Not in the top 1,000 by GitHub stars
andyzengmath/quantum-loop
Spec-driven autonomous development loop for Claude Code. Combines structured PRD generation, dependency DAG execution, two-stage review gates, and Iron Law verification.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/ql-brainstorm/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → bed463b5db7e
No earlier version was observed for comparison.
skills/ql-deep-review/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → bed463b5db7e
No earlier version was observed for comparison.
skills/ql-deslop/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → bed463b5db7e
No earlier version was observed for comparison.
skills/ql-execute/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → bed463b5db7e
No earlier version was observed for comparison.
skills/ql-housekeep/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → bed463b5db7e
No earlier version was observed for comparison.
skills/ql-intent-check/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → bed463b5db7e
No earlier version was observed for comparison.
skills/ql-plan/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → bed463b5db7e
No earlier version was observed for comparison.
skills/ql-review/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → bed463b5db7e
No earlier version was observed for comparison.
skills/ql-spec/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → bed463b5db7e
No earlier version was observed for comparison.
skills/ql-verify/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → bed463b5db7e
No earlier version was observed for comparison.
Verified commit bed463b5db7ec57e30f3c3a47ca1025f95cfe453
git clone --filter=blob:none --no-checkout https://github.com/andyzengmath/quantum-loop.git .hotskills/andyzengmath-quantum-loop && git -C .hotskills/andyzengmath-quantum-loop checkout --detach bed463b5db7ec57e30f3c3a47ca1025f95cfe453
# Copy each selected skill directory from .hotskills/andyzengmath-quantum-loop into .claude/skills/<skill-name>/Heat
0.3- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- ql-brainstorm
skills/ql-brainstorm - ql-deep-review
skills/ql-deep-review - ql-deslop
skills/ql-deslop - ql-execute
skills/ql-execute - ql-housekeep
skills/ql-housekeep - ql-intent-check
skills/ql-intent-check - ql-plan
skills/ql-plan - ql-review
skills/ql-review - ql-spec
skills/ql-spec - ql-verify
skills/ql-verify
How it works
ql-brainstorm
When your agent uses it
Part of the quantum-loop autonomous development pipeline (brainstorm → spec → plan → execute → review → verify). Deep Socratic exploration of a feature idea before implementation. Asks questions one at a time, proposes 2-3 alternative approaches with trade-offs, presents design section-by-section for approval, and saves an approved design document. Use when starting a new feature, exploring an idea, or before writing a spec. Triggers on: brainstorm, explore idea, design this, think through, ql-brainstorm.
What it loads into context
Frontmatter
132 tokensAlways available to the agent
SKILL.md
3,551 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Phase 0: Phase-skip check (Phase 18 / P2.4)
- Phase 0B: Ambiguity gate (Phase 19 / P2.8, OMC deep-interview)
- Phase 1: Understand the Problem
- Phase 2: Explore Approaches
- Phase 3: Present Design Section-by-Section
- Phase 4: Save Design Document
- Phase 4d: Post-exit design-review (P5.B4 / US-006 / v0.6.3 — advisory)
- Anti-Rationalization Guards
- Output Format
Scripts executed separately
../../lib/ambiguity.sh../../lib/ambiguity.sh../../lib/ambiguity.sh../../lib/ambiguity.sh../../lib/finding-persist.sh../../lib/finding-persist.sh../../lib/finding-persist.sh../../lib/finding-synth.sh../../lib/finding-synth.sh../../lib/finding-synth.sh../../lib/finding-synth.sh../../lib/handoff.sh../../lib/handoff.sh../../lib/handoff.sh../../lib/handoff.sh../../lib/handoff.sh../../lib/handoff.sh../../lib/phase-skip.sh../../lib/phase-skip.sh../../lib/phase-skip.sh../../lib/phase-skip.sh
Files
../../.claude-plugin/marketplace.jsonasset998 bytes../../.claude-plugin/plugin.jsonasset310 bytes../../lib/ambiguity.shruns6,777 bytes../../lib/ambiguity.shruns6,777 bytes../../lib/ambiguity.shruns6,777 bytes../../lib/ambiguity.shruns6,777 bytes../../lib/finding-persist.shruns8,455 bytes../../lib/finding-persist.shruns8,455 bytes../../lib/finding-persist.shruns8,455 bytes../../lib/finding-synth.shruns8,054 bytes../../lib/finding-synth.shruns8,054 bytes../../lib/finding-synth.shruns8,054 bytes../../lib/finding-synth.shruns8,054 bytes../../lib/handoff.shruns10,701 bytes../../lib/handoff.shruns10,701 bytes../../lib/handoff.shruns10,701 bytes../../lib/handoff.shruns10,701 bytes../../lib/handoff.shruns10,701 bytes../../lib/handoff.shruns10,701 bytes../../lib/phase-skip.shruns6,185 bytes../../lib/phase-skip.shruns6,185 bytes../../lib/phase-skip.shruns6,185 bytes../../lib/phase-skip.shruns6,185 bytesSKILL.mdcore14,056 bytesSKILL.mdcore14,056 bytesSKILL.mdcore14,056 bytesSKILL.mdcore14,056 bytesSKILL.mdcore14,056 bytesSKILL.mdcore14,056 bytesSKILL.mdcore14,056 bytes
Read SKILL.md
# Quantum-Loop: Brainstorm
You are conducting a structured design exploration. Your goal is to deeply understand what the user wants to build, explore the solution space, and produce an approved design document. You must NEVER start implementing.
## Phase 0: Phase-skip check (Phase 18 / P2.4)
Before asking any question, check whether a prior `/ql-brainstorm` run already covered this exact input:
```bash
# Inputs that define "same brainstorm": verbatim user intent + any existing design doc
INTENT_TEXT=$(jq -r '.userIntent.text // ""' quantum.json 2>/dev/null)
DESIGN=$(ls docs/plans/*-design.md 2>/dev/null | tail -1) # most recent if multiple
ARGS=()
[[ -n "$INTENT_TEXT" ]] && ARGS+=("inline:$INTENT_TEXT")View the complete source on GitHubql-deep-review
When your agent uses it
Multi-perspective post-implementation review aggregator for quantum-loop. Invokes 2-7 reviewer agents in parallel based on risk score, applies actionability filter, dedups, aggregates with evidence requirements. Use AFTER the per-story two-stage review gates pass and before merging a whole-feature PR to master. Complements ql-review (per-story) with whole-feature review.
What it loads into context
Frontmatter
101 tokensAlways available to the agent
SKILL.md
2,668 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- When to use
- What it does NOT do
- Risk scoring (0-100)
- Reviewer agents (dispatched per tier)
- Actionability filter (the Chowdhury 2604.03196 fix)
- Synthesis
- Output format
- Anti-rationalization guards
- How to invoke
- Integration with existing skills
- Known limitations (honest)
Files
SKILL.mdcore10,497 bytes
Read SKILL.md
# ql-deep-review — whole-feature post-implementation review
## Purpose
quantum-loop's built-in two-stage review gate (`ql-review`: spec-compliance → code-quality) operates on ONE story at a time inside ONE worktree. It does not detect:
1. **Cross-story divergence** (e.g., story A uses `'google'` as a secret key while story B uses `'google-api-key'` for the same constant).
2. **Post-merge regressions** (test that was green in isolation breaks after integration).
3. **Drift from original user intent** (paraphrase chain from intent → design → PRD → plan → code).
4. **Low-signal comments** that look like findings but lack evidence (CRA actionability is 0.9-19.2% per Chowdhury 2604.03196; human baseline is ~60%).
`ql-deep-review` closes these gaps with a whole-feature review that runs AFTER all stories in a wave / feature pass the per-story gate.
## When to useView the complete source on GitHubql-deslop
When your agent uses it
Post-review AI-slop cleanup pass. After quality review approves a story/feature, scans only the changed files for: duplicate code, dead code, needless abstraction, boundary violations, missing tests. Proposes deletions with regression-test gate — rolls back on regression. Mandatory unless explicitly skipped via --no-deslop. Borrowed from OMC Ralph 7.5 + 7.6.
What it loads into context
Frontmatter
103 tokensAlways available to the agent
SKILL.md
2,531 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- When to use
- Opt-out
- Scope — strict file-list only
- Smell taxonomy — 5 categories
- Single-pass discipline
- Regression gate (the 7.6 step)
- Protect behavior first (regression test synthesis)
- Reviewer-only mode (writer/reviewer separation)
- Output
- Anti-rationalization guards
- Integration with existing skills
- Known limitations
- How to invoke
Files
SKILL.mdcore10,706 bytesSKILL.mdcore10,706 bytes
Read SKILL.md
# ql-deslop — post-review AI-slop cleanup
## Purpose
Review approval does not mean the code is clean. LLM-authored code routinely introduces:
- **Duplication** of helpers / types / imports under slightly different names.
- **Dead code** — functions added but never called; exports that no consumer uses.
- **Needless abstraction** — factory for one caller; wrapper that only aliases; configurable field never varied