writing-naturally
This skill should be used when writing documentation, PR descriptions, handover docs, PEPs, Confluence pages, or any prose output. Activates when the user asks to "write a document", "create a handover", "update the docs", "write a PR description", "draft a PEP", or any task producing written content. Enforces natural, casual writing style and prevents AI-sloppy output.
What this skill does
# Writing Naturally
Enforce a natural, human writing voice across all prose output. This skill exists because AI-generated text has recognizable patterns that read as artificial. The goal is output that sounds like a developer explaining something to a colleague.
## Style Rules
### Tone
- Casual and direct, like talking to a teammate
- No sales pitch language, no hype, no filler
### Formatting
- Minimal use of dashes (em dashes, en dashes) -- one or two per document is fine, not every other sentence
- Do not number section titles
- Do not add a table of contents unless the document exceeds 5 pages
- Single blank line before code blocks, no extra whitespace padding
- Shorter paragraphs over dense walls of text
### Word Choice
- Simple, everyday words only
- Avoid: "leverage", "utilize", "facilitate", "comprehensive", "robust", "seamless", "cutting-edge", "tune empirically", "it's worth noting"
- Do not pad sentences with: "It should be mentioned that", "It's important to note", "As previously discussed"
- No emojis unless explicitly requested
### Structure
- Do not repeat the same point in different words
- Do not open with "In this document, we will explore..."
- Do not start consecutive bullet points with the same word
- Avoid balanced hedging like "On the other hand" unless genuinely presenting a tradeoff
- No superlatives without evidence
## Self-Check
Before presenting any written output, score it 1-10 for AI sloppiness:
- 1-3: natural, reads like a human wrote it
- 4-6: some tells, needs a pass
- 7-10: obvious AI output, rewrite
Target score: 3 or below. If above 3, rewrite the sloppy parts before presenting.
## When Corrected
If the user points out sloppy phrasing, fix it immediately and remember the pattern for the rest of the session. Common corrections from past sessions:
- Too many dashes
- Numbered section titles when not needed
- Vocabulary that sounds academic ("empirically", "facilitates")
- Redundant sections saying the same thing twice
- Including specific line numbers when referencing source files (e.g. "see `foo.ts` (lines 82-180)"). Line numbers go stale and scream AI-generated.
- Excessive inline source file paths. A path here and there for key entry points is fine. But when every paragraph has one in parentheses it reads like a machine dumping search results. Use short names in prose ("the cache refresh worker") and put full paths in a reference table if needed.
Related in Productivity
gitea-workflow
IncludedOrchestrate agile development workflows for Gitea repositories using the tea CLI. Use when working with Gitea-hosted repos and asking to 'run the workflow', 'continue working', 'what's next', 'complete the task cycle', 'start my day', 'end the sprint', 'implement the next task', or wanting guided step-by-step development assistance. Keywords: workflow, orchestrate, agile, task cycle, sprint, daily, implement, review, PR, standup, retrospective, gitea, tea.
microsoft-graph-gateway
IncludedRoute Microsoft Graph work in this workspace. Use when users want to read or write Outlook mail, calendar events, contacts, OneDrive or SharePoint files, Teams, Planner, To Do, users, groups, directory data, or arbitrary Microsoft Graph endpoints from VS Code. Prefer WorkIQ for common read scenarios. Use Microsoft Graph for write actions and gap-read scenarios that need exact Graph properties, filters, permissions, or endpoints.
copilotkit
IncludedUse when building with CopilotKit — setup, development, integrations, debugging, upgrading, or contributing. Routes to the appropriate specialized skill based on the task.
wordly-wisdom
IncludedProvides calibrated decision analysis using Charlie Munger-style multiple mental models, inversion, incentive mapping, circle-of-competence checks, misjudgment audits, second-order effects, and forecast updates. Use when the user asks for an oracle take, a hard call, a decision memo, a premortem, an outside view, a red-team, a sanity-check, what am I missing, think this through, or wants a strategy, hire, investment, plan, product, partnership, or major life choice analysed. Avoid for simple factual lookups or time-sensitive legal, medical, or market questions without fresh evidence.
swain-session
IncludedSession management and project status dashboard. Owns the full session lifecycle (start/work/close/resume), focus lane, bookmarks, worktree detection, and tab naming. Also serves as the project status dashboard — shows active epics, progress, actionable next steps, blocked items, tasks, GitHub issues, and recommendations. Worktree creation is deferred to swain-do task dispatch (SPEC-195). Triggers on: 'session', 'status', 'what's next', 'dashboard', 'overview', 'where are we', 'what should I work on', 'show me priorities', 'bookmark', 'focus on', 'session info'.
gandi
IncludedComprehensive Gandi domain registrar integration for domain and DNS management. Register and manage domains, create/update/delete DNS records (A, AAAA, CNAME, MX, TXT, SRV, and more), configure email forwarding and aliases, check SSL certificate status, create DNS snapshots for safe rollback, bulk update zone files, and monitor domain expiration. Supports multi-domain management, zone file import/export, and automated DNS backups. Includes both read-only and destructive operations with safety controls.