fjrevoredo

Applies to Mini Diarium's marketing site (`website/`) and its SEO data under `docs/seo/`. Use this recurring, data-driven review when the user has fresh (or wants to pull) Google Search Console / Bing Webmaster performance exports and asks to turn them into ranked, actionable recommendations. Triggers include "SEO performance review," "GSC data," "Search Console export," "Bing keyword report," "how are we ranking now," "what should I write next," "SEO content briefs," "striking distance," "CTR gaps," "update the SEO action plan," or "run the SEO cycle." This is distinct from `seo-audit` (technical on-page auditing): this skill analyzes performance data over time and produces content briefs and an updated action plan. If the user wants a technical/on-page audit instead, use `seo-audit`.

Applies to the static marketing site under `website/` only. Use when the user wants to audit, review, or diagnose SEO issues on that site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tags review," "SEO health check," "my traffic dropped," "lost rankings," "not showing up in Google," "site isn't ranking," "Google update hit me," "page speed," "core web vitals," "crawl errors," or "indexing issues." Use this even if the user just says something vague like "my SEO is bad" or "help with SEO" — start with an audit.

Mini Diarium's opinionated security, encryption, and privacy stance. Load when touching crypto (src-tauri/src/crypto/), auth (src-tauri/src/auth/, commands/auth/), IPC boundaries (src/lib/errors.ts, tauri.ts), auto-lock (screen_lock.rs, App.tsx idle timer), database schema/migrations (db/schema.rs), backups (backup.rs), config.json / JournalConfig, import/export, plugin sandbox (Rhai), search (intentionally stubbed), debug dump, Tauri capabilities (src-tauri/capabilities/) or CSP (tauri.conf.json), E2E isolation env vars, or anything involving passwords, keys, nonces, zeroization, or entry persistence. Also load when reviewing or proposing new features to judge against the six PHILOSOPHY.md principles and five non-negotiables.

SolidJS framework development skill for building reactive web applications with fine-grained reactivity. Use when working with SolidJS projects including: (1) Creating components with signals, stores, and effects, (2) Implementing reactive state management, (3) Using control flow components (Show, For, Switch/Match), (4) Data fetching with createResource, (5) Context API for shared state. Triggers: solid, solidjs, solid-js, createSignal, createStore, createEffect.

Spawn, probe, and stop Mini Diarium's live Windows Tauri dev app with WebView2 CDP enabled, then hand control to agent-browser for real UI inspection. Use this whenever the user wants to manually test the real desktop UI, drive the dev app, verify a bug or preference in the actual window, inspect localStorage, take a real screenshot, or "actually try it in the app" instead of relying only on unit tests or WDIO. Triggers: manually test the UI, drive the dev app, verify in the real UI, agent dev mode, spawn the dev app, open the running app and check, inspect the live Tauri window.

Route low-frequency Mini Diarium maintenance workflows to one selected runbook. Use only for manual or exceptional project workflows that are intentionally not registered as standalone top-level skills.

Create, update, review, and execute manual Markdown implementation plans when harness planning mode is not being used. Use when the user asks for a plan file, manual plan, implementation plan, execution plan, roadmap, task checklist, planning document, or agent-maintained plan with statuses, validations, milestones, approval gates, and cleanup steps.

Regenerate both npm lockfiles after any manual change to package.json. Use this skill when the user has added, removed, or bumped a dependency in package.json and needs bun.lock and package-lock.json kept in sync. Triggers: "sync lockfiles", "update lockfiles", "I edited package.json", "regenerate lockfiles". Distinct from apply-dependency-prs, which handles the PR-discovery workflow — this skill handles lockfile sync only.

Toolkit-side handoff for Calixto research preparation. Use when starting from the toolkit root and the user's topic needs clarification, normalization, or a durable brief before source gathering. This skill triages the raw question, asks targeted clarification only when needed, creates or selects a standalone workspace boundary, writes notes/research-brief.md, and hands off to the workspace-local preparation or downstream research skill.

Performs structured, reproducible research with full source-to-claim traceability inside a standalone Calixto workspace. Use when the user asks for a research report, comparison, literature scan, or any task that needs multiple cited sources. Workflow: confirm the workspace question, search the web and the right scholarly provider, extract findings (fnd_NNN), synthesize insights (ins_NNN), write a report with inline [src_NNN] citations, run strict traceability checks, and generate a manual citation-review artifact.

Produces a structured academic literature review inside a standalone Calixto workspace with full citation tracking and methodology assessment. Use when the user asks for a literature review, related-work section, systematic survey, or scholarly analysis. Emphasizes domain-appropriate scholarly search, venue assessment, citation count, quality tiers, and explicit gaps.

Normalizes a raw or underspecified research topic inside a standalone Calixto workspace before source gathering. Use when the question is ambiguous, too broad, high-stakes, time-sensitive, subjective, or missing a clear output shape. The workflow triages the request, asks targeted clarification only when needed, writes notes/research-brief.md, updates config.json.question when approved or safely assumed, and then hands off to deep-research or literature-review.

