CCDawn/briefbound-skills / skills/engineering/briefbound-router
briefbound-router
VerifiedUse when Chinese-first active intent discovery, local context probing, user calibration before downstream skill selection, owner/workflow routing, continuation, permission inference, or multi-thread/conflict coordination is needed.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 10.8 KB |
| agents/openai.yaml | config | 375 B |
| references/capability-routing.md | markdown | 5.2 KB |
| references/collaboration-discovery.md | markdown | 1.7 KB |
| references/evaluation.md | markdown | 989 B |
| references/github-skill-candidates.md | markdown | 11.0 KB |
| references/harness-compat.md | markdown | 3.6 KB |
| references/output-forms.md | markdown | 2.9 KB |
| references/review-test.md | markdown | 2.6 KB |
| references/routing-practice.md | markdown | 9.8 KB |
| references/runtime.md | markdown | 3.2 KB |
| references/ui-preview-approval.md | markdown | 3.3 KB |
references/review-test.md
View on GitHub# Briefbound Router Review and Test Reference
Read this file when Briefbound Router needs a Review Matrix, evidence quality check, or test-level choice before routing to the next Briefbound stage.
## Review Matrix
Choose the perspectives the current risk demands, not a fixed role checklist:
- Core user: visible behavior, failure path, expectation mismatch.
- Maintainer: complexity, ownership, future change cost.
- Test/QA: observable contract, missing cases, flaky evidence.
- Security/privacy: permission, secrets, data retention, deletion, logging.
- Ops/support: rollout, rollback, diagnostics, recovery.
- Integrator/API user: compatibility, schema, state, public contract.
Each row must be short:
```text
Review Matrix:
- [Perspective]: Challenge: ...; Evidence: ...; Verdict: PASS / NEEDS_CLARIFICATION / NEEDS_CHANGE / ACCEPT_RISK
```
Verdict rules:
- `PASS`: evidence directly supports the behavior or route.
- `NEEDS_CLARIFICATION`: user choice or missing requirement can change behavior, scope, or risk.
- `NEEDS_CHANGE`: current contract, plan, task, or implementation is wrong.
- `ACCEPT_RISK`: residual risk is known, bounded, and explicitly accepted or recommended with clear tradeoff.
Unresolved `NEEDS_CLARIFICATION` or `NEEDS_CHANGE` blocks the next stage.
## Evidence Quality
Valid evidence comes from at least one source:
- user selection or confirmation;
- local code, docs, tests, logs, config, commit history, or project memory;
- executable test, build, lint, type check, smoke check, or structural inspection;
- reversible probe with expected observation signals;
- explicit assumption plus risk and later verification method.
Invalid evidence:
- "should work";
- "looks fine";
- "low risk";
- "will test later";
- repeating the recommendation as proof;
- saying the agent will be careful.
If evidence is thin but the risk is low and reversible, mark `ACCEPT_RISK` and state the verification anchor. If evidence is missing for a high-risk choice, mark `NEEDS_CLARIFICATION` or `NEEDS_CHANGE`.
## Test Level Choice
Use the lowest level that proves the behavior:
- Unit: rules, parsing, strategy, state decisions, pure logic.
- Integration: persistence, filesystem, multiple modules, agent workflow, config.
- End-to-end: only a real chain proves the user-visible behavior.
- Manual acceptance: visual quality, exploratory behavior, or temporarily non-automatable outcomes.
Testing anchor format:
```text
Test Anchors:
- Minimum proof: ...
- Command or check: ...
- Expected signal: ...
- Residual gap: ...
```
Do not route forward when the test anchor cannot prove the agreed behavior and no acceptable residual risk is recorded.
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 | Unverified | 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 |