Huruikagi/pc-build-planner / .claude/skills/sb-configure
sb-configure
VerifiedConfigure or explicitly update SpecBind for a project and complete the resulting aftercare. Use for an explicit SpecBind binary or project-asset update request, initial post-install review, or later changes to Agents, role models, artifact language, project instructions, templates, shared Rules, operational adapters, Steering, or existing artifacts affected by configuration changes.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 6.5 KB |
| references/adapters.md | markdown | 3.1 KB |
| references/aftercare.md | markdown | 2.4 KB |
| references/installation-and-agents.md | markdown | 2.6 KB |
| references/migrations/descriptions.md | markdown | 2.2 KB |
| references/rules.md | markdown | 1.6 KB |
| references/steering.md | markdown | 1.2 KB |
| references/templates-and-reconciliation.md | markdown | 5.1 KB |
| references/update.md | markdown | 8.2 KB |
references/migrations/descriptions.md
View on GitHub# Reconcile durable responsibility descriptions
This procedure owns the catalog entries `requirements-description`,
`design-description`, and `steering-description`. Use the new binary's migration
plan with the original pre-update version; treat its pending paths as a preview
inventory, never as write authority. Re-evaluate before each resumed batch.
1. Read the selected live artifacts through `artifact read` or `steering read`,
and templates through `template read`. If ordinary loading fails, stop with
the exact diagnostic; raw migration inspection is not authority to bypass it.
2. Read complete responsibilities and relevant current status. Propose one
non-empty single-line description per missing field in the artifact language.
Requirements describe the complete Spec behavior; Design describes technical
decisions; Steering describes project-wide decisions. Template descriptions
describe recurring responsibilities. Do not infer them from names alone.
3. Present the exact per-path diff and lifecycle effect. Obtain the separately
confirmed reconciliation scope under templates-and-reconciliation guidance.
Keep template and live changes separate; no template provenance is implied.
4. Apply only the confirmed targets through their owning authoring workflow.
Preserve IDs, durable instructions, and body semantics. Never modify
`spec.yaml`, `tasks.yaml`, Gate evidence, release history, or approval state to
make the descriptions appear current. Metadata edits can stale fingerprints;
any revalidation or approval is separately authorized ordinary lifecycle work.
5. Re-list templates and the relevant `spec list`, `artifact list <spec>`, or
`steering list`. Inspect parser, traceability, and status diagnostics for the
changed live artifacts. Re-run `migration plan --from <from> --json` with the
same target version if explicitly supplied. Only missing fields remain
pending; retain existing valid descriptions without rewriting them.
A complete probe proves metadata presence and validity, not semantic approval
or freshness. Report these separately. Recommended work may remain declined;
record its original version and remaining targets in the handoff so a later run
can resume without a persistent migration ledger.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |