RonanCodes/skills/brief-to-live
skills/brief-to-live/SKILL.md
--- name: brief-to-live description: Take a brief/spec/task handed over in an interview or customer engagement and drive it end-to-end — grill + research → ingest to an LLM wiki vault → baseline infra → GitHub parent issues → auto-slice → autonomous build (ultracode) → a business/tech/way-of-working presentation. It's a conductor that chains existing ronan skills with human-in-the-loop checkpoints. Triggers when Ronan says he's been given a spec/brief/task to plan or implement — and SPECIFICALLY
development
Updated Jun 29, 2026
$ install --global
skillsauthnpx skillsauth add RonanCodes/ronan-skills skills/brief-to-liveInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 29, 2026, 2:30 AM220.6s1 file scanned
SKILL.md
- name:
- brief-to-live
- description:
- Take a brief/spec/task handed over in an interview or customer engagement and drive it end-to-end — grill + research → ingest to an LLM wiki vault → baseline infra → GitHub parent issues → auto-slice → autonomous build (ultracode) → a business/tech/way-of-working presentation. It's a conductor that chains existing ronan skills with human-in-the-loop checkpoints. Triggers when Ronan says he's been given a spec/brief/task to plan or implement — and SPECIFICALLY when he says he's got the housapp brief/task and needs to implement it. Phrases: "I just got the brief/spec/task", "here's the brief from <company>", "I got the housapp brief", "turn this brief into a plan", "brief to live", "let's run brief-to-live".
- category:
- workflow
- argument-hint:
- [<brief-text-or-path>] [--vault <short>] [--phase <n>] [--resume]
- allowed-tools:
- Bash Read Write Edit Glob Grep WebFetch WebSearch Skill Agent Workflow AskUserQuestion
Brief to Live
The front door for "someone handed me a brief, take it all the way to shipped + presented." This skill is a conductor — it sequences existing ronan skills and owns the human-in-the-loop checkpoints. It does NOT reimplement grill/research/slice/build logic.
Status: scaffold. Phases 1-3 are the priority to flesh out first (the planning half). Phases 6-9 reuse mature skills and need mostly glue + checkpoint logic.
When this fires
Ronan was given a brief/spec/task (interview, customer engagement, stakeholder) and
needs to plan and/or implement it. Explicit housapp trigger: "I got the housapp
brief / task and need to implement it" → run this flow against the housapp repo and
reuse the housapp wiki vault.
The 9 phases
Run phases in order. Phases 2→3 end in a natural PAUSE (Ronan goes off to do ChatGPT
deep research + Mobbin design); resume at phase 5 when material is pasted back.
Use --phase <n> / --resume to re-enter mid-flow.
1. Intake
- Capture the brief (arg, pasted text, or a file path). Save it verbatim into the engagement's working area.
- Parse it into a numbered list of discrete requirements/claims. This list is what the grill walks, item by item.
2. Grill + initial research → /ro:grill-with-docs
- Run grill-with-docs against EVERY item in the brief. Capture decisions into CONTEXT.md + ADRs as the grill skill does.
- Knowledge-gap loop: whenever an item is genuinely uncertain (domain you can't resolve from the brief + code + a quick search), STOP and proactively suggest Ronan: (a) kick off a ChatGPT deep research, or (b) find + paste articles / YouTube videos. Then pause cleanly for the paste-back (see Ingestion below).
- Ask the infra questions here too (Supabase shape, subdomain) — see phase 4.
3. Ingest → LLM wiki vault → /ro:wiki + ro:wiki-curator
- Vault rule: default = create a NEW vault per engagement (ASK Ronan for the
name first). Exception: a housapp brief reuses the existing
housappvault (~/Dev/ai-projects/llm-wiki/vaults/llm-wiki-housapp/). If unsure, ask. - Route grill output + all research into the vault via the
ro:wiki-curatoragent (single-writer librarian; keeps main context clean). - PAUSE here: tell Ronan the planning baseline is captured; he goes to run a
ChatGPT deep research and do Mobbin FE design. Offer
mcp__mobbinassistance.
4. Baseline infra (fresh per engagement)
- Vercel project (ask up front), Supabase project + subdomain (asked during the grill).
- Skills:
/ro:new-app(or the existing repo if implementing into one),/ro:supabase,/ro:domain//ro:cloudflare-dns. Fresh project + subdomain each engagement.
5. Deep research returns → re-check the solution
- Ronan pastes the ChatGPT deep-research doc (and/or YouTube/articles). Ingest into the vault (see Ingestion). Then RE-EVALUATE: does it change the solution shape? If yes, loop back to re-grill the affected items before decomposing. This gate sits deliberately before phase 6.
6. Decompose → GitHub parent issues → /ro:write-a-prd / /ro:generate-spec
- Split the solution into feature-level GitHub parent issues (one PRD per feature).
7. Auto-slice → PR-sized children → /ro:slice-into-issues
- Slice each parent into vertical-slice child issues, each buildable as one PR
(
ready-for-agent).
8. Build (autonomous) → /ro:ultracode
- Kick off ultracode (the dynamic Workflow-tool orchestrator). It reads the sliced backlog, fans out worktree agents, opens PRs, reviews, merges, deploys.
- For a CRM brief specifically, the build can invoke
/ro:create-crmas the domain generator (umbrella + component relationship).
9. Present → interview-build-session / housapp-build-session / /ro:build-session-deck
- Generate a deck themed: business value · technical approach · way of working.
- Housapp → reuse
ronan-private-skills/housapp-build-session.
Ingestion behaviours (a live loop, not one-shot)
- ChatGPT deep-research doc pasted → ingest verbatim via wiki-curator → phase-5 re-check.
- YouTube URL pasted → MUST
/ro:video-summarizeit (transcript + summary + scene screenshots) → ingest the synthesis. Never just link it. - Article/link pasted → WebFetch, summarize, ingest.
- All ingestion goes through
ro:wiki-curatorinto the engagement's vault.
Relationship to other skills
/ro:create-crm— a domain generator this skill's build phase calls for CRM briefs./ro:ultracode— the build engine (phase 8)./ro:grill-with-docs,deep-research,/ro:wiki,/ro:slice-into-issues,interview-build-session— the chained phase skills.
Open / TODO for fleshing out
- Engagement working-dir convention (where the brief + CONTEXT.md + phase state live).
- Phase-state file for
--resumeacross the phase-3 pause. - Whether phases 6-8 run AFK (then fire
/ro:pushover+/ro:telegram+ completion report at the end, per the local-factory rule).
Related Skills
RonanCodes/skills/linear-pipeline
testing
VerifiedTrustedCommunity
--- name: linear-pipeline description: The Fable orchestrator for a single dispatched Linear ticket. Holds almost no context itself; it receives `--issue <ID> --detached`, decides the stage sequence, and fans out a sub-agent per stage, passing forward only each stage's artifact (never re-derived, never inlined into its own context). Step zero, before any planning or stage routing, is a boundary triage against `canon/security-boundary.md` (#199): a match tags Ronan Connolly and stops the run, no
SKILL.mdUpdated Jul 5, 2026
RonanCodes/skills/in-your-face
development
VerifiedTrustedCommunity
--- name: in-your-face description: Capture a chat-only answer into a durable artifact (markdown + HTML, PDF when cheap) and launch it automatically so the user cannot miss it. Use when user says "in your face", "don't let me lose this", "save that answer", "make that durable", or right after answering a substantive side question (a recipe, comparison, how-to, or generated prompt) that would otherwise die with the context. category: workflow argument-hint: [--no-open] [--vault <short>] [hint of
SKILL.mdUpdated Jul 5, 2026
RonanCodes/codex
tools
VerifiedTrustedCommunity
One-shot headless OpenAI Codex CLI calls for background/admin AI tasks — summaries, classification, extraction, admin glue. The default engine for anything that runs AI constantly in the background (daemon-driven, per-event), because it bills the flat ChatGPT subscription instead of Claude usage or per-token API spend, and it keeps working while Claude is rate-limited. NEVER for coding — coding stays Claude. Use when a skill or daemon needs a cheap always-on AI call, when the user says "use codex", "ask codex", "codex as backup", or when building a background summarizer/classifier into a listener or loop. Reads auth from ~/.codex/auth.json (ChatGPT account, no API key).
SKILL.mdUpdated Jul 5, 2026
RonanCodes/warranty-check
research
VerifiedTrustedCommunity
Turn a warranty rejection, repair quote, or RMA email into a cited decision brief — legal read (NL/EU consumer law), is the part user-serviceable, live part and new-unit prices, repair-vs-DIY-vs-new economics, before-you-send-it checklist, deadlines. Use when the user pastes or screenshots a repair quote, warranty rejection, "not covered" email, onderzoekskosten fee, or asks "should I repair or replace this".
SKILL.mdUpdated Jul 4, 2026