@massa-ai/codex-plugin 1.54.1 → 1.55.0

package/skills/agents/architecture-specialist/SKILL.md

@@ -56,7 +56,7 @@ Provide architectural guidance by evaluating structure, suggesting boundaries, a
 - Verification Ladder: static (coupling, depth, boundary) checks; no behavioral changes.
 - Massa-ai Memory: suggest durable architecture-decision memories only when a boundary or abstraction is recommended; main agent persists.
 - Synapse: own ephemeral session when evaluation spans multiple modules with repeated searches.
-- References: `references/architecture-lenses.md`, `references/architecture-domain-lens.md`, `references/architecture-coupling-lens.md`, `references/architecture-deepening-lens.md`.
+- References (paths relative to the `massa-ai` skill directory): `references/architecture-lenses.md`, `references/architecture-domain-lens.md`, `references/architecture-coupling-lens.md`, `references/architecture-deepening-lens.md`.
 
 ## Validation Sensors
 - Every finding has a `path:line` or metric pointer.

package/skills/agents/audit-specialist/SKILL.md

@@ -72,7 +72,7 @@ All lenses share `references/audit-scope.md` (scope rules) and `references/audit
 - Verification Ladder: static checks per lens; no behavioral changes (findings-only).
 - Massa-ai Memory: suggest durable audit-pattern memories only when a lens reveals a recurring issue class; main agent persists.
 - Synapse: own ephemeral session when the audit spans multiple modules with repeated searches.
-- References: `references/audit-scope.md`, `references/audit-report-io.md`, plus the per-lens references above.
+- References (paths relative to the `massa-ai` skill directory): `references/audit-scope.md`, `references/audit-report-io.md`, plus the per-lens references above.
 
 ## Validation Sensors
 - Every finding has a `path:line` pointer.

package/skills/agents/builder/SKILL.md

@@ -58,7 +58,7 @@ Implement an approved plan or task by modifying source code with a disjoint writ
 - Verification Ladder: run the task's sensors (static + behavioral) before claiming Complete.
 - Massa-ai Memory: suggest durable code-pattern memories only when the implementation establishes a reusable convention; main agent persists.
 - Synapse: none (implementation is not a repeated-search task).
-- References: `references/agent-orchestration.md`, `references/naming-standards.md`, `references/code-annotation.md`, `references/root-cause-scripts.md`.
+- References (paths relative to the `massa-ai` skill directory): `references/agent-orchestration.md`, `references/naming-standards.md`, `references/code-annotation.md`, `references/root-cause-scripts.md`.
 
 ## Validation Sensors
 - Verification commands from the plan pass (tests, build, typecheck, lint).

package/skills/agents/context-curator/SKILL.md

@@ -58,7 +58,7 @@ Prepare the minimum high-quality Context Packet required for another agent to do
 - Verification Ladder: static checks only (file existence, reference existence).
 - Massa-ai Memory: retrieve via `recall`; do not persist unless the main agent assigns it.
 - Synapse: own ephemeral session per `references/synapse-policy.md`; pass `synapseSessionId` on every `search`.
-- References: `references/context-firewall.md`, `references/synapse-policy.md`, `references/mcp-tools.md`.
+- References (paths relative to the `massa-ai` skill directory): `references/context-firewall.md`, `references/synapse-policy.md`, `references/mcp-tools.md`.
 
 ## Validation Sensors
 - Every file in the Context Packet exists (`test -f`).

package/skills/agents/designer/SKILL.md

@@ -59,7 +59,7 @@ Own the screen: verify an existing user-facing screen against its design source,
 - Verification Ladder: behavioral (the UI module builds and its tests pass) and file-integrity (no validation asset weakened).
 - Massa-ai Memory: suggest durable memories only when a reusable screen or design-token convention is established; the main agent persists.
 - Synapse: none by default; request an ephemeral session only when the scope needs two or more related searches across the UI layer.
-- References: `references/figma-pre-analysis.md`, `references/figma-wiring.md`, `references/design-implementation.md`, `references/naming-standards.md`, `references/verification-ladder.md`.
+- References (paths relative to the `massa-ai` skill directory): `references/figma-pre-analysis.md`, `references/figma-wiring.md`, `references/design-implementation.md`, `references/naming-standards.md`, `references/verification-ladder.md`.
 
