account-rotation
Switch coding-agent accounts and verify runtime identity. Use when: the caller requests an account change; never rotate automatically to evade a quota.
Write grounded docs, READMEs, repo instructions or continuity handoffs. Use when: these documents are requested; no reports as a routine completion ritual.
$ npx -y skills add boshu2/agentops --skill doc --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/docContext preview
The summary Claude sees to decide when to auto-load this skill.
Write grounded docs, READMEs, repo instructions or continuity handoffs. Use when: these documents are requested; no reports as a routine completion ritual.
name: doc
description: 'Write grounded docs, READMEs, repo instructions or continuity handoffs. Use when: these documents are requested; no reports as a routine completion ritual.'
practices:
- wiki-knowledge-surface
- code-complete
- pragmatic-programmer
hexagonal_role: supporting
consumes:
- repo-context
produces:
- documentation
- session-handoff
context_rel: []
skill_api_version: 1
user-invocable: true
context:
window: fork
intent:
mode: task
sections:
exclude:
- HISTORY
metadata:
capabilities: [doc, initialize_missing_docs, write_session_handoff]
effects: [write_documentation, write_requested_handoff, create_requested_evidence_directory]
canonical_status: canonical
disposition: keep_specialist
tier: product
dependencies: []
output_contract: requested documentation or handoff with source references, check results and explicit gapsWrite or update the documentation the caller needs, grounded in the current repository and its accepted intent. A small explanation needs no interview, coverage ledger or separate report. Select only the mode relevant to the task.
| Need | Scope and reference | |---|---| | Explain an API, command, code-map or architecture | Inspect its consumers and source; use [code/API guidance](references/default-mode.md) or [architecture guidance](references/architecture-report.md) when useful. | | Create or improve a README | Lead with the user's problem and a working first-use path; preserve useful depth. See [README craft](references/readme-craft.md). | | Audit or scaffold OSS documentation | Compare existing docs with the requested pack. Create missing files; revise existing files only within the authorized request. See [OSS pack](references/oss-pack.md). | | Initialize missing entry documents | Create only explicitly requested missing files; report existing paths as skipped. See [setup examples](references/bootstrap/examples.md). | | Preserve a session for another context | Write the compact factual handoff described below to the caller's authorized destination. |
These are optional task shapes, not successive phases. Detailed references supply techniques and formats; they do not add interviews, approval checkpoints, reports or files beyond the accepted request. Existing authorization to revise specified documents is sufficient.
1. Identify the audience, question and existing document owner. Reuse accepted intent; ask only for missing content that materially changes the document. 2. Read the relevant declarations and verify them against code, configuration, command help or executable behavior. Use the caller's domain terminology. For a larger surface, retain enough source references to disclose what was inspected and what remains unknown; do not imply whole-repository coverage. 3. Make the smallest useful edit. Explain non-obvious rules, ordering and tradeoffs when they help the reader; a reference page need not manufacture a lesson. Preserve operator policy and history outside the authorized scope. 4. Check links, examples and the repository's applicable documentation build or validator. Remove empty claims and redundant prose; [prose guidance](references/de-slopify.md) can help when the requested output is substantial. 5. Return changed paths and check results, plus unresolved factual gaps. Write a separate report only when the caller requests one or an existing consumer requires it.
For AgentOps itself, read `docs/contracts/ubiquitous-language.md`: the product is the operations layer for agentic engineering. Preserve the distinction between that layer and caller-owned execution, work tracking and delivery.
Create only the requested missing documents, such as `PRODUCT.md`, `GOALS.md` or `AGENTS.md`; a collision is skipped, not overwritten by setup. Verify the created paths and report created, skipped and failed writes. Setup does not install tools, run `ao session bootstrap`, initialize Git or trackers, start a runtime, add hooks, or infer a repository workflow.
Standalone verdict storage at `.agents/ao/verdicts/sha256/` is created only when explicitly requested. New CDLC proof uses the caller-selected protected external non-Git evidence root; a missing route permits no checkout fallback. Preserve existing evidence and use the repository's actual source owners.
A requested handoff records end-state facts another context can verify:
remaining allowance or explicit unknowns; record whether the helper for a current HOLD incident was used when that fact matters to continuation;
identities, with separately evidenced parent/resume links and source bounds;
Follow [session associations](../cass/references/SESSION_FORMATS.md#work-to-session-associations) for those identities. End-state notes cannot replace missing startup evidence. Do not invent IDs, infer a paused goal from a report saying HOLD, assign a whole multi-work session to one task, or reset budgets and helper incidents through compaction. Preserve informative failures and withdrawn claims.
Check source, recipient/model and destination authorization before copying metadata. An opaque locator grants no access. New CDLC handoffs require the selected protected external non-Git destination; preserve legacy evidence and report missing routing without creating a fallback file. Otherwise use the caller's named location and read it back after writing.
Existing JSON under `.agents/handoff/` remains read-only evidence. `ao session handoff` writes `.agents/ao/handoff/`; `ao session rehydrate` searches both and selec
Agent work you can verify and build on. AgentOps means agent operations: applying years of DevOps experience to how coding agents plan, implement, validate, and hand off work.
Switch coding-agent accounts and verify runtime identity. Use when: the caller requests an account change; never rotate automatically to evade a quota.
Coordinate selected writers with Agent Mail messages and advisory file reservations. Use when: this adapter is requested; mail does not own tracker status.
Dispatch independent tasks to parallel workers or selected persistent roles. Use when: delegation is authorized with disjoint scopes; execution does not…
Run a supplied task in AGY Antigravity and collect its result. Use when: the caller selects AGY; never a fallback for native coding.
Search agent session logs and cited episodes with CASS. Use when: past prompts, decisions or failures may answer a question; repeated text is not a proven…