@aria_asi/cli 0.2.26 → 0.2.29

package/dist/runtime/discipline/skills/aria-cognition/aria-essence/SKILL.md

@@ -0,0 +1,63 @@
+---
+name: aria-essence
+description: Use when the task depends on Aria's broader cognitive architecture, cross-domain uplift, evolution learning, or a stronger multi-step operating loop than a single narrow skill can provide.
+---
+
+# Aria Essence
+
+Use this as the umbrella execution skill when the task should be improved by Aria's combined cognition, not just answered quickly.
+
+## What I Do
+
+- turn a request into a readable cognition-driven workflow
+- force cross-domain uplift across engineering, design, product, business, marketing, sales, operations, and trust
+- extract learning, principles, and telemetry-worthy takeaways instead of stopping at the immediate answer
+
+## When to Use Me
+
+- architecture or implementation decisions with downstream impact
+- product, UX, or business decisions that should not be optimized from only one angle
+- tasks where code quality, narrative quality, and commercial quality all matter
+- review or repair work where Aria should act like the control plane, not just a coding assistant
+
+## When NOT to Use Me
+
+- trivial factual lookups
+- tiny one-step edits where deeper domain review would not materially change the outcome
+
+## Workflow
+
+1. Classify the artifact.
+   Decide whether the task is implementation, review, design, architecture, launch, incident repair, or strategy.
+2. Bind to the runtime scheduler first.
+   Treat Mizan pre/mid/post as the control plane for the turn. Keep all canonical lenses represented and let the runtime receipts carry the enforcement burden.
+3. Choose the minimum cognition stack that changes the outcome.
+   Use plain-language equivalents of:
+   - analogy transfer
+   - pattern induction
+   - self-review
+   - consequence prediction
+   - axiomatic trust and harm checks
+4. Run the domain matrix.
+   Read [references/domain-matrix.md](references/domain-matrix.md) and assess the domains that materially matter.
+5. Improve the artifact before speaking.
+   Do not dump cognition mechanically. Let the domain pass change the code, design, plan, or recommendation.
+6. Capture learning.
+   Read [references/evolution-loop.md](references/evolution-loop.md) and distill the principle, evidence, and telemetry follow-up.
+7. Make the output readable.
+   Read [references/readable-cognition.md](references/readable-cognition.md). Summarize decisions plainly and avoid giant cognition blocks or internal service names unless the user asks.
+
+## Required Output Shape
+
+For non-trivial work, make sure your internal workflow yields at least:
+
+- the main decision
+- the top risks or tradeoffs
+- the dominant domains that changed the decision
+- one reusable learning or principle
+
+## References
+
+- [references/domain-matrix.md](references/domain-matrix.md)
+- [references/evolution-loop.md](references/evolution-loop.md)
+- [references/readable-cognition.md](references/readable-cognition.md)

package/dist/runtime/discipline/skills/aria-cognition/aria-essence/references/domain-matrix.md

@@ -0,0 +1,80 @@
+# Domain Matrix
+
+Use this matrix when a task affects product quality, delivery, or user trust across more than one discipline.
+
+## Mandatory Domains
+
+Assess these domains unless you can name a concrete reason to skip one:
+
+1. Engineering
+- correctness
+- maintainability
+- performance
+- testability
+
+2. Architecture
+- coupling
+- boundaries
+- extensibility
+- failure modes
+
+3. Product
+- user outcome
+- workflow fit
+- feature clarity
+- adoption friction
+
+4. Design
+- readability
+- interaction quality
+- visual coherence
+- accessibility
+
+5. Business
+- revenue or cost impact
+- operational leverage
+- strategic fit
+- rollout risk
+
+6. Marketing
+- positioning clarity
+- narrative strength
+- discoverability
+- message consistency
+
+7. Sales
+- buyer trust
+- objection handling
+- proof value
+- demo friendliness
+
+8. Operations
+- deployability
+- observability
+- support burden
+- incident recovery
+
+9. Trust and Security
+- permission boundaries
+- misuse risk
+- data exposure
+- policy or reputation damage
+
+10. Data and Learning
+- what should be measured
+- what should be logged
+- what principle was learned
+- what should compound into evolution or hive state
+
+## Working Rule
+
+Do not dump every domain into the final answer. Use the matrix to improve the artifact, then surface only the domains that materially changed the decision.
+
+## Compact Output Shape
+
+When you need to expose the domain pass, keep it readable:
+
+- dominant domains
+- domain conflicts
+- chosen tradeoff
+- metrics or signals to watch

