Writing & Editing

Use on Windows for unexpected DSH sandbox access denials: workspace writes or listing fail, or an ordinarily readable path cannot be read. One bundled command inspects the path and every ancestor and repairs the ACL problems it proves in that same run. Expected confinement denials need no ACL repair.

Discovers and injects project-specific coding guidelines from .trellis/spec/ before implementation begins. Reads spec indexes, pre-development checklists, and shared thinking guides for the target package. Use when starting a new coding task, before writing any code, switching to a different package, or needing to refresh project conventions and standards.

Writes, optimizes, and debugs C++ applications using modern C++20/23 features, template metaprogramming, and high-performance systems techniques. Use when building or refactoring C++ code requiring concepts, ranges, coroutines, SIMD optimization, or careful memory management — or when addressing performance bottlenecks, concurrency issues, and build system configuration with CMake.

Use when given a FICC or macro topic and a large corpus (research library, data, old drafts) and asked for a research report that lays out the lines of analysis, organizes material and supports decisions: screen material, form views, deliver a view outline (FICCOutline format) and an index of main materials and data; placement, relations and writing then go to the ficc-voice relay. Not for monthly short pieces, Q&A or data lookups, or rewriting finished articles (ficc-voice). Keywords: 专题研究报告, 主线支线, 脉络, 组织材料, 协助决策, 给题目和语料, 更新上一版判断, 宏观题目, 语料, 研报库, 旧稿, 观点提纲. Not for: 月报短文, 问答取数, 改写已成的文章.

Four-seat relay for Chinese FICC writing: ficc-outliner (outline, placement), ficc-structurer (relations), ficc-composer (paragraphs), ficc-writer (sentences, wording). For research articles, monthly letters, market commentary, lecture notes, case scripts, turning recordings into written text; not finance Q&A, data lookups or calculations. Keywords: 中文 FICC 文稿, 研究文章, 月报, 市场评论, 讲义, 案例讲稿, 录音稿书面化. Not for: 普通金融问答, 取数, 计算.

Orchestration pattern for AI coding agents — keep the judgment on the strongest model, delegate everything else by default to cheaper models through self-contained briefs. Works on Claude Code, Antigravity and ChatGPT/Codex; the model for each tier is set in one editable block at the top. Use on any task that involves reading, researching, or writing more than a couple of lines, or when asked to delegate, use subagents, work in parallel, save tokens, manage context, or save the expensive model for judgment. Includes model tiers per AI system, decomposition into units, a named-worktree convention (one per writer), audit tiers by risk, and the context rules — what to keep out, what to write to disk, when to compact. The brief is the deliverable; it must carry what a weaker model would not think of on its own.

End-to-end multi-agent Software Factory (DISCOVER -> PLAN -> CHECKS -> BUILD -> VERIFY) with a Thin-Orchestrator subagent-per-phase architecture across Antigravity, Claude Code, and Codex. Freezes obligations with EARS criteria and proof-backed checks, delegates every heavy phase to fresh isolated subagents to protect the main context window, and gates completion with an independent Verifier. Use when the user says "software-factory", "discover feature", "plan feature", "specify feature", "write the checks", "build this plan", or "verify work".

Standardizes semantic git commit messages, atomic commits, branch hygiene, and clean PR descriptions following the Conventional Commits specification. Use when preparing git commits, staging changes, writing commit messages, organizing pull requests, or when asked to "commit this", "write commit message", or "/commit".

Create new Agent Skills and validate existing SKILL.md files against the Agent Skills open standard (agentskills.io). Use when the user wants to write, scaffold, lint, check or fix an agent skill, or asks whether a SKILL.md is valid. Generation uses Google Gemma 4 (open-weight) via the Gemini API; validation works offline.

>- Scaffold Amazon Bedrock AgentCore resources as infrastructure as code: a Runtime (ECR repository, service role, `aws_bedrockagentcore_agent_runtime` with a JWT authorizer and lifecycle settings), a Gateway (role, JWT authorizer, pinned MCP revisions, one target), Identity (Cognito M2M client plus an OAuth2 credential provider with write-only secrets) or Memory (memory, strategies, customer-managed key). Terraform modules are the default and the recommendation; a TypeScript CDK stack with the `aws-bedrockagentcore` L1 constructs and the AgentCore CLI (`@aws/agentcore`) commands are offered for teams already on them. Every write is shown as a plan first (`--dry-run`), existing files are never overwritten without `--force`, and nothing is planned or applied. Use when asked to "create an AgentCore runtime", "scaffold a gateway", "add AgentCore memory", "write the Terraform for AgentCore", "start a new AgentCore stack", or "give me the CDK for this". Don't use for a gateway in front of an existing Lambda, HT...

Use when writing, reviewing, debugging, or modernizing Go code in a module whose `go.mod` declares `go 1.27`.

Write a pull request title and description from the actual diff and commits, with what changed, why, how it was tested and what to review. Use when asked to write or improve a PR description.

Write a short parent-facing class report (date, belt/sprint/lessons, student names, and a 150-word summary of what students learned) from lesson plans or a deck made with lesson-generator. Use when a teacher asks for a class report, parent update, parent message, or parent email after teaching a lesson. Not for building slides (use lesson-generator).

Generate a 7-day LinkedIn content plan from a theme, audience, and pillars. Produces per-day post pillar, format, hook type, CTA, posting time, daily comment targets, and a weekly inbound-readiness check. Use when the user wants to plan a week or month of content, not draft a single post (use linkedin-post-writer).

Plan, draft, audit, and publish LinkedIn posts and comments. Use when the user wants to write a viral LinkedIn post, draft a comment or reply on any LinkedIn post URL, audit a draft against 2026 algorithm heuristics, remove AI tells, extract hook formulas from viral posts, or plan a week of content. Powered by the Publora API for publishing. User provides post/comment URLs, skill drafts content, user approves, then publishes.

>- Rules, style standards, and audience guidelines for writing and updating Diosix documentation in docs/ and README.md. Activate this skill whenever writing new documentation, updating CLI or architecture docs after code changes, or auditing documentation against docs/style-guide.md.

>- Rules, idioms, and enterprise hypervisor standards for writing Zig 0.17, RISC-V assembly, and system software in Diosix. Activate this skill whenever writing, refactoring, or planning M-mode hypervisor code, S-mode emulation code, or U-mode userland tools (diosix-ctl, diosix-gui, diosix-config, guest-shim).

Multi-agent project framework — one brainstorm agent scopes a new project and writes per-part briefs; one coordinator (no real work) dispatches, stops and resumes; N part agents implement in parallel, talking only through a shared status board and rare one-line messages. Use when the user says "you're the brainstorm agent", "you are the coordinator", "you are part N" / "agent task N" / "task N", "start a new project with agents", "next wave", or when a repo has a `team/` folder and a session is told its role. Not for single-session tasks.

Write business prose that gets action. Use for drafting, editing, e-mail, memos, letters, decks, speeches, plans, reports, proposals, sales/fund-raising, resumes. Combines Thompson clarity, Roman/Raphaelson effectiveness, Ogilvy persuasion.

>- Write Instagram DMs that get replies - the keyword delivery, the first message to someone who engaged, the collab pitch, and the two follow-ups. Use when the user says "DM this person", "what do I send them", "outreach message", "how do I follow up", "pitch this brand", or is reaching out to someone specific.

Sets up and manages UptimeLens uptime monitoring through the UptimeLens MCP server — create HTTP/HTTPS monitors, recommend what to monitor after a deploy, pause or resume checks, schedule maintenance windows to mute deploy noise, model monitor dependencies, and open, update or resolve incidents, then write up the postmortem and its follow-up actions. Use when the user mentions adding or creating a monitor, monitoring a URL or a newly deployed service, what to monitor after deploying, pausing or resuming a monitor, scheduling a maintenance window, checking what is down or what the uptime was, or opening, updating, resolving or writing a postmortem for an incident.

Create, audit, or maintain implementation-grounded developer documentation for software repositories. Use for README, onboarding, setup, configuration, architecture, API reference, deployment runbooks, troubleshooting, undocumented environment variables, and stale documentation. Inspect code and verify procedures; do not use for marketing copy or implementation changes alone.

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.

Hard rules, templates, ffmpeg commands and failure diagnosis for authoring ASS/SSA subtitles and burning them with libass on this machine. Load this before writing any ASS file, when a burn "succeeds" but no text appears, when text is misplaced/too big, when \p1 drawings are offset, or when you need the transparent-overlay export recipe. Contains the exact pitfalls hit in this project (timestamp format, style colour trailing ampersand, fontsdir, drawing anchor, chained \t, Permanent Marker sizing).