Open canon

Take the artefacts

All 94 artefacts that run the system, as plain markdown — the same files the agents read. No sign-up, no licence theatre. They are written for one practice; the ideas travel. Start with core-operating-model if you want the shape, or skill-exec if you want to see an agent's working instructions.

94 artefacts

agent-aide

agent

Profile for Aide (label A1-DE) — the Owner-serving personal chief-of-staff: sweeps the committed cycle for what needs Aled, sizes it, and books it into his work.Hold calendar window (propose-and-confirm)

in use.md

agent-atlas

agent

Profile for Atlas (label ATL-4S, future) — planning and strategy: goals, prioritisation, and cycle commitment

in use.md

agent-forge

agent

Profile for Forge (label F0-RGE) — implementation: builds a ticket and opens a PR, never merges

in use.md

agent-pixel

agent

Profile for Pixel (label P1-XEL) — brand and design: the design system, brand identity, and visual production across the ventures

in use.md

agent-prism

agent

Profile for Prism (label PR-1SM) — review and quality: the independent verdict and good-to-merge signal

in use.md

agent-pulse

agent

Profile for Pulse (label PUL-5E) — ops and self-improvement: parity, friction capture, task health, optimisation review, and the model-and-schedule efficiency of the scheduled layer; propose-only

in use.md

agent-reach

agent

Profile for Reach (label R3-ACH) — marketing and go-to-market: strategy, content, channels, lifecycle, and discovery across the ventures

in use.md

agent-relay

agent

Profile for Relay (label R3-LAY) — delivery management: triage, routing, blocker resolution, and the post-approval merge

in use.md

agent-roster

agent

Index of the os.Claude Layer 3 fleet — the functional agents and the vertical operators, their labels, roles, and profile files

in use.md

agent-scout

agent

Profile for Scout (label SC-0UT) — pipeline: captures people and opportunities into Linear and qualifies them

in use.md

agent-sonar

agent

Profile for Sonar (label SO-N4R) — design strategy, discovery and service design: building a consulting-grade understanding of who a venture serves, the jobs they are trying to do, and how well the experience and serv…

in use.md

content-engine

agent

Three-stage content pipeline — truth capture to case study to article — governed by cos-tov throughout

proposed.md

convention-analytics

convention

Conventions for web analytics and consent in Aled's system — the consent posture chosen by site type (personal/portfolio vs commercial), the tracking approach that follows from it, and what requires human action

in use.md

convention-artefact-format

convention

The house format for every os.Claude canon artefact — the frontmatter schema and the section skeleton each artefact type follows (skill, task, routine, agent, operator, convention, core, workflow, playbook)

in use.md

convention-audit

convention

The audit apparatus Sonar uses to open an engagement — the category sets per audit type (App, Design System, Team, the technical/sourcing-feasibility audit, and the conversion-diagnostic variant) and the four-card lad…

in use.md

convention-brand

convention

The per-domain brand and identity standard for Aled's ventures — what every domain's brand definition must specify (positioning, voice, palette, type, logo, imagery, design-system pointer), with BARA as the first inst…

in use.md

convention-decision-log

convention

The tool-agnostic standard for the decision log — what it records, the index-plus-weekly-child-documents structure, the entry format, and the lifecycle (append newest-first, one entry per decision, update rather than…

in use.md

convention-github

convention

Conventions for GitHub in Aled's system — repos in scope, branch naming, PR structure, and GitHub MCP usage

in use.md

convention-lean-discovery

convention

The lean discovery kit Sonar reaches for when a full engagement-kickoff is too heavy for a first pass — a minimum-viable set of four artefacts (actor card, who-does-what map, findings + opportunities, lean prioritisat…

proposed.md

convention-linear

convention

How Aled's work is expressed in Linear specifically — the teams and projects, the issue states per workflow, the label taxonomy, the agent single-select group and its routing values (including the lowercase operator-p…

in use.md

convention-mux

convention

Conventions for Mux video in Aled's system — the per-project environment model, the setup sequence for standing up a dedicated Mux environment and least-privilege credentials, the Vercel/Sanity wiring, playback defaul…

