOKES: docker-compose, bundle exec jekyll, yamllint, markdownlint, the project test runners under test/. DO NOT USE FOR: actual releases (use the commit-publish prompt) or one-off `jekyll build` invocations where you already know what to run.

Build and maintain the profile/portfolio landing page for the bamr87.github.io site — the curated showcase of GitHub repos, sites, and projects (badges, descriptions, live links, topics). Use this skill whenever the user wants to add, remove, reorder, feature, or refresh a project on their portfolio, profile, homepage, or "project dashboard"; when they mention showcasing a repo, updating project badges/stars/descriptions, or regenerating the projects list; or after shipping a new repo they'd want listed — even if they don't say the word "portfolio". Edits flow through _data/projects.yml and the generator script, never by hand-editing the rendered pages.

Frames research and explanations in financial-analyst style using filings, fundamentals, and risk-focused reasoning. Use when analyzing companies, SEC/EDGAR data, financial statements, ratios, earnings quality, credit or equity narratives, or when the user asks for investment-style analysis in this repository.

Deploy Barodybroject to Azure Container Apps with azd and Bicep. Use when: Azure deployment, azd up, azd provision, azd deploy, Container Apps, Bicep infrastructure, production environment variables, smoke tests, or deployment troubleshooting.