ebellefontaine
UserShared AI skills and configurations
Categories
Indexed Skills (5)
no-slop-grenade
Use when drafting Slack messages, chat replies, emails, PR comments, code review responses, or any synchronous/conversational reply where the user asked a direct question. Triggers on requests to "write a Slack message", "reply to this", "respond to", "draft a message", or when about to paste long AI-generated text into a chat-style medium. Prevents dumping massive AI-generated walls of text where a human would write one or two sentences.
pjf
Professional Judgment Filter — a reusable decision module for deciding whether content from a private communication source (direct messages, private channels or group chats, email received or sent, meeting transcripts, or any other non-public exchange) may be used in a write to a more-visible destination: a task or ticket, a project tracker or board, a wiki or doc page, or a draft reply. Apply this skill whenever you process private-source content and must decide what to include. Use it in any scheduled task, capture bot, watch, digest, or follow-up drafter that reads private communications before writing to a shared or public destination. If you are about to write content sourced from a private message, email, private channel, or transcript into any destination more visible than the source — run the PJF first.
readable-references
Replace opaque spec/plan/requirement pointers with self-describing, linked references whenever writing for a human. Use this skill whenever you are about to write an identifier that points into a spec, plan, requirements doc, design doc, or task breakdown — a section number like 3.1 or 4.2.1, a requirement ID like FR001 / NFR-12 / RD-XAT1 / REQ-045, a phase or milestone like Phase 2B / P3b / Milestone 3, or a task like "P3b Task 3" — into a PR description or review comment, a source-code comment or docstring, a commit message, a task or ticket update, an ADR / README / generated doc, or any Slack/email/chat message to a person. Instead of emitting the bare code (which forces the reader to leave and hunt for its meaning), expand it to include its human-readable title and hyperlink it to the source it came from — e.g. "[Requirement 3.1: User Login via Social](link) is satisfied by this design" rather than "3.1 is satisfied by this design". Trigger even when the user never mentions links or references — any time
simplified-technical-english
Enforce ASD-STE100 Simplified Technical English (STE) in all technical documentation you write or edit. Use this skill whenever you draft, generate, or revise READMEs, specifications, design docs, architecture decision records (ADRs), runbooks, technical playbooks, API docs, configuration and setup guides, troubleshooting guides, release notes, inline code comments, or docstrings — any project documentation that describes technical aspects of a system. Apply it even when the user does not mention "STE", "controlled language", or "plain English". It keeps documentation short, active, and consistent so a global audience with basic English can read it correctly the first time. Do not apply it to marketing copy, casual chat replies, or narrative prose where a natural voice is wanted.
task-status-update
Write short, human-readable status updates on a task and record them wherever the task lives — a Jira issue, a Notion task, a GitHub or Linear issue, or a plain status post (Slack, standup, email). Use whenever work is finished or has moved and belongs on a tracked task: when an agent or the user completes a unit of work, or the user says "update the task", "post an update", "log progress", "comment on CAI-123", "mark this in review / blocked / done", "close this out", "give me a standup update", or names a task by key or link. Trigger proactively after finishing a build, PR, fix, migration, or investigation that maps to a task, even if the user never says the tracker's name — offer to record it. A good update lets a busy reader answer in ten seconds: what got done, what's left, what's blocked, what was decided, and what decision is now needed. When the work surfaces a choice the user must make, state the decision and the factual options plainly and ask — do not recommend one. Keeps updates short and free of
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.