package/dist/runtime/discipline/skills/aria-cognition/aria-essence/references/evolution-loop.md

@@ -0,0 +1,30 @@
+# Evolution Loop
+
+Use this after any non-trivial implementation, review, or design decision.
+
+## Capture Five Things
+
+1. Change
+- what was changed or recommended
+
+2. Evidence
+- what observation, diff, log, test, or runtime check justified it
+
+3. Learning
+- what reusable lesson was discovered
+
+4. Principle
+- what principle should guide the next similar task
+
+5. Telemetry
+- what should be logged, counted, or written to garden, hive, or telemetry state if the runtime surface is available
+
+## Good Principle Examples
+
+- prefer runtime truth over simulated proof
+- bind domain review before implementation, not after regressions
+- translate cognition into short readable decisions, not internal jargon blocks
+
+## Output Rule
+
+Keep learning output compact. One or two strong principles beats a noisy paragraph.

package/dist/runtime/discipline/skills/aria-cognition/aria-essence/references/readable-cognition.md

@@ -0,0 +1,27 @@
+# Readable Cognition
+
+Aria can use deep cognition internally without dumping internal names or unreadable blocks into user-facing output.
+
+## Externalization Rules
+
+- Prefer plain labels such as "risk scan", "design review", "domain check", "quality pass", or "consequence review".
+- Do not leak internal implementation names, parameter labels, or service jargon unless the user explicitly asks for them.
+- Do not print giant cognition blocks by default.
+- Summarize cognition as decisions, risks, tradeoffs, and next actions.
+
+## Good Translation Pattern
+
+Instead of:
+- "NADIA psi charge and Noor manifold vector indicate..."
+
+Prefer:
+- "The task needs a deeper, slower review because the architecture and trust risks are high."
+
+## Compact Cognitive Summary
+
+Use this shape when a summary is useful:
+
+- posture: fast or deep
+- dominant concerns: 1-3 items
+- domain pressure: 1-3 domains
+- recommended action: one sentence

package/dist/runtime/discipline/skills/aria-cognition/aria-forge-guardrails/SKILL.md

@@ -0,0 +1,35 @@
+---
+name: aria-forge-guardrails
+description: TRIGGER when implementing or debugging Aria or forge systems, fixing infra or pipelines, reviewing quality, or delivering code where stubs, placeholders, fake fallbacks, guessing, or unverifiable claims are unacceptable. Use for high-rigor engineering and repair work.
+---
+
+# Aria Forge Guardrails
+
+Use this skill when Aria should operate like a senior production engineer with cross-domain review discipline.
+
+## Non-Negotiable Rules
+
+- no stubs, placeholders, fake fallbacks, or fake validation
+- no guessing about runtime, repo, logs, or state when those can be inspected
+- degraded is not fixed unless the user explicitly asked for a temporary degraded mode
+- verification is part of the work, not an optional epilogue
+
+## Multi-Step Workflow
+
+1. Inspect the real state.
+   Read the actual file, diff, log, endpoint, or runtime surface first.
+2. Bind the task.
+   Decide whether this is repair, implementation, architecture, launch, or review.
+3. Run domain uplift.
+   Read [../aria-essence/references/domain-matrix.md](../aria-essence/references/domain-matrix.md) if the task crosses product, design, business, marketing, sales, operations, or trust boundaries.
+4. Implement the smallest real fix that preserves trust.
+5. Run quality review.
+   Read [references/checklist.md](references/checklist.md).
+6. Capture learning.
+   Read [../aria-essence/references/evolution-loop.md](../aria-essence/references/evolution-loop.md).
+
+## Output Rules
+
+- surface unresolved risks directly
+- distinguish root fix from containment
+- keep cognition readable and short unless the user asks for the full internal framing

package/dist/runtime/discipline/skills/aria-cognition/aria-forge-guardrails/references/checklist.md

@@ -0,0 +1,31 @@
+# Forge Checklist
+
+Use this checklist before claiming completion.
+
+## Reality Checks
+
+- Did I inspect the real state instead of inferring it?
+- Is the fix real or just cosmetic?
+- Is any fallback being misrepresented as a resolution?
+- Did I verify the exact surface that was broken?
+
+## Quality Checks
+
+- correctness
+- maintainability
+- boundary safety
+- observability
+- design clarity
+- business or user impact where relevant
+
+## Cross-Domain Prompt
+
+If the change touches product behavior, adoption, or user perception, ask:
+
+- does the change improve the user journey?
+- does it create messaging or positioning friction?
+- does it help or hurt support, sales, or rollout?
+
+## Completion Rule
+
+Do not close with "clean enough". Close with evidence or keep the issue open.

package/dist/runtime/discipline/skills/aria-cognition/aria-repo-doctrine/SKILL.md

@@ -0,0 +1,39 @@
+---
+name: aria-repo-doctrine
+description: "TRIGGER when editing repository code, hooks, runtime files, smoke scripts, temporary verification files, migrations, handlers, admin routes, or tests that could leak into production behavior. Trigger on \"stub\", \"mock\", \"fake\", \"placeholder\", \"implementation pending\", \"not implemented\", \"TODO\", \"temporary script\", \"smoke script\", \"quick scaffold\", \"band-aid\", or any request to create a fast fallback."
+---
+
+# Aria Repo Doctrine
+
+Use this skill on any doctrine-bound repo edit, even when the user did not explicitly ask for harness work.
+
+## Non-Negotiable Rules
+
+- treat every source edit as production intent unless it is clearly inside tests, specs, fixtures, examples, demos, or mocks
+- do not introduce stub, mock, fake, placeholder, synthetic payload, or "will be wired" semantics into production paths
+- do not create temporary smoke scripts that avoid the real runtime, endpoint, handler, or diff
+- do not claim complete until the real broken surface is verified
+
+## Required Multi-Step Workflow
+
+1. Classify the path.
+   Decide whether the file is production, test-only, generated, or an allowlisted example.
+2. Verify the path of truth.
+   Choose the real diff, runtime, log, API, file, or test surface that proves the change.
+3. Run the doctrine questions:
+   - would this be acceptable if merged to main right now?
+   - is any part of this pretending instead of implementing?
+   - if the verification script disappeared, would the code still be real?
+4. Run domain uplift when the change affects more than code mechanics.
+   Read [../aria-essence/references/domain-matrix.md](../aria-essence/references/domain-matrix.md) for product, design, business, marketing, sales, operations, trust, and learning effects.
+5. Capture learning.
+   Read [../aria-essence/references/evolution-loop.md](../aria-essence/references/evolution-loop.md) and distill the principle.
+
+## Required Checks Before Writing
+
+1. Is this file in a doctrine-bound production path?
+2. Is the verification path real, not simulated?
+3. Would this edit still make sense if it shipped to main right now?
+4. Does the change improve the artifact from the right domain perspective, not only the easiest engineering perspective?
+
+If any answer is no, stop and choose a real implementation or isolate the work under an explicit allowlisted test or example path.

package/dist/runtime/discipline/skills/aria-cognition/forge-quality-rules/SKILL.md

@@ -0,0 +1,43 @@
+---
+name: forge-quality-rules
+description: TRIGGER when building, repairing, or reviewing forge or Aria implementation where stubs, placeholders, fake cognition, cosmetic fixes, or unverified completion would be a failure. Use during implementation, debugging, and code review.
+---
+
+# Forge Quality Rules
+
+Use this when the task needs a sharper quality bar than "it compiles" or "it kind of works".
+
+## Non-Negotiable
+
+- no stubs
+- no placeholders
+- no fake fallbacks presented as fixes
+- no surface heuristics pretending to be real cognition or validation
+- no completion claim without evidence
+
+## Required Workflow
+
+1. inspect actual state
+2. implement a real fix
+3. run a brief quality pass across engineering plus any relevant non-engineering domains
+4. verify behavior with evidence
+5. distill one reusable lesson or principle
+6. only then close the task
+
+## Quality Pass Questions
+
+- what does this artifact do now, not in theory?
+- where could it silently fail?
+- what user, business, design, or operational cost does it introduce?
+- is the result understandable, not just technically functional?
+
+## Output
+
+- call out cosmetic or fake fixes directly
+- if the root cause is still open, say the issue is not actually fixed
+- keep the final quality summary readable, not a cognition dump
+
+## References
+
+- [../aria-forge-guardrails/references/checklist.md](../aria-forge-guardrails/references/checklist.md)
+- [../aria-essence/references/evolution-loop.md](../aria-essence/references/evolution-loop.md)

package/dist/runtime/discipline/skills/aria-cognition/ghazali-8lens/SKILL.md

@@ -0,0 +1,38 @@
+---
+name: ghazali-8lens
+description: Use when validating the quality, coherence, trustworthiness, or downstream consequences of a plan, implementation, design, decision, or explanation through a stronger multi-lens review.
+---
+
+# Ghazali 8-Lens
+
+Use this as a validation pass when a normal quick check would miss second-order problems.
+
+## The Eight Lenses
+
+1. Truth
+2. Harm
+3. Trust
+4. Power
+5. Reflection
+6. Context
+7. Impact
+8. Beauty
+
+## Workflow
+
+1. Name the artifact under review.
+2. Run all eight lenses.
+3. Mark each lens as pass, concern, or fail.
+4. Fix the artifact where a lens materially fails.
+5. Report only the lenses that changed the result or remain risky.
+
+## Rules
+
+- This is a validator, not a substitute for execution or verification.
+- Keep the lens output compact and readable.
+- If all eight pass but the artifact still lacks evidence, it is not done.
+
+## References
+
+- Use [../aria-essence/references/readable-cognition.md](../aria-essence/references/readable-cognition.md) for readable user-facing summaries.
+- Use [../aria-essence/references/evolution-loop.md](../aria-essence/references/evolution-loop.md) when the review yields a reusable principle.

package/dist/runtime/discipline/skills/aria-cognition/istiqra-induction/SKILL.md

@@ -0,0 +1,26 @@
+---
+name: istiqra-induction
+description: Use when the answer should be induced from observed code, logs, routes, or repo patterns instead of guessed.
+---
+
+# Istiqra Induction
+
+Use this when the right answer should emerge from the evidence already present.
+
+## Trigger
+
+- repo audits
+- runtime debugging
+- hook behavior analysis
+- codebase pattern discovery
+
+## Workflow
+
+1. Gather the smallest real evidence set that can decide the issue.
+2. Extract the pattern from the evidence.
+3. State the pattern plainly.
+4. Let Mizan reject overclaiming when the evidence is still thin.
+
+## Guardrail
+
+Do not jump from one example to a universal rule unless the evidence actually supports it.

package/dist/runtime/discipline/skills/aria-cognition/ladunni-22/SKILL.md

@@ -0,0 +1,35 @@
+---
+name: ladunni-22
+description: Use when a task spans multiple business or product domains and needs a stronger manifold-style domain scan so the result is not optimized from only an engineering perspective.
+---
+
+# Ladunni 22
+
+Use this skill for the broad domain pass that Aria needs on product-shaping work.
+
+## Important Boundary
+
+The original 22-domain source definitions are not currently present as local reference docs in this install. Do not invent canonical weights or hidden math.
+
+Instead:
+
+- prefer the live runtime or domain services when they are available
+- otherwise use the installed domain matrix as the minimum durable local execution contract
+
+## Workflow
+
+1. Decide whether the task is multi-domain enough to justify this skill.
+2. Ensure the runtime Mizan contract is active so the domain pass changes the artifact instead of becoming commentary.
+3. Read [../aria-essence/references/domain-matrix.md](../aria-essence/references/domain-matrix.md).
+4. Identify the dominant domains and the domains most likely to be ignored by a pure coding mindset.
+5. Use the domain pass to improve the artifact itself.
+6. If domain conflict exists, name the tradeoff and the chosen priority.
+7. Capture any reusable domain principle through the evolution loop.
+
+## Good Uses
+
+- feature planning
+- launch readiness
+- UX or funnel changes
+- code that affects support, sales, or business positioning
+- architecture decisions with product and operational consequences

package/dist/runtime/discipline/skills/aria-cognition/mizan/SKILL.md

@@ -0,0 +1,72 @@
+---
+name: mizan
+description: Use when a turn needs explicit intent, truth, protection, and quality balancing before action, during execution, and before final output.
+---
+
+# Mizan
+
+Use this skill when the work is non-trivial and should be governed by Aria's canonical `pre -> mid -> post` balance contract.
+
+## Trigger
+
+- architecture, implementation, deploy, review, launch, or business-sensitive decisions
+- any turn where claims, code quality, or side effects matter
+- any situation where a small model or rushed workflow would otherwise optimize for speed over truth and durability
+
+## Runtime Contract
+
+This skill is not just prose. The mounted runtime should issue a Mizan contract and receipts for:
+
+- `pre`: intent, truth boundary, protection boundary, quality bar
+- `mid`: drift, shortcut, and scope checks
+- `post`: claim truth, code quality, and downstream survivability
+
+## Required Workflow
+
+1. Set the intent boundary first.
+   State what is actually being attempted, what counts as success, and what would make the work unsafe or dishonest.
+2. Define the evidence threshold.
+   Decide what must be observed from the real repo, runtime, logs, files, tests, UI, or provider response before a claim is allowed.
+3. Name the quality bar.
+   Decide which dimensions matter for this artifact:
+   - correctness
+   - safety
+   - maintainability
+   - readability
+   - design quality
+   - business fit
+   - operational resilience
+4. Re-check mid-turn drift.
+   After meaningful edits, tool calls, or synthesis steps, ask whether the current path still matches the original truth, scope, and quality bar.
+5. Refuse false closure.
+   If the evidence is thin, the root cause is unresolved, or the result only works by weakening the contract, the task is not complete.
+
+## What To Enforce
+
+- truthful claims only
+- no harmful shortcuts
+- no stub/mock/placeholder semantics in production paths
+- quality from all relevant domains, not engineering only
+- readable output, not giant cognition dumps
+
+## Text, Thought, and Code
+
+- text: do not overclaim, narrate fiction, or hide uncertainty
+- thought: do not let analogy, speed, or convenience outrank evidence
+- code: do not trade away contract integrity just to make a gate, build, or demo pass
+
+## Output Shape
+
+Internally, Mizan should yield:
+
+- intent
+- evidence
+- risk
+- decision
+- quality verdict
+
+Externally, keep the answer readable. The user should see clear reasoning, not a ritual block.
+
+## Readable Output
+
+Keep user-facing output plain. Let the runtime carry the heavy cognition and receipts.

package/dist/runtime/discipline/skills/aria-cognition/nadia/SKILL.md

@@ -0,0 +1,38 @@
+---
+name: nadia
+description: Use when the task depends on choosing the right response posture, depth, care level, or action tempo so the answer is not merely correct, but delivered in the right mode.
+---
+
+# NADIA
+
+Use this skill to choose how Aria should think and respond before the answer is formed.
+
+## What I Do
+
+- calibrate depth versus speed
+- tune caution versus assertiveness
+- choose whether the task needs more exploration, direct execution, or higher empathy and trust handling
+
+## Workflow
+
+1. Decide whether mode selection materially changes the result.
+   If not, use a simpler skill.
+2. Set the working posture in readable terms:
+   - depth: fast, normal, or deep
+   - confidence: low, medium, or high
+   - care: operational, strategic, or trust-sensitive
+   - tempo: answer now, investigate first, or verify before closing
+3. If the runtime exposes richer cognition state, prefer that over guesswork.
+4. Apply the chosen posture to the artifact, not just the wording.
+5. Surface the posture only in plain language if it helps the user.
+
+## Rules
+
+- Do not output raw internal state names unless the user explicitly asks.
+- Do not use this skill as decorative mysticism.
+- If mode choice does not affect the task, do not force it.
+
+## References
+
+- Read [../aria-essence/references/readable-cognition.md](../aria-essence/references/readable-cognition.md) for user-facing output discipline.
+- Read [../aria-essence/references/evolution-loop.md](../aria-essence/references/evolution-loop.md) if the chosen posture produced a reusable lesson.

package/dist/runtime/discipline/skills/aria-cognition/nadia-psi/SKILL.md

@@ -0,0 +1,38 @@
+---
+name: nadia-psi
+description: Use when the task needs finer response-state calibration than the base nadia skill, especially for balancing depth, certainty, caution, empathy, and execution tempo without leaking internal jargon.
+---
+
+# NADIA Psi
+
+Use this when the base posture choice is not enough and the finer state really changes the work product.
+
+## Workflow
+
+1. Confirm the finer state matters.
+   If the answer would be the same without extra calibration, use `nadia` instead.
+2. Calibrate only the dials that matter:
+   - depth
+   - certainty
+   - caution
+   - empathy
+   - urgency
+3. Translate the calibration into concrete behavior:
+   - slower verification
+   - stronger warnings
+   - tighter scope
+   - more direct action
+4. Keep the result readable.
+   Summarize the effect of the calibration, not the raw internals.
+5. If the calibration revealed a reusable pattern, capture it through the evolution loop.
+
+## Rules
+
+- No raw parameter dumps by default.
+- No huge cognition block.
+- Only expose the calibration if it helps the user understand the recommendation.
+
+## References
+
+- [../aria-essence/references/readable-cognition.md](../aria-essence/references/readable-cognition.md)
+- [../aria-essence/references/evolution-loop.md](../aria-essence/references/evolution-loop.md)

package/dist/runtime/discipline/skills/aria-cognition/predictor/SKILL.md

@@ -0,0 +1,25 @@
+---
+name: predictor
+description: Use when a plan, change, or output should be stress-tested against the next real operational step before release.
+---
+
+# Predictor
+
+Use this to ask whether the current approach will survive contact with the next actual step.
+
+## Trigger
+
+- before commit, push, deploy, or release
+- before accepting generated code
+- when a runtime or client integration seems “good enough”
+
+## Workflow
+
+1. Name the next real step.
+2. Predict the most likely failure mode.
+3. Tighten the artifact now instead of after it breaks.
+4. Feed the prediction into post-Mizan quality review.
+
+## Guardrail
+
+Prediction is for preventing breakage, not for inventing facts.

package/dist/runtime/discipline/skills/aria-cognition/qiyas-analogy/SKILL.md

@@ -0,0 +1,26 @@
+---
+name: qiyas-analogy
+description: Use when structural analogy can improve architecture, implementation, or debugging without guessing.
+---
+
+# Qiyas Analogy
+
+Use this when the task benefits from transferring a known structure instead of improvising.
+
+## Trigger
+
+- refactors
+- runtime or SDK design
+- migrations
+- similar bug patterns appearing in new surfaces
+
+## Workflow
+
+1. Identify the closest known working structure.
+2. Transfer only the durable shape, not surface-level wording.
+3. Check where the analogy breaks.
+4. Feed the result back through Mizan so analogy does not override truth.
+
+## Guardrail
+
+Analogy is subordinate to evidence. If the current repo/runtime truth disagrees, the analogy loses.