 ## Validation Sensors
 - Every design element in scope appears in the conformance table with a verdict, or the table states why the design source did not cover it.

package/skills/agents/documentation-agent/SKILL.md

@@ -56,7 +56,7 @@ Generate engineering documentation artifacts (README, ADR, RFC, changelog, KDoc,
 - Verification Ladder: static (doc-lint, stale-reference, link check); no behavioral sensors.
 - Massa-ai Memory: suggest durable doc-format memories only when a documentation convention is established; main agent persists.
 - Synapse: none (documentation is not a repeated-search task).
-- References: `references/adr-authoring.md`, `references/rfc/`.
+- References (paths relative to the `massa-ai` skill directory): `references/adr-authoring.md`, `references/rfc/`.
 
 ## Validation Sensors
 - Stale-reference scan passes (no dead links to removed files).

package/skills/agents/furps-analyst/SKILL.md

@@ -60,7 +60,7 @@ Analyze exactly one FURPS+ dimension of a PRD or ADR against its checklist secti
 - Verification Ladder: static evidence checks only — source-location proof per claim, absent-claim detection per `missing`.
 - Massa-ai Memory: suggest durable memories only when a reusable refinement pattern is discovered; the main agent persists.
 - Synapse: own ephemeral session when >= 2 searches are expected, per `references/synapse-policy.md`.
-- References: `references/furps/checklist.md`, `references/furps/report-contract.md`, `references/furps/intake.md`, `references/agent-orchestration.md`.
+- References (paths relative to the `massa-ai` skill directory): `references/furps/checklist.md`, `references/furps/report-contract.md`, `references/furps/intake.md`, `references/agent-orchestration.md`.
 
 ## Validation Sensors
 - Source-location proof (quote plus section) for every `covered`/`partial` claim.

package/skills/agents/investigator/SKILL.md

@@ -59,7 +59,7 @@ Read and understand the codebase to answer engineering questions without modifyi
 - Verification Ladder: static checks (grep, search) and file-integrity; no behavioral changes.
 - Massa-ai Memory: suggest durable architecture/dependency memories only when useful; main agent persists.
 - Synapse: own ephemeral session per `references/synapse-policy.md`; pass `synapseSessionId` on every `search`.
-- References: `references/codebase-investigation.md`, `references/agent-orchestration.md`, `references/synapse-policy.md`.
+- References (paths relative to the `massa-ai` skill directory): `references/codebase-investigation.md`, `references/agent-orchestration.md`, `references/synapse-policy.md`.
 
 ## Validation Sensors
 - Source-backed evidence for every claim (`path:line`).

package/skills/agents/judge/SKILL.md

@@ -80,7 +80,7 @@ next_step: <string>
 - Verification Ladder: every score cites a quotation; a score without a quote is a sensor failure.
 - Massa-ai Memory: suggest durable memories only for reusable evaluation failure patterns; the main agent persists.
 - Policy: the orchestrator owns dispatch, consensus arithmetic, and the final verdict; this agent owns its scores and its file only.
-- References: `references/agent-orchestration.md`, `references/audit-report-io.md` (Judge With Debate Report Contracts).
+- References (paths relative to the `massa-ai` skill directory): `references/agent-orchestration.md`, `references/audit-report-io.md` (Judge With Debate Report Contracts).
 
 ## Model Hint
 See `references/agent-orchestration.md` (Model Diversity Fallback): `metadata.model_tier`

package/skills/agents/meta-judge/SKILL.md

@@ -71,7 +71,7 @@ overall: weighted-mean
 - Verification Ladder: every criterion must be checkable by quoting the artifact — a criterion that cannot be evidenced is not a criterion.
 - Massa-ai Memory: suggest durable memories only for reusable rubric patterns; the main agent persists.
 - Policy: the main agent (judge-with-debate orchestrator) owns dispatch, YAML validation, retry, and consensus; this agent owns the specification only.
-- References: `references/agent-orchestration.md`, `references/audit-report-io.md` (Judge With Debate Report Contracts).
+- References (paths relative to the `massa-ai` skill directory): `references/agent-orchestration.md`, `references/audit-report-io.md` (Judge With Debate Report Contracts).
 