in use.md

convention-sanity

convention

Conventions for Sanity CMS in Aled's system — projects in scope, schema setup, naming standards, field UX, and deployment

in use.md

convention-shopify

convention

Conventions for Shopify in Aled's system — store in scope, the connector-vs-theme split, product and collection naming, discounts and inventory, the ShopifyQL queries that define each KPI, and what requires human action

in use.md

convention-storybook

convention

Conventions for Storybook and visual regression in Aled's system — the build-first harvest-from-build model, the component hierarchy, the story coverage bar, design-token wiring, client-facing Chromatic publish, the F…

in use.md

convention-ticket

convention

How work is written and run as tickets in Aled's system, independent of the tracker — the standard ticket shape, the capture-then-refine-then-ready discipline, the evidence-first capture format, Pattern A folded valid…

in use.md

convention-user-modelling

convention

The shared definitions for the user-modelling toolkit Sonar uses to understand who a venture serves and why they do or don't convert — the artefacts (segment, archetype, persona, JTBD, forces, opportunity solution tre…

in use.md

convention-vercel

convention

Conventions for Vercel in Aled's system — projects in scope, deployment setup, environment variable naming, and what requires human action

in use.md

core-operating-model

core

The canonical reference for how Aled's AI operating layer is structured — the six layers (inputs, skills, scheduled, agents & operators, workflows, governance), what each is, and the rules that distinguish them

in use.md

cos-article

skill

Procedure for writing long-form articles for the careerOS writing surface

proposed.md

cos-case-study

skill

Procedure for writing cOS case studies sourced from truth captures

proposed.md

cos-tov

skill

Apply Aled's tone of voice — calm, precise, structurally confident

proposed.md

cos-truth-capture

skill

Procedure for writing a truth capture (tc.*) from a build, role, or project

proposed.md

operator-bara

operator

The Operator of the BARA vertical — owns BARA's relaunch outcome end-to-end within a granted mandate, commanding the functional fleet through Relay and reporting to the Owner

in use.md

playbook-client-onboard

playbook

The prescribed sequence for opening a new A1 client engagement — create the client project under the A1 team, frame the engagement (advisory-led by default), scaffold the per-client decision log, set up the phase/mile…

proposed.md

playbook-engagement-kickoff

playbook

The prescribed sequence for kicking off and running a Sonar engagement — lock the spine and actor, model the audience and where we win, map content and belief, blueprint the service, synthesise opportunities and gaps,…

in use.md

routine-delivery-loop

routine

Driver routine for the full Claude Code delivery loop

in use.md

skill-architecture-spike

skill

Research and specify a technical approach before any code is written, on behalf of the Forge role

in use.md

skill-attention-sweep

skill

Sweep the committed cycle for everything that needs Aled and size it

in use.md

skill-audience-icp

skill

Define and refine the target audience — ideal customer profile and segments — for a domain

in use.md

skill-brand-system

skill

Define and maintain a domain's design system and brand identity — palette, type, logo usage, art direction, photography guidelines and components

in use.md

skill-campaign-report

skill

Measure marketing performance against KPI targets and report movement in plain language

in use.md

skill-channel-ops

skill

Execute marketing on specific channels via connectors — schedule and send email, queue social posts, manage marketplace and store listings, set up discount codes

in use.md

skill-content-studio

skill

Plan and draft marketing content in a domain's own voice — email, social posts, product and listing copy, landing-page copy, ad copy

in use.md

skill-conversion-diagnostic

skill

Diagnose where qualified users leak from a venture's funnel — build the stage spine, overlay the forces-and-barriers conversion engine, and find the leaks against the one or two metrics that matter, surfacing each gap…

in use.md

skill-coordinate

skill

Cross-board PM coordination for Aled's delivery projects

in use.md

skill-creative-brief

skill

Turn a need into a creative brief and, where possible, into first assets — translating a campaign, page or product requirement into clear direction for design

in use.md

skill-design-parity

skill

Review a UI build against its intended design and write a plain-language verdict Aled can act on without reading the code