Performs a user-mediated two-agent retrospective of a completed Calixto research workspace. Use when Agent B must independently audit Agent A's research, derive a case-specific but non-leading questionnaire from that adversarial report, pause while the user gives it to Agent A in the original research session, then synthesize the report, questionnaire, and returned answers into prioritized improvements for Calixto tooling, setup, runtime, skills, scaffold, audits, documentation, or product behavior.

Teaches an agent how to create a new Calixto skill (a research workflow packaged as a directory of markdown with a SKILL.md file). Use when the user wants to add a new research skill, formalize a recurring pattern, or build a domain-specific variant of an existing skill (e.g., competitive analysis, bug triage, codebase archaeology). Covers the Agent Skills spec, skill file structure, ID conventions, validation, and examples.

Toolkit-side handoff for Calixto deep research. Use when starting from the toolkit root and the user needs a structured, cited research workflow. This skill creates a standalone workspace snapshot, switches into it, and then continues with the bundled workspace-local deep-research skill.

Toolkit-side handoff for Calixto literature reviews. Use when starting from the toolkit root and the user needs a paper-heavy review workflow. This skill creates a standalone workspace snapshot, switches into it, and then continues with the bundled workspace-local literature-review skill.

Create or maintain a skill library that groups two or more related, low-frequency Agent Skills behind one discoverable dispatcher. Use when the user wants to consolidate skills, reduce the active skill catalog, group manual runbooks, or keep exceptional workflows available without loading every skill description. Also use when deciding which skills should remain standalone versus move into a library. Triggers: skill library, skill of skills, meta-skill, consolidate skills, group skills, runbooks library, reduce active skills, skill catalog pollution, nested skills, skill dispatcher.

Evaluate a subagent by running its scenario suite as parallel subagents, scoring results against observable criteria, and producing exact FIND/REPLACE edits for any failing behaviors. Use this skill whenever the user wants to evaluate, test, score, or quality-check a subagent — even if they don't use those exact words. Triggers on: "evaluate the agent", "run evals on [agent]", "assess agent performance", "score the agent", "check if the agent works", "run the eval suite", "test the agent", "quality-check [agent]", "is the agent working correctly", or after applying fixes "did that improve things?". Also triggers proactively after an agent file is edited and the user asks "does it work now?" or similar. Triggers: evaluate agent, run evals, assess agent, score agent, test agent, quality-check, eval suite, agent performance, agent working, improve agent, rerun evals, benchmark agent.

Create, update, review, and execute manual Markdown implementation plans when harness planning mode is not being used. Use when the user asks for a plan file, manual plan, implementation plan, execution plan, roadmap, task checklist, planning document, or agent-maintained plan with statuses, validations, milestones, approval gates, and cleanup steps.

Port a repo-specific skill into a generic, reusable skill for the agent-skills library. Use this skill whenever the user asks to extract a skill from a project, generalize a skill, port a skill to another repo, convert a project-specific skill into a reusable one, or remove repo-specific context from a skill. Also use when the user mentions skill extraction, skill generalization, or creating a library skill from a project skill — even if they don't explicitly say "extract" or "generalize." If a skill exists in a project's `.agents/skills/` directory and the user wants to make it reusable across repositories, this skill should be used. Triggers: extract skill, generalize skill, port skill, convert skill, remove repo-specific, make skill reusable, skill extraction, skill generalization, library skill, repo-agnostic skill, skill from project.

Captures lessons from completed tasks and turns them into concrete improvements. Triggers proactively after high-ceremony tasks (build failures, multi-hour sessions, production incidents) and on-demand when the user asks for "post-mortem", "reflect", "improve the skill", "lessons learned", "what went wrong". Covers skills, repo artifacts (scripts, CI, configs), and process changes. For small/obvious fixes, edits directly. For structural changes, produces a plan. Use this whenever a task surfaced gaps in tooling, documentation, or automation.

End-to-end management of TODO items in a Markdown-based backlog. Covers creation with auto-assigned IDs, status tracking, archival of completed items, and format validation. Use this skill whenever the user asks to add a new TODO, check TODO status, archive completed items, validate the TODO system, or set up a new TODO backlog from scratch. Also use when the user mentions a task list, backlog, roadmap, or task tracking in a Markdown file — even if they don't explicitly say "TODO". If the repo has a `TODO.md` file or similar Markdown-based task tracking, this skill should be used to interact with it. Triggers: TODO, todo item, add todo, create todo, todo status, archive todo, validate TODO, TODO ID, TODO-0001, check TODO, todos, list todos, todo list, backlog, task tracking, roadmap, task list.

Create, update, review, and execute manual Markdown implementation plans when harness planning mode is not being used. Use when the user asks for a plan file, manual plan, implementation plan, execution plan, roadmap, task checklist, planning document, or agent-maintained plan with statuses, validations, milestones, approval gates, and cleanup steps.