 ## Model Hint
 See `references/agent-orchestration.md` (Model Diversity Fallback): `metadata.model_tier`

package/skills/agents/mobile-specialist/SKILL.md

@@ -73,7 +73,7 @@ If none are present, refuse with: `Non-mobile target. Refusing mobile-specialist
 - Verification Ladder: platform-specific static checks when available; no behavioral changes.
 - Massa-ai Memory: suggest durable mobile-decision memories only when a platform constraint or lifecycle pattern is established; main agent persists.
 - Synapse: own ephemeral session when guidance spans multiple mobile modules with repeated searches.
-- References: `references/mobile-context.md`, `references/mobile-diagnosis.md`, `references/maestro.md`.
+- References (paths relative to the `massa-ai` skill directory): `references/mobile-context.md`, `references/mobile-diagnosis.md`, `references/maestro.md`.
 
 ## Validation Sensors
 - At least one detection signal is confirmed present before guidance is given.

package/skills/agents/navigator/SKILL.md

@@ -66,7 +66,7 @@ The user's codebase is **already indexed** by massa-ai. The first move on any qu
 - Orphaned-dims recovery: if a vector `search` returns 0 results while other dim tables hold chunks for the project, report to the parent agent that `index` with `forceReindex=true` is required. Do not run it.
 - Context Firewall: summarize search output; return only `path:line` pointers and findings.
 - Massa-ai Memory: suggest durable navigation facts (entry points, ownership boundaries) only when reusable; the main agent persists.
-- References: `references/mcp-tools.md`, `references/codebase-investigation.md`, `references/synapse-policy.md`, `references/context-firewall.md`.
+- References (paths relative to the `massa-ai` skill directory): `references/mcp-tools.md`, `references/codebase-investigation.md`, `references/synapse-policy.md`, `references/context-firewall.md`.
 
 ## Validation Sensors
 - Every claim carries a `path:line` or symbol pointer.

package/skills/agents/plan-critic/SKILL.md

@@ -79,7 +79,7 @@ Never receives full conversation context.
 - Verification Ladder: every challenge names the concrete sensor that would settle it.
 - Massa-ai Memory: suggest durable memories only for reusable failure modes or rejected approaches; the main agent persists.
 - Policy: the main agent owns mode selection, synthesis, plan revision, and the Evidence Gate; this agent owns the critique only.
-- References: `references/agent-orchestration.md`, `references/the-fool/`, `references/verification-ladder.md`.
+- References (paths relative to the `massa-ai` skill directory): `references/agent-orchestration.md`, `references/the-fool/`, `references/verification-ladder.md`.
 
 ## Validation Sensors
 - Every challenge ties to a plan section plus a concrete evidence gap or falsifiable check.

package/skills/agents/planner/SKILL.md

@@ -56,7 +56,7 @@ Transform an engineering request into a structured implementation plan.
 - Verification Ladder: plan references expected sensors; does not run them.
 - Massa-ai Memory: suggest durable decision memories only when the plan locks a strategy; main agent persists.
 - Synapse: none (planning is not a repeated-search task).
-- References: `references/agent-orchestration.md`, `references/subagent-design.md`.
+- References (paths relative to the `massa-ai` skill directory): `references/agent-orchestration.md`, `references/subagent-design.md`.
 
 ## Validation Sensors
 - Every step in the plan references a concrete file, module, or task.

package/skills/agents/requirements-analyst/SKILL.md

@@ -55,7 +55,7 @@ Analyze requirements before implementation to surface ambiguity, gaps, contradic
 - Verification Ladder: static (spec citation) only; no behavioral sensors.
 - Massa-ai Memory: suggest durable requirement-decision memories only when an implicit requirement is accepted as an assumption; main agent persists.
 - Synapse: none (analysis is not a repeated-search task).
-- References: `references/spec-driven/specify.md`, `references/furps/`.
+- References (paths relative to the `massa-ai` skill directory): `references/spec-driven/specify.md`, `references/furps/`.
 
 ## Validation Sensors
 - Every finding cites a requirement ID or spec section.

package/skills/agents/reviewer/SKILL.md

@@ -57,7 +57,7 @@ Review implementation quality by analyzing the diff and flagging bugs, regressio
 - Verification Ladder: static checks (lint, typecheck) as supporting evidence; behavioral checks belong to verification-agent.
 - Massa-ai Memory: suggest durable code-quality memories only when a review reveals a reusable pattern; main agent persists.
 - Synapse: none (review is not a repeated-search task).
-- References: `references/agent-orchestration.md`.
+- References (paths relative to the `massa-ai` skill directory): `references/agent-orchestration.md`.
 