in use.md

skill-design-tokens

skill

Maintain design tokens, component libraries and the Figma-to-code bridge for a domain — the machinery that keeps design and build in sync

in use.md

skill-discovery-audit

skill

Run a discovery audit at the start of an engagement — assess a venture against a chosen category set, capture each observation as a Finding card, cluster the findings into Theme Summaries with root cause and How-Might…

in use.md

skill-exec

skill

Execute a Claude Code ticket end to end and open a pull request for review, on behalf of the Forge role

in use.md

skill-goal-review

skill

Periodic review of progress against the outcome-initiatives and their KPIs across all ventures

in use.md

skill-gtm-plan

skill

Turn a strategy and KPI tree into a go-to-market plan — channels, messages and a campaign calendar — for any domain

in use.md

skill-issue-capture

skill

Inline-callable procedure that files a Backlog ticket in Apps / os.Claude when a skill hits an unexpected problem

in use.md

skill-lifecycle

skill

Design and maintain lifecycle marketing — retention, nurture and repeat- purchase flows — for a domain

in use.md

skill-merge

skill

Merge approved pull requests on behalf of the PM agent

in use.md

skill-operating-loop

skill

The operator's standing cycle, run in the context of a single vertical — read the goal and KPIs, assess against target, decide the next best actions, dispatch through Relay to the functional fleet, escalate only at th…

in use.md

skill-operator-time

skill

Plan Aled's time against his priorities

in use.md

skill-opportunity-eval

skill

Evaluate a new opportunity — a venture, a role, a bet, a partnership — against current strategy, goals and capacity, and produce a structured decision brief

in use.md

skill-ops-retro

skill

Turn friction observed while running the operator's skills, tasks, and routines into ready-to-add canon artefacts — a new or updated skill, task, routine, convention, or agent profile the operator saves

in use.md

skill-ops-sync

skill

Audit parity between the Claude-side saved artefacts (canon) and the claude-ops repo (published mirror), and raise publish tickets where Claude is ahead so the agents site and the remote routines build from current so…

in use.md

skill-optimisation-review

skill

Periodic Pulse review that keeps Aled's tooling conventions current, his operating shape sound, and his scheduled layer efficiently run, raising proposals into the os.Claude Backlog

in use.md

skill-outreach-draft

skill

Draft personalised outreach and follow-up messages in Aled's voice for a Network contact or a Pipeline opportunity, from the context skill-pipeline-sweep already captured

in use.md

skill-pipeline-qualify

skill

Qualify Pipeline tickets from Backlog to Ready on behalf of the PM role

in use.md

skill-pipeline-sweep

skill

Run a scheduled Gmail-to-Linear sweep that captures inbound pipeline mail into Aled's Pipeline team — people into Network, opportunities into Roles

in use.md

skill-plan

skill

Prioritisation and focus management for Aled's delivery teams

in use.md

skill-prioritise

skill

Turn findings, themes, and opportunities into a scored, sequenced plan — apply the prioritisation standard (severity, or Impact × Effort × Confidence with the confidence overlay), output a ranked table and an Impact ×…

in use.md

skill-product-design

skill

Design product and UI against a design system — screens, flows and components for the digital products

in use.md

skill-qa

skill

Review a Claude Code pull request for Aled and write a plain-language verdict he can act on without reading the code

in use.md

skill-security-review

skill

Review a Claude Code pull request for security risks and write a plain-language verdict Aled can act on without reading the code

in use.md

skill-seo-discovery

skill

Improve search and discoverability for a domain — keywords, on-page and metadata, product and content structure, and discovery on the platforms that matter (web search, marketplace search, Pinterest for homeware)

in use.md

skill-service-blueprint

skill

Build a service blueprint — lay a stage spine across the evidence, customer, frontstage, backstage, and support lanes, connect the actor's traversal to the service stack behind it, colour-code confidence, and flag the…

in use.md

skill-storefront-merchandising

skill

Provide visual and merchandising design for an ecommerce storefront — product pages, collection layouts, homepage sections, lifestyle and product imagery direction

in use.md

skill-strategy-cascade

skill

Turn a venture's stated goal into a strategy cascade — one strategy statement, a small set of objectives, and a measurable KPI tree with named targets and baselines — expressed as Linear outcome-initiatives

in use.md

skill-task-health

skill

Verify the scheduled layer is healthy on two axes — behaviour (each scheduled task still produces its expected observable output) and deployment parity (every canon task/routine artefact has a live, enabled schedule,…

in use.md

skill-time-management

skill

Plan Aled's time against his priorities

in use.md

skill-triage

skill

Triage and project-manage Linear tickets in the operator's delivery projects on behalf of the Claude Code PM role

in use.md

skill-user-modelling

skill

Produce the user-modelling artefacts for a venture — segment, persona, JTBD layers, forces, opportunity solution tree, behavioural modes, scenarios — one artefact per job, grounded in research and tagged known/assumed…

in use.md

skill-visual-production

skill

Produce on-brand visual assets from a brief — social and ad creative, page and email graphics, product imagery layouts, decks and documents

in use.md

standard-prioritisation

standard

The quality bar for how Sonar prioritises — severity tiers for audit and release-gating work, Impact × Effort × Confidence scoring for roadmap and intervention work, and the known/assumed/unknown confidence overlay th…

in use.md

task-bara-operator-loop

task

Weekly thin loader that runs skill-operating-loop in the context of the BARA vertical, on behalf of operator-bara

in use.md

task-content-drain

task

Weekly Mr Pritchard content qualify pass — works through the new captures (decisions, moments, breakthroughs, opinions) and asks of each "what is this, and is it worth publishing?" Worth it → flesh into a stated posit…

in use.md

task-content-review

task

Monthly Mr Pritchard capture review — sweeps the parked captures the weekly qualify pass set aside and asks whether they now cluster, by theme, into something shareable that no single one was on its own

in use.md

task-coordinate

task

Scheduled deployment of skill-coordinate — the Relay (R3-LAY) cross-board PM coordination pass

in use.md

task-daily-report

task

Morning brief on delivery work, posted as Linear initiative status updates — one per team-mirror initiative (Apps, careerOS, A1, Mr Pritchard) — so the briefs surface in Pulse

in use.md

task-ops-sync

task

Scheduled deployment of skill-ops-sync — the Claude→claude-ops parity audit

in use.md

task-pipeline-graduation

task

Pipeline graduation (Scout) — promote surfaced:* Network contacts into the right opportunity funnel (Roles/Advisory/Pitches), link back, mark surfaced:done

in use.md

task-pipeline-qualify

task

Scheduled deployment of skill-pipeline-qualify (Scout) — qualify Pipeline Backlog tickets to Ready

in use.md

task-pipeline-sweep

task

Scheduled deployment of the Gmail→Pipeline sweep (Scout) — runs skill-pipeline-sweep once per intake (network, recruiters, roles, advisory)

in use.md

task-plan

task

Scheduled deployment of skill-plan — the weekly prioritisation and focus pass

in use.md

task-pulse-retro

task

Scheduled deployment of skill-ops-retro in drain mode — the weekly Pulse retro that turns the friction queue into ready-to-save canon artefacts

in use.md

task-strategy-review

task

Weekly Atlas strategy review — sweeps every area for a complete strategy (purpose, objectives, KPI tree with baselines and targets) and for drift, and raises a surfaced gap ticket to Aled for each thing missing or off…

in use.md

task-triage

task

Scheduled deployment of skill-triage — the Relay (R3-LAY) triage pass

in use.md

workflow-delivery-loop

workflow

The delivery workflow — the standing path every build ticket flows through, from Backlog to Done, composing the Relay, Forge and Prism behaviours across the triage, build, review and merge stages with the operator as…

in use.md

workflow-venture-operating-loop

workflow

The standing cycle an operator drives its vertical through — read goal and KPIs, assess, decide, dispatch to the functional fleet via Relay, gate at the mandate edge with the Owner, execute, report, repeat

in use.md