scistudio 0.3.4a32__tar.gz

scistudio-0.3.4a32/.agents/rules/rules.md

@@ -0,0 +1,77 @@
+# SciStudio AI Rules Index
+
+This file is a pointer only. It is not an independent policy source.
+
+- Use `AGENTS.md` for root repository policy.
+
+- Use `docs/ai-developer/rules.md` for rules every AI persona must follow.
+
+- Use `docs/ai-developer/rules.md#5-gate-cli-command-set` for the canonical
+  AI-facing gate record and local receipt commands.
+
+- Use `docs/ai-developer/release-runbook.md` if you are cutting a desktop
+  release or publishing an OTA update. Two of its rules brick users when
+  broken: the installer must be downloadable before any mandatory manifest,
+  and it must carry a build number at or above the highest published patch.
+
+- Use `docs/ai-developer/gate-cli-command-set.md` for the full consolidated
+  gate CLI reference (arguments, `--mode` family, exit codes, strictness tiers,
+  per-task-kind and per-persona profiles, and a soft-routing decision guide).
+
+- Use `docs/ai-developer/specific_rules/gated-workflow.md` for AI-authored
+  gate workflow work.
+
+- Use `docs/ai-developer/specific_rules/new-feature.md` if you are building a
+  new feature.
+
+- Use `docs/ai-developer/specific_rules/bug-fix.md` if you are fixing a bug.
+
+- Use `docs/ai-developer/specific_rules/hotfix.md` if the owner explicitly
+  authorizes hotfix mode.
+
+- Use `docs/ai-developer/specific_rules/guided-work.md` if you are carrying out
+  owner-directed live implementation (task kind `guided`).
+
+- Use `docs/ai-developer/specific_rules/docs-change.md` if you are changing
+  documentation only.
+
+- Use `docs/ai-developer/specific_rules/agent-dispatch.md` if you are
+  dispatching or coordinating agents.
+
+- Use `docs/ai-developer/specific_rules/document-standards.md` if you need the
+  ADR-042 document structure reference.
+
+- Use `docs/ai-developer/personas/manager.md` if you are the manager persona.
+
+- Use `docs/ai-developer/personas/implementer.md` if you are the implementer
+  persona.
+
+- Use `docs/ai-developer/personas/adr-author.md` if you are the ADR author
+  persona.
+
+- Use `docs/ai-developer/personas/audit-reviewer.md` if you are the audit
+  reviewer persona.
+
+- Use `docs/ai-developer/personas/test-engineer.md` if you are the test
+  engineer persona.
+
+- Use `docs/ai-developer/personas/live-implementer.md` if you are the
+  `live_implementer` persona carrying out a `guided` task kind.
+
+- Use `docs/ai-developer/templates/agent-dispatch-checklist-template.md` if you
+  are creating a manager dispatch checklist.
+
+- Use `docs/ai-developer/templates/agent-dispatch-prompt-template.md` if you
+  are dispatching non-audit work.
+
+- Use `docs/ai-developer/templates/agent-dispatch-audit-with-context-prompt-template.md`
+  if you are dispatching an audit with issue, checklist, PR, and claimed-work
+  context.
+
+- Use `docs/ai-developer/templates/agent-dispatch-audit-no-context-prompt-template.md`
+  if you are dispatching an audit without current task context.
+
+- Use `docs/ai-developer/skills/scistudio-e2e-test/SKILL.md` if you are running
+  a live end-to-end SciStudio session from a scenario file under
+  `docs/ai-developer/e2e/`. Pair it with
+  `docs/ai-developer/e2e/template.md` and `docs/ai-developer/e2e/README.md`.

scistudio-0.3.4a32/.agents/skills/adr-author/SKILL.md

@@ -0,0 +1,19 @@
+---
+name: adr-author
+description: Use when acting as the SciStudio ADR author persona for ADRs, addenda, specs, governance text, document standards, schemas, and architecture-facing decisions.
+---
+
+# SciStudio ADR Author Skill
+
+This skill is a hard pointer only. It does not define independent policy.
+
+Before doing ADR author work, load and follow:
+
+- @AGENTS.md
+- @docs/ai-developer/rules.md
+- @docs/ai-developer/personas/adr-author.md
+- @docs/ai-developer/specific_rules/docs-change.md
+- @docs/ai-developer/specific_rules/document-standards.md
+- @docs/ai-developer/specific_rules/gated-workflow.md
+
+Do not continue as ADR author until the persona file and common rules are loaded.

