## What
Wave 2 of the AgentOps 3.0 honest-docs sweep (post-#518 audit, bead
ag-qbw). Makes the `docs/` prose match the shipped code: the daemon,
scheduler, factory, and all hooks were **DELETED** (not deprecated).
AgentOps is the in-session loop + context compiler; out-of-session
orchestration is delegated to a substrate (Gas City reference City /
Olympus). Mirrors the already-correct `docs/3.0.md`.
This makes `docs/3.0.md:150` ("the standalone
daemon/scheduler/overnight-runner surfaces are gone from ... live doc
prose") true for the enumerated wave-2 surfaces.
## Deleted (whole docs about deleted commands)
- `docs/scheduling.md` — entire `ao schedule` + `ao daemon` guide
-
`docs/contracts/{agentopsd-control-plane,agentopsd-schedule,routing-policy}.md`
- `docs/contracts/jobspec-openapi-v0.yaml`
- `docs/templates/dark-factory-schedule.yaml.example`
- `docs/design/olympus-v4-specs/*.md` — v4-port reference for the dead
Olympus → agentopsd extraction
## Reframed (prose → in-session + Gas City)
- Daemon/schedule/overnight: `agentops-3-youtube-starter-series.md`,
`agentops-3-pmf-evidence-loop.md`, `wiki-for-agents.md`,
`activation-profiles.md` (+ `profiles/README.md` profile rename),
`CI-CD.md` (overnight lane)
- Hooks → hookless + CI-as-authoritative-gate (hooks removed #511):
`knowledge-flywheel.md`, `troubleshooting.md`, `reference.md`,
`CI-CD.md`, `release-e2e-checklist.md`, `seed-definition.md`
## Catalog + cross-link cleanup (no broken links)
- `documentation-index.md` — removed deleted-doc rows + the v4 section
- `contracts/index.md` — removed deleted-contract cards
- `rfcs/0002-jobspec-openapi-v0.md` marked superseded; `SCHEMAS.md`,
`templates/README.md` cross-links fixed
## Created
- `docs/MIGRATION-3.0.md` (from the approved draft) + catalog row +
mkdocs nav entry
## Gates (green for this PR's surfaces)
- Link check: **2723 links, 0 broken**
- Contracts structural floor: **PASS (45 contracts)**
- Contract compatibility (orphans): **PASS**
- markdownlint (all changed/new files): **clean**
- `heal.sh --strict`: **All clean**
- mkdocs-strict: my new doc + nav entry build cleanly. The strict build
is **red on main for pre-existing reasons outside this scope** —
`docs/_hooks/gen_cli_reference.py` FATALs on missing `cli/docs/HOOKS.md`
(hooks removed #511, generator not updated; release-mechanics domain)
and `docs/3.0.md:172` links `../PRODUCT.md`/`../GOALS.md` (root files
outside the docs tree). Both confirmed present on `origin/main`; filed
for wave 3.
## Scope notes
- Did **not** touch `CHANGELOG.md`, `cli/`, or version files (parallel
worker owns release mechanics).
- The audit grep still matches ~40 more out-of-scope `docs/` files
(contracts/*, code-map, comparisons, narrative pages, runbooks). Filed
as **wave 3 (ag-p7j)**.
Closes-scenario: ag-qbw#doc-sweep-2
Bounded-context: BC1-Corpus
Evidence: docs/3.0.md
Role-Based Profiles
Purpose: Organize 12 domain skills into 3 discoverable profiles for different work contexts.
Version: 4.0.0 (Updated for skills-based approach)
How to Use Profiles
Profiles are documentation groupings, not executable configs. They organize AgentOps skills by domain so you can quickly find which skills are relevant to your work.
For AgentOps 3.0 workflow recipes such as product-council,
engineering-team, and always-on-substrate, see
Activation Profiles. Activation profiles are
product recipes with explicit inputs, commands, and expected artifacts; this
page remains the role taxonomy.
To use a profile:
- Find your domain in the table below
- Open the profile YAML (e.g.,
docs/profiles/roles/software-dev.yaml) to see which skills it groups together - Use those skills directly via slash commands (
/research,/plan,/implement) or by reading the SKILL.md files listed in the profile
You do not "load" or "activate" a profile — you read it to discover which skills apply to your workflow, then invoke those skills individually.
Quick Start
| You're doing... | Profile | Key Skills |
|---|---|---|
| Building apps (APIs, frontends, features) | software-dev | languages, development, code-quality |
| Operations (incidents, monitoring, deploys) | platform-ops | operations, monitoring, security |
| Writing (docs, research, patterns) | content-creation | documentation, research, meta |
The 3 Profiles
1. Software Development (software-dev)
What you do:
- Build applications (backend APIs, frontends, full-stack)
- Write code in Python, Go, Rust, TypeScript, Java
- Review code and generate tests
- Deploy with CI/CD pipelines
Skills included:
| Skill | Knowledge Areas |
|---|---|
| languages | Python, Go, Rust, Java, TypeScript, Shell (6) |
| development | Backend, frontend, fullstack, mobile, iOS, deployment, AI, prompts (8) |
| code-quality | Review, improve, test generation (3) |
| validation | Assumptions, continuous, planning, tracer bullets (4) |
| data | Engineering, science, ML, MLOps (4) |
Example workflow:
1. /research "API design for user auth"
2. Load languages skill for Python patterns
3. Load development skill for backend architecture
4. Load code-quality skill before commit
2. Platform Operations (platform-ops)
What you do:
- Respond to production incidents
- Monitor system health and performance
- Debug errors and analyze logs
- Manage deployments and infrastructure
Skills included:
| Skill | Knowledge Areas |
|---|---|
| operations | Incident response, triage, postmortems, error detection (4) |
| monitoring | Alerts/runbooks, performance engineering (2) |
| security | Penetration testing, network engineering (2) |
| validation | Assumptions, tracer bullets (4) |
| meta | Context, execution, autonomous work (6) |
Example workflow:
1. Alert fires → Load operations skill
2. Check metrics → Load monitoring skill
3. After resolution → Load meta skill for postmortem
3. Content Creation (content-creation)
What you do:
- Write documentation (technical and non-technical)
- Extract patterns from completed work
- Conduct research and analysis
- Create tutorials and examples
Skills included:
| Skill | Knowledge Areas |
|---|---|
| documentation | Create, optimize, Diátaxis audit, API docs (4) |
| research | Code, docs, history, archive, structure, specs (6) |
| meta | Context, observer, memory, retro analysis (6) |
| specialized | Accessibility, support, UX (6) |
Example workflow:
1. /research "authentication patterns in our codebase"
2. Load research skill for exploration
3. Load documentation skill for writing
4. Load meta skill for retrospective
Skills by Profile
| Skill | software-dev | platform-ops | content-creation |
|---|---|---|---|
| languages | ✅ | ||
| development | ✅ | ||
| documentation | ✅ | ||
| code-quality | ✅ | ||
| research | ✅ | ||
| validation | ✅ | ✅ | |
| operations | ✅ | ||
| monitoring | ✅ | ||
| security | ✅ | ||
| data | ✅ | ||
| meta | ✅ | ✅ | |
| specialized | ✅ |
Loading Skills
Skills load into main context with full tool access:
# Read a skill directly
Read skills/languages/SKILL.md
# Or let triggers auto-load
"I need help with Python async patterns"
# → languages skill auto-activates
Profile Files
profiles/
├── README.md # This file
├── roles/
│ ├── software-dev.yaml # Software development profile
│ ├── platform-ops.yaml # Platform operations profile
│ └── content-creation.yaml # Content creation profile
└── examples/
├── software-dev-session.md # Example dev session
├── platform-ops-session.md # Example ops session
└── content-creation-session.md # Example writing session