 ## Validation Sensors
 - Every finding has a `path:line` pointer.

package/skills/agents/test-engineer/SKILL.md

@@ -58,7 +58,7 @@ Generate a testing strategy that covers unit, integration, edge cases, negative
 - Verification Ladder: behavioral (tests) and file-integrity (no validation assets weakened).
 - Massa-ai Memory: suggest durable test-pattern memories only when a testing convention is established; main agent persists.
 - Synapse: none (test planning is not a repeated-search task).
-- References: `references/verification-ladder.md`, `references/code-annotation.md`, `references/root-cause-scripts.md`.
+- References (paths relative to the `massa-ai` skill directory): `references/verification-ladder.md`, `references/code-annotation.md`, `references/root-cause-scripts.md`.
 
 ## Validation Sensors
 - Every acceptance criterion maps to at least one test case.

package/skills/agents/verification-agent/SKILL.md

@@ -55,7 +55,7 @@ Centralize Verification Ladder logic and validate that a task's output meets its
 - Verification Ladder: this agent IS the ladder; choose the cheapest sufficient evidence first.
 - Massa-ai Memory: suggest durable verification-recipe memories only when a sensor pattern is reusable; main agent persists.
 - Synapse: none (verification is not a repeated-search task).
-- References: `references/verification-ladder.md`, `references/evidence-gate.md`.
+- References (paths relative to the `massa-ai` skill directory): `references/verification-ladder.md`, `references/evidence-gate.md`.
 
 ## Validation Sensors
 - Every acceptance criterion has a PASS/FAIL verdict with evidence.

package/skills/massa-ai/references/architecture-lenses.md

@@ -39,28 +39,7 @@ Analyze dependency cost with strength, distance, and volatility.
 
 Load `references/architecture-coupling-lens.md` when the audit target includes dependencies, imports, service calls, shared schemas/models, direct persistence access, co-change, or contract leakage.
 
-Strength levels:
-
-- Intrusive: downstream depends on internals not designed for integration.
-- Functional: sequential, transactional, or duplicated symmetric business rules.
-- Model: upstream exposes internal domain model to downstream.
-- Contract: integration-specific DTO/protocol hides internals.
-
-Distance levels:
-
-- same function or class
-- same package
-- same module/library
-- different service
-- external system or team
-
-Volatility signals:
-
-- core business logic
-- frequent git changes or co-change
-- TODO/FIXME clusters
-- evolving API versions
-- fragile tests or recurring regressions
+Strength, distance, and volatility level definitions: full detail in `references/architecture-coupling-lens.md`.
 
 Flag highest risk when high strength, high distance, and high volatility combine.
 
@@ -88,10 +67,7 @@ Check:
 - test-only extraction that loses locality
 - concepts split across many files without leverage
 
-Use the deletion test:
-
-- If deleting a module removes complexity, it was probably shallow.
-- If deleting it spreads complexity across callers, it was probably earning its keep.
+Deletion test: full detail in `references/architecture-deepening-lens.md`.
 
 Only recommend a new seam when variation, dependency direction, external I/O, or test substitution is real.
 

package/skills/massa-ai/references/conversation-feedback.md

@@ -17,19 +17,7 @@ repeated micro-events.
 
 ## Line Shape
 
-Each status update must be 1-2 lines. Use an emoji, a capitalized label in square brackets, and one or two plain sentences.
-
-Do:
-
-```md
-🔵 [Start] Planning visual feedback for massa-ai. Workflow: Spec Driven. Session: Visual Feedback.
-🔄 [Loading] Reading AGENTS.md and massa-ai router guidance before planning.
-🧠 [Context] Found 8 relevant massa-ai memories and queried the requested NotebookLM source.
-🤖 [Agent Running] Plan Critic is checking failure modes for the proposed design.
-⚠️ [Divergence] Expected the legacy router path, but this checkout uses skills/massa-ai/SKILL.md.
-✅ [Verified] Stale-reference checks and skill validation passed.
-🏁 [Finished] Plan complete. Changed files: none. Remaining risk: none found.
-```
+Each status update must be 1-2 lines. Use an emoji, a capitalized label in square brackets, and one or two plain sentences. The worked example is not repeated here — it lives in the canonical policy block named under Policy Source above, which is always in context.
 
 Avoid terse machine-shaped status lines, lowercase labels, equals-sign syntax, and tiny abbreviations.
 

package/skills/massa-ai/references/hook-enforcement.md

@@ -131,7 +131,7 @@ recall stays owned by the router.
 
 | Failure | Behavior |
 |---|---|
-| massa-ai REST unavailable | lesson still lands in `lessons.json`; skipped memory write logged to `scripts/hooks-state/skip.log` |
-| `.specs/STATE.md` absent / workflow unset | stop gate falls back to flat matrix |
+| massa-ai REST unavailable | lesson still lands in `lessons.json`; the memory write is fire-and-forget and is dropped silently (a timeout emits a `deadline-on-fire` JSON breadcrumb on **stderr**, nothing is written to disk) |
+| `.specs/project/STATE.md` absent / workflow unset | stop gate falls back to flat matrix |
 | bad / malformed stdin | hook exits 0, never blocks |
-| hook non-critical error | exit 0, approve, log skip |
+| hook non-critical error | exit 0, approve, degrade silently — there is no skip log file |

package/skills/massa-ai/references/lessons.md

@@ -166,5 +166,5 @@ best-effort. An ungrounded lesson is refused by both `add` and the massa-ai writ
 ### Self-Check
 
 After verification: if a reusable signal was found but no lesson was recorded,
-state the skipped reason. The hook loop logs every skip to
-`scripts/hooks-state/skip.log`.
+state the skipped reason. Nothing else records it — the hook loop keeps no skip
+log on disk, so your stated reason is the only record.

package/skills/massa-ai/references/maestro.md

@@ -19,22 +19,6 @@ Official source anchors:
 - Cloud limits: https://docs.maestro.dev/maestro-cloud/limits.md
 - Maestro MCP: https://docs.maestro.dev/get-started/maestro-mcp.md
 
-## Load Map
-
-| Need | Load |
-|---|---|
-| Source authority, Q&A checklist handling, unsupported facts, transcript requirements | `references/maestro/fact-ledger.md` |
-| CLI preflight, device/platform readiness, local command flags, sharding, live help capture | `references/maestro/cli-device.md` |
-| YAML commands, flow headers, AI commands, examples | `references/maestro/yaml-commands.md` |
-| Core, relational, trait, state, dimension, platform, regex, and web-only selector behavior | `references/maestro/selectors.md` |
-| Flow discovery, config.yaml discovery patterns, tags, execution order, suite isolation | `references/maestro/workspace-execution.md` |
-| Flow header/config/env/report-output boundaries | `references/maestro/config-env-output.md` |
-| `evalScript`, `runScript`, `output`, `faker`, logging, `maestro.log` | `references/maestro/js-scripting.md` |
-| JUnit/HTML reports, artifact directories, debug output, screenshots, videos, AI reports, recording | `references/maestro/artifacts-reports.md` |
-| Cloud binary eligibility, auth/plan needs, app-binary reuse, Cloud device flags, Cloud limits | `references/maestro/cloud.md` |
-| Maestro MCP install/use, tool metadata, Viewer, Cloud-auth tools | `references/maestro/mcp.md` |
-| Stable suite design, setup/teardown, selectors, fixtures, output contracts, skipped checks | `references/maestro/patterns.md` |
-
 ## Minimum Step Selection
 
 - Flow implementation: load `fact-ledger.md`, `cli-device.md`, then only the focused files for the flow surface being edited: commonly `yaml-commands.md`, `selectors.md`, `workspace-execution.md`, `config-env-output.md`, `js-scripting.md`, and `patterns.md`.

package/skills/massa-ai/workflows/discovery.md

@@ -89,39 +89,6 @@ effects ("if we do X, what does that enable or foreclose?"); bring in
 competitive response; think in timeframes (3 months vs 12 months vs 3
 years).
 
-## Frameworks As Tools
-
-Pull a framework in when it moves the conversation forward — never dump
-frameworks or force the conversation through them as a checklist.
-
-- **How Might We (HMW)**: "How might we [outcome] for [user] without
-  [constraint]?" Aim between too broad ("improve onboarding") and too narrow
-  (a disguised solution); generate 5–10 reframings — each opens a different
-  solution space.
-- **Jobs-to-be-Done (JTBD)**: "When [situation], I want to [motivation] so I
-  can [outcome]." The job is stable while solutions change; emotional and
-  social jobs often outweigh functional ones. Ask "what did they fire to
-  hire this?" — it reveals the real competitive set.
-- **Opportunity Solution Tree**: outcome → opportunities (evidence-backed
-  user needs) → multiple solutions per opportunity → cheapest experiment per
-  solution. One solution per opportunity means exploration stopped too
-  early; the tree is a living artifact.
-- **First Principles Decomposition**: state the assumption, break it into
-  fundamental components, ask of each "law of physics or convention?", then
-  rebuild from only the fundamentals. Use when the team is stuck in
-  incremental thinking.
-- **SCAMPER**: seven lenses on an existing product — Substitute, Combine,
-  Adapt, Modify (10x bigger/smaller/faster), Put to other use, Eliminate
-  ("would anyone notice?"), Reverse (flip the sequence or the default).
-- **OODA Loop** (Observe–Orient–Decide–Act): a decision-tempo framework —
-  gather raw signals wide, make sense of them while challenging your own
-  orientation, choose a proportional reversible bet, act, and cycle. Use
-  when the conversation over-deliberates or keeps circling: orient with what
-  exists, decide, and let the next observation correct course.
-- **Reverse Brainstorming**: invert the problem ("how could we make this
-  worse?"), generate freely — people find flaws more easily than fixes —
-  then reverse each worsening idea into the seed of a solution.
-
 ## Session Rhythm
 
 A good session opens up before it narrows down. Move through five stages;
@@ -134,8 +101,9 @@ name the stage transition when it helps the user follow.
    to nothing.
 2. **Diverge** — Generate many ideas without judgment; build on ideas rather
    than shooting them down; follow tangents; push past the first 3–5 obvious
-   ideas; use the frameworks above to open new angles. Do not evaluate
-   feasibility here — that kills divergent thinking.
+   ideas; pull in whatever brainstorming frameworks fit the conversation to
+   open new angles. Do not evaluate feasibility here — that kills divergent
+   thinking.
 3. **Provoke** — The sparring-partner stage: "What is the strongest argument
    against this?", "Who would hate this and why?", "What are we not
    seeing?", "What if the opposite were true?", "What is the 10x more

package/skills/massa-ai/workflows/skill-architect.md

@@ -47,32 +47,15 @@ what "success" looks like.
 
 ### 1.1 — Understand the Problem
 
-Start by asking about the OUTCOME, not the implementation. Key questions
-(ask conversationally, not as a checklist dump):
-
-- **What workflow do you want to make consistent?** Get a concrete example
-  of what they do today, step by step.
-- **What goes wrong without the skill?** Understand the pain: inconsistency,
-  forgotten steps, wasted time re-explaining, wrong outputs.
-- **Who will use this skill?** Just them? Their team? Public distribution?
-  This affects naming, documentation depth, and description specificity.
-- **What tools are involved?** Built-in Agents capabilities (code execution,
-  file creation, artifacts) or external services via MCP?
+Determine: the workflow to make consistent, what goes wrong without the
+skill, who will use it (affects naming, documentation depth, and description
+specificity), and what tools are involved (built-in Agents capabilities or
+external services via MCP).
 
 ### 1.2 — Define Use Cases
 
-Nail down 2-3 concrete use cases. For each, capture:
-
-```
-Use Case: [Name]
-Trigger: What the user would say or do
-Steps: The sequence of actions
-Tools: Built-in or MCP tools needed
-Result: What success looks like (specific output)
-```
-
-If the user is vague, give them examples to react to. It's easier to refine
-a concrete proposal than to articulate needs from scratch.
+Nail down 2-3 concrete use cases, each capturing name, trigger, steps, tools
+needed, and expected result.
 
 ### 1.3 — Identify the Category
 
@@ -87,11 +70,8 @@ detailed pattern guidance):
 
 ### 1.4 — Establish Success Criteria
 
-Before moving on, agree on how they'll know the skill works:
-
-- **Trigger accuracy:** What should trigger it? What should NOT?
-- **Output quality:** What does a good result look like concretely?
-- **Efficiency:** How many interactions should it take?
+Before moving on, agree on trigger accuracy, output quality, and efficiency
+expectations — how they'll know the skill works.
 
 **Exit criteria for Discovery:**