scistudio-0.3.4a32/.agents/skills/audit-reviewer/SKILL.md

@@ -0,0 +1,18 @@
+---
+name: audit-reviewer
+description: Use when acting as the SciStudio audit reviewer persona for reviews, audits, CI investigation, drift detection, conformance checks, and readiness assessment.
+---
+
+# SciStudio Audit Reviewer Skill
+
+This skill is a hard pointer only. It does not define independent policy.
+
+Before doing audit reviewer work, load and follow:
+
+- @AGENTS.md
+- @docs/ai-developer/rules.md
+- @docs/ai-developer/personas/audit-reviewer.md
+- @docs/ai-developer/specific_rules/gated-workflow.md
+
+Follow the audit context boundaries in the task instruction.
+Do not continue as audit reviewer until the persona file and common rules are loaded.

scistudio-0.3.4a32/.agents/skills/implementer/SKILL.md

@@ -0,0 +1,19 @@
+---
+name: implementer
+description: Use when acting as the SciStudio implementer persona for scoped code, tests, tool wiring, implementation-linked docs, and gate-record evidence.
+---
+
+# SciStudio Implementer Skill
+
+This skill is a hard pointer only. It does not define independent policy.
+
+Before doing implementer work, load and follow:
+
+- @AGENTS.md
+- @docs/ai-developer/rules.md
+- @docs/ai-developer/personas/implementer.md
+- @docs/ai-developer/specific_rules/gated-workflow.md
+- The matching task-specific rule under @docs/ai-developer/specific_rules/
+
+When dispatched by a manager, also follow @docs/ai-developer/specific_rules/agent-dispatch.md.
+Do not continue as implementer until the persona file and common rules are loaded.

scistudio-0.3.4a32/.agents/skills/live-implementer/SKILL.md

@@ -0,0 +1,20 @@
+---
+name: live-implementer
+description: Use when acting as the SciStudio live implementer persona for owner-directed live implementation sessions under the guided task kind.
+---
+
+# SciStudio Live Implementer Skill
+
+This skill is a hard pointer only. It does not define independent policy.
+
+Before doing live implementer work, load and follow:
+
+- @AGENTS.md
+- @docs/ai-developer/rules.md
+- @docs/ai-developer/personas/live-implementer.md
+- @docs/ai-developer/specific_rules/guided-work.md
+- @docs/ai-developer/specific_rules/gated-workflow.md
+
+The live_implementer persona is not the ordinary implementer. Do not inherit the
+ordinary implementer workflow by implication.
+Do not continue as live implementer until the persona file and common rules are loaded.

scistudio-0.3.4a32/.agents/skills/manager/SKILL.md

@@ -0,0 +1,20 @@
+---
+name: manager
+description: Use when acting as the SciStudio manager persona for planning, coordination, dispatch, hotfix ownership, integration testing, e2e testing, PR readiness, and durable status reporting.
+---
+
+# SciStudio Manager Skill
+
+This skill is a hard pointer only. It does not define independent policy.
+
+Before doing manager work, load and follow:
+
+- @AGENTS.md
+- @docs/ai-developer/rules.md
+- @docs/ai-developer/personas/manager.md
+- @docs/ai-developer/specific_rules/gated-workflow.md
+- @docs/ai-developer/specific_rules/agent-dispatch.md
+- @docs/ai-developer/specific_rules/hotfix.md when hotfix mode is explicitly authorized
+
+Use the templates under @docs/ai-developer/templates/ when dispatching agents.
+Do not continue as manager until the persona file and common rules are loaded.

scistudio-0.3.4a32/.agents/skills/scistudio-e2e-test/SKILL.md

@@ -0,0 +1,26 @@
+---
+name: scistudio-e2e-test
+description: Use when running a live end-to-end SciStudio session — driving the GUI in Chrome via Chrome MCP, verifying a PR before merge, reproducing a hotfix bug live, or any time the user says "跑 e2e", "do an e2e", "verify in Chrome", "run e2e on PR #N", or hands you a path under docs/ai-developer/e2e/. Pairs a user-filled scenario file with a pass/fail verdict written back into the same file.
+---
+
+# SciStudio E2E Test Skill
+
+This skill is a hard pointer only. It does not define independent policy.
+
+Before doing e2e work, load and follow:
+
+- @AGENTS.md
+- @docs/ai-developer/rules.md
+- @docs/ai-developer/skills/scistudio-e2e-test/SKILL.md
+- @docs/ai-developer/e2e/template.md (the scenario shape this skill expects)
+- @docs/ai-developer/e2e/README.md (workflow + naming for scenario files)
+- @docs/ai-developer/personas/manager.md when the e2e is part of a manager coordination
+- @docs/ai-developer/specific_rules/hotfix.md when the e2e is a hotfix repro
+
+The Chrome MCP recipes, dev-server lifecycle, screenshot recipes, and
+final report template live alongside the canonical SKILL.md under
+`docs/ai-developer/skills/scistudio-e2e-test/references/`. Read whichever
+reference the current step needs.
+
+Do not continue as the e2e tester until the canonical SKILL.md and the
+scenario template are loaded.

scistudio-0.3.4a32/.agents/skills/test-engineer/SKILL.md

@@ -0,0 +1,19 @@
+---
+name: test-engineer
+description: Use when acting as the SciStudio test_engineer persona for test architecture, test design, test additions, runtime validation, e2e evidence, and test-only artifacts.
+---
+
+# SciStudio Test Engineer Skill
+
+This skill is a hard pointer only. It does not define independent policy.
+
+Before doing test-engineer work, load and follow:
+
+- @AGENTS.md
+- @docs/ai-developer/rules.md
+- @docs/ai-developer/personas/test-engineer.md
+- @docs/ai-developer/specific_rules/test-engineering.md
+- @docs/ai-developer/specific_rules/gated-workflow.md
+
+When dispatched by a manager, also follow @docs/ai-developer/specific_rules/agent-dispatch.md.
+Do not continue as test engineer until the persona file and common rules are loaded.

scistudio-0.3.4a32/.claude/rules/rules.md

@@ -0,0 +1,77 @@
+# Claude Rules Index
+
+This file is a pointer only. It is not an independent policy source.
+
+- Use `AGENTS.md` for root repository policy.
+
+- Use `docs/ai-developer/rules.md` for rules every AI persona must follow.
+
+- Use `docs/ai-developer/rules.md#5-gate-cli-command-set` for the canonical
+  AI-facing gate record and local receipt commands.
+
+- Use `docs/ai-developer/release-runbook.md` if you are cutting a desktop
+  release or publishing an OTA update. Two of its rules brick users when
+  broken: the installer must be downloadable before any mandatory manifest,
+  and it must carry a build number at or above the highest published patch.
+
+- Use `docs/ai-developer/gate-cli-command-set.md` for the full consolidated
+  gate CLI reference (arguments, `--mode` family, exit codes, strictness tiers,
+  per-task-kind and per-persona profiles, and a soft-routing decision guide).
+
+- Use `docs/ai-developer/specific_rules/gated-workflow.md` for AI-authored
+  gate workflow work.
+
+- Use `docs/ai-developer/specific_rules/new-feature.md` if you are building a
+  new feature.
+
+- Use `docs/ai-developer/specific_rules/bug-fix.md` if you are fixing a bug.
+
+- Use `docs/ai-developer/specific_rules/hotfix.md` if the owner explicitly
+  authorizes hotfix mode.
+
+- Use `docs/ai-developer/specific_rules/guided-work.md` if you are carrying out
+  owner-directed live implementation (task kind `guided`).
+
+- Use `docs/ai-developer/specific_rules/docs-change.md` if you are changing
+  documentation only.
+
+- Use `docs/ai-developer/specific_rules/agent-dispatch.md` if you are
+  dispatching or coordinating agents.
+
+- Use `docs/ai-developer/specific_rules/document-standards.md` if you need the
+  ADR-042 document structure reference.
+
+- Use `docs/ai-developer/personas/manager.md` if you are the manager persona.
+
+- Use `docs/ai-developer/personas/implementer.md` if you are the implementer
+  persona.
+
+- Use `docs/ai-developer/personas/adr-author.md` if you are the ADR author
+  persona.
+
+- Use `docs/ai-developer/personas/audit-reviewer.md` if you are the audit
+  reviewer persona.
+
+- Use `docs/ai-developer/personas/test-engineer.md` if you are the test
+  engineer persona.
+
+- Use `docs/ai-developer/personas/live-implementer.md` if you are the
+  `live_implementer` persona carrying out a `guided` task kind.
+
+- Use `docs/ai-developer/templates/agent-dispatch-checklist-template.md` if you
+  are creating a manager dispatch checklist.
+
+- Use `docs/ai-developer/templates/agent-dispatch-prompt-template.md` if you
+  are dispatching non-audit work.
+
+- Use `docs/ai-developer/templates/agent-dispatch-audit-with-context-prompt-template.md`
+  if you are dispatching an audit with issue, checklist, PR, and claimed-work
+  context.
+
+- Use `docs/ai-developer/templates/agent-dispatch-audit-no-context-prompt-template.md`
+  if you are dispatching an audit without current task context.
+
+- Use `docs/ai-developer/skills/scistudio-e2e-test/SKILL.md` if you are running
+  a live end-to-end SciStudio session from a scenario file under
+  `docs/ai-developer/e2e/`. Pair it with
+  `docs/ai-developer/e2e/template.md` and `docs/ai-developer/e2e/README.md`.

scistudio-0.3.4a32/.claude/settings.local.json

@@ -0,0 +1,16 @@
+{
+  "permissions": {
+    "allow": [
+      "Bash(pip --version)",
+      "Bash(git reset:*)",
+      "Bash(git rm:*)",
+      "Bash(git commit:*)",
+      "Bash(git branch:*)",
+      "Bash(git push:*)",
+      "Bash(gh pr:*)",
+      "Bash(gh run:*)",
+      "Bash(git pull:*)",
+      "Bash(git add:*)"
+    ]
+  }
+}

scistudio-0.3.4a32/.claude/skills/adr-author/SKILL.md

@@ -0,0 +1,19 @@
+---
+name: adr-author
+description: Use when acting as the SciStudio ADR author persona for ADRs, addenda, specs, governance text, document standards, schemas, and architecture-facing decisions.
+---
+
+# SciStudio ADR Author Skill
+
+This skill is a hard pointer only. It does not define independent policy.
+
+Before doing ADR author work, load and follow:
+
+- @AGENTS.md
+- @docs/ai-developer/rules.md
+- @docs/ai-developer/personas/adr-author.md
+- @docs/ai-developer/specific_rules/docs-change.md
+- @docs/ai-developer/specific_rules/document-standards.md
+- @docs/ai-developer/specific_rules/gated-workflow.md
+
+Do not continue as ADR author until the persona file and common rules are loaded.

scistudio-0.3.4a32/.claude/skills/audit-reviewer/SKILL.md

@@ -0,0 +1,18 @@
+---
+name: audit-reviewer
+description: Use when acting as the SciStudio audit reviewer persona for reviews, audits, CI investigation, drift detection, conformance checks, and readiness assessment.
+---
+
+# SciStudio Audit Reviewer Skill
+
+This skill is a hard pointer only. It does not define independent policy.
+
+Before doing audit reviewer work, load and follow:
+
+- @AGENTS.md
+- @docs/ai-developer/rules.md
+- @docs/ai-developer/personas/audit-reviewer.md
+- @docs/ai-developer/specific_rules/gated-workflow.md
+
+Follow the audit context boundaries in the task instruction.
+Do not continue as audit reviewer until the persona file and common rules are loaded.

scistudio-0.3.4a32/.claude/skills/implementer/SKILL.md

@@ -0,0 +1,19 @@
+---
+name: implementer
+description: Use when acting as the SciStudio implementer persona for scoped code, tests, tool wiring, implementation-linked docs, and gate-record evidence.
+---
+
+# SciStudio Implementer Skill
+
+This skill is a hard pointer only. It does not define independent policy.
+
+Before doing implementer work, load and follow:
+
+- @AGENTS.md
+- @docs/ai-developer/rules.md
+- @docs/ai-developer/personas/implementer.md
+- @docs/ai-developer/specific_rules/gated-workflow.md
+- The matching task-specific rule under @docs/ai-developer/specific_rules/
+
+When dispatched by a manager, also follow @docs/ai-developer/specific_rules/agent-dispatch.md.
+Do not continue as implementer until the persona file and common rules are loaded.

scistudio-0.3.4a32/.claude/skills/live-implementer/SKILL.md

@@ -0,0 +1,20 @@
+---
+name: live-implementer
+description: Use when acting as the SciStudio live implementer persona for owner-directed live implementation sessions under the guided task kind.
+---
+
+# SciStudio Live Implementer Skill
+
+This skill is a hard pointer only. It does not define independent policy.
+
+Before doing live implementer work, load and follow:
+
+- @AGENTS.md
+- @docs/ai-developer/rules.md
+- @docs/ai-developer/personas/live-implementer.md
+- @docs/ai-developer/specific_rules/guided-work.md
+- @docs/ai-developer/specific_rules/gated-workflow.md
+
+The live_implementer persona is not the ordinary implementer. Do not inherit the
+ordinary implementer workflow by implication.
+Do not continue as live implementer until the persona file and common rules are loaded.

scistudio-0.3.4a32/.claude/skills/manager/SKILL.md

@@ -0,0 +1,20 @@
+---
+name: manager
+description: Use when acting as the SciStudio manager persona for planning, coordination, dispatch, hotfix ownership, integration testing, e2e testing, PR readiness, and durable status reporting.
+---
+
+# SciStudio Manager Skill
+
+This skill is a hard pointer only. It does not define independent policy.
+
+Before doing manager work, load and follow:
+
+- @AGENTS.md
+- @docs/ai-developer/rules.md
+- @docs/ai-developer/personas/manager.md
+- @docs/ai-developer/specific_rules/gated-workflow.md
+- @docs/ai-developer/specific_rules/agent-dispatch.md
+- @docs/ai-developer/specific_rules/hotfix.md when hotfix mode is explicitly authorized
+
+Use the templates under @docs/ai-developer/templates/ when dispatching agents.
+Do not continue as manager until the persona file and common rules are loaded.

scistudio-0.3.4a32/.claude/skills/scistudio-e2e-test/SKILL.md

@@ -0,0 +1,26 @@
+---
+name: scistudio-e2e-test
+description: Use when running a live end-to-end SciStudio session — driving the GUI in Chrome via Chrome MCP, verifying a PR before merge, reproducing a hotfix bug live, or any time the user says "跑 e2e", "do an e2e", "verify in Chrome", "run e2e on PR #N", or hands you a path under docs/ai-developer/e2e/. Pairs a user-filled scenario file with a pass/fail verdict written back into the same file.
+---
+
+# SciStudio E2E Test Skill
+
+This skill is a hard pointer only. It does not define independent policy.
+
+Before doing e2e work, load and follow:
+
+- @AGENTS.md
+- @docs/ai-developer/rules.md
+- @docs/ai-developer/skills/scistudio-e2e-test/SKILL.md
+- @docs/ai-developer/e2e/template.md (the scenario shape this skill expects)
+- @docs/ai-developer/e2e/README.md (workflow + naming for scenario files)
+- @docs/ai-developer/personas/manager.md when the e2e is part of a manager coordination
+- @docs/ai-developer/specific_rules/hotfix.md when the e2e is a hotfix repro
+
+The Chrome MCP recipes, dev-server lifecycle, screenshot recipes, and
+final report template live alongside the canonical SKILL.md under
+`docs/ai-developer/skills/scistudio-e2e-test/references/`. Read whichever
+reference the current step needs.
+
+Do not continue as the e2e tester until the canonical SKILL.md and the
+scenario template are loaded.

scistudio-0.3.4a32/.claude/skills/speckit-analyze/SKILL.md

@@ -0,0 +1,191 @@
+---
+name: speckit-analyze
+description: Perform a non-destructive cross-artifact consistency and quality analysis
+  across spec.md, plan.md, and tasks.md after task generation.
+compatibility: Requires spec-kit project structure with .specify/ directory
+metadata:
+  author: github-spec-kit
+  source: templates/commands/analyze.md
+disable-model-invocation: true
+---
+
+## User Input
+
+```text
+$ARGUMENTS
+```
+
+You **MUST** consider the user input before proceeding (if not empty).
+
+## Goal
+
+Identify inconsistencies, duplications, ambiguities, and underspecified items across the three core artifacts (`spec.md`, `plan.md`, `tasks.md`) before implementation. This command MUST run only after `/speckit.tasks` has successfully produced a complete `tasks.md`.
+
+## Operating Constraints
+
+**STRICTLY READ-ONLY**: Do **not** modify any files. Output a structured analysis report. Offer an optional remediation plan (user must explicitly approve before any follow-up editing commands would be invoked manually).
+
+**Constitution Authority**: The project constitution (`.specify/memory/constitution.md`) is **non-negotiable** within this analysis scope. Constitution conflicts are automatically CRITICAL and require adjustment of the spec, plan, or tasks—not dilution, reinterpretation, or silent ignoring of the principle. If a principle itself needs to change, that must occur in a separate, explicit constitution update outside `/speckit.analyze`.
+
+## Execution Steps
+
+### 1. Initialize Analysis Context
+
+Run `.specify/scripts/powershell/check-prerequisites.ps1 -Json -RequireTasks -IncludeTasks` once from repo root and parse JSON for FEATURE_DIR and AVAILABLE_DOCS. Derive absolute paths:
+
+- SPEC = FEATURE_DIR/spec.md
+- PLAN = FEATURE_DIR/plan.md
+- TASKS = FEATURE_DIR/tasks.md
+
+Abort with an error message if any required file is missing (instruct the user to run missing prerequisite command).
+For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot").
+
+### 2. Load Artifacts (Progressive Disclosure)
+
+Load only the minimal necessary context from each artifact:
+
+**From spec.md:**
+
+- Overview/Context
+- Functional Requirements
+- Success Criteria (measurable outcomes — e.g., performance, security, availability, user success, business impact)
+- User Stories
+- Edge Cases (if present)
+
+**From plan.md:**
+
+- Architecture/stack choices
+- Data Model references
+- Phases
+- Technical constraints
+
+**From tasks.md:**
+
+- Task IDs
+- Descriptions
+- Phase grouping
+- Parallel markers [P]
+- Referenced file paths
+
+**From constitution:**
+
+- Load `.specify/memory/constitution.md` for principle validation
+
+### 3. Build Semantic Models
+
+Create internal representations (do not include raw artifacts in output):
+
+- **Requirements inventory**: For each Functional Requirement (FR-###) and Success Criterion (SC-###), record a stable key. Use the explicit FR-/SC- identifier as the primary key when present, and optionally also derive an imperative-phrase slug for readability (e.g., "User can upload file" → `user-can-upload-file`). Include only Success Criteria items that require buildable work (e.g., load-testing infrastructure, security audit tooling), and exclude post-launch outcome metrics and business KPIs (e.g., "Reduce support tickets by 50%").
+- **User story/action inventory**: Discrete user actions with acceptance criteria
+- **Task coverage mapping**: Map each task to one or more requirements or stories (inference by keyword / explicit reference patterns like IDs or key phrases)
+- **Constitution rule set**: Extract principle names and MUST/SHOULD normative statements
+
+### 4. Detection Passes (Token-Efficient Analysis)
+
+Focus on high-signal findings. Limit to 50 findings total; aggregate remainder in overflow summary.
+
+#### A. Duplication Detection
+
+- Identify near-duplicate requirements
+- Mark lower-quality phrasing for consolidation
+
+#### B. Ambiguity Detection
+
+- Flag vague adjectives (fast, scalable, secure, intuitive, robust) lacking measurable criteria
+- Flag unresolved placeholders (TODO, TKTK, ???, `<placeholder>`, etc.)
+
+#### C. Underspecification
+
+- Requirements with verbs but missing object or measurable outcome
+- User stories missing acceptance criteria alignment
+- Tasks referencing files or components not defined in spec/plan
+
+#### D. Constitution Alignment
+
+- Any requirement or plan element conflicting with a MUST principle
+- Missing mandated sections or quality gates from constitution
+
+#### E. Coverage Gaps
+
+- Requirements with zero associated tasks
+- Tasks with no mapped requirement/story
+- Success Criteria requiring buildable work (performance, security, availability) not reflected in tasks
+
+#### F. Inconsistency
+
+- Terminology drift (same concept named differently across files)
+- Data entities referenced in plan but absent in spec (or vice versa)
+- Task ordering contradictions (e.g., integration tasks before foundational setup tasks without dependency note)
+- Conflicting requirements (e.g., one requires Next.js while other specifies Vue)
+
+### 5. Severity Assignment
+
+Use this heuristic to prioritize findings:
+
+- **CRITICAL**: Violates constitution MUST, missing core spec artifact, or requirement with zero coverage that blocks baseline functionality
+- **HIGH**: Duplicate or conflicting requirement, ambiguous security/performance attribute, untestable acceptance criterion
+- **MEDIUM**: Terminology drift, missing non-functional task coverage, underspecified edge case
+- **LOW**: Style/wording improvements, minor redundancy not affecting execution order
+
+### 6. Produce Compact Analysis Report
+
+Output a Markdown report (no file writes) with the following structure:
+
+## Specification Analysis Report
+
+| ID | Category | Severity | Location(s) | Summary | Recommendation |
+|----|----------|----------|-------------|---------|----------------|
+| A1 | Duplication | HIGH | spec.md:L120-134 | Two similar requirements ... | Merge phrasing; keep clearer version |
+
+(Add one row per finding; generate stable IDs prefixed by category initial.)
+
+**Coverage Summary Table:**
+
+| Requirement Key | Has Task? | Task IDs | Notes |
+|-----------------|-----------|----------|-------|
+
+**Constitution Alignment Issues:** (if any)
+
+**Unmapped Tasks:** (if any)
+
+**Metrics:**
+
+- Total Requirements
+- Total Tasks
+- Coverage % (requirements with >=1 task)
+- Ambiguity Count
+- Duplication Count
+- Critical Issues Count
+
+### 7. Provide Next Actions
+
+At end of report, output a concise Next Actions block:
+
+- If CRITICAL issues exist: Recommend resolving before `/speckit.implement`
+- If only LOW/MEDIUM: User may proceed, but provide improvement suggestions
+- Provide explicit command suggestions: e.g., "Run /speckit.specify with refinement", "Run /speckit.plan to adjust architecture", "Manually edit tasks.md to add coverage for 'performance-metrics'"
+
+### 8. Offer Remediation
+
+Ask the user: "Would you like me to suggest concrete remediation edits for the top N issues?" (Do NOT apply them automatically.)
+
+## Operating Principles
+
+### Context Efficiency
+
+- **Minimal high-signal tokens**: Focus on actionable findings, not exhaustive documentation
+- **Progressive disclosure**: Load artifacts incrementally; don't dump all content into analysis
+- **Token-efficient output**: Limit findings table to 50 rows; summarize overflow
+- **Deterministic results**: Rerunning without changes should produce consistent IDs and counts
+
+### Analysis Guidelines
+
+- **NEVER modify files** (this is read-only analysis)
+- **NEVER hallucinate missing sections** (if absent, report them accurately)
+- **Prioritize constitution violations** (these are always CRITICAL)
+- **Use examples over exhaustive rules** (cite specific instances, not generic patterns)
+- **Report zero issues gracefully** (emit success report with coverage statistics)
+
+## Context
+
+$ARGUMENTS