skills/project/atm10/atm10-change-protocol/SKILL.md
--- name: atm10-change-protocol scope: project status: evaluated summary: Thin ATM10 overlay for bounded change execution with repo-relative route cards, public docs, commands, review checks, recovery anchors, and explicit local approval notes. invocation_mode: explicit-preferred technique_dependencies: - AOA-T-0001 - AOA-T-0002 --- # atm10-change-protocol ## Intent Use this skill to adapt `aoa-change-protocol` to an `atm10-*` repository without changing the base workflow meaning or movin
npx skillsauth add 8Dionysus/aoa-skills atm10-change-protocolInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use this skill to adapt aoa-change-protocol to an atm10-* repository without changing the base workflow meaning or moving ATM10 runtime authority into aoa-skills.
Use this skill when:
aoa-change-protocol workflow is already correct, but an atm10-* repo needs repo-relative paths, commands, or local approval notesDo not use this skill when:
aoa-dry-run-first, aoa-safe-infra-change, or aoa-approval-gate-checkatm10-source-of-truth-checkAGENTS.md, nearest nested AGENTS.md, docs/SOURCE_OF_TRUTH.md, docs/RUNBOOK.md, docs/PRODUCT_EDGE_POSTURE.md, or the exact touched local surfaceaoa-change-protocol rather than rewriting the workflowAGENTS.md for every touched pathdocs/SOURCE_OF_TRUTH.md; when runnable commands may move, read docs/RUNBOOK.md; when support claims or test tiers may move, read docs/PRODUCT_EDGE_POSTURE.mdplan -> scoped change -> verify -> report shapepython -m pytest, public-doc hardening tests, a script smoke, or an explicitly skipped check with reasonaoa-skills as owner of ATM10 perception, KAG, retrieval, service, voice, operator-panel, or safe-automation runtime truthManifest-backed techniques:
8Dionysus/aoa-techniques at cd276f040d55d490bd015b8698c7a5d594b9f875 using path techniques/execution/agent-workflows-core/plan-diff-apply-verify-report/TECHNIQUE.md and sections: Intent, When to use, Inputs, Outputs, Core procedure, Contracts, Risks, Validation8Dionysus/aoa-techniques at cd276f040d55d490bd015b8698c7a5d594b9f875 using path techniques/instruction/docs-boundary/source-of-truth-layout/TECHNIQUE.md and sections: Intent, When to use, Inputs, Outputs, Core procedure, Contracts, Risks, Validationdevelopment
Sanitize private technical material into a public-safe owner-bounded derivative, or resolve authority among authored, generated, runtime, and installed sources. Use for governed incidents, logs, configs, diagnostics, or conflicting source roles. Do not use for ordinary editing, memo/session work, direct publication, or durable-memory authority.
tools
Diagnose a reviewed recurring session/workflow failure, or carry one bounded owner repair through checkpoint, rollback, and real health verification. Use for reviewed contamination, drift, repeated route/tool failure, or an established diagnosis ready for repair. Do not use on live evidence, for vague self-improvement, or to call a proposed or merely executed change verified.
tools
Use only when a literal ref to a closed/reviewed session packet is supplied, to extract, classify, propose promotion or branching, or identify an automation opportunity. Missing, live, or unreviewed evidence must fail closed without inventing a ref. Natural closeout preservation belongs to aoa-memo-writeback. Do not use for generic summaries, progression, direct owner writes, scheduling, mutation, or telemetry authority.
testing
Turn one stable technical truth into bounded evidence through contract, coverage-audit, or property mode. Use to define a named consumer seam, audit what existing checks really constrain, or express a broad invariant after manual cases establish meaning. Compose with aoa-eval when an evaluation surface must first be found or applied. Do not use for undefined behavior, generic test plans, or green checks as whole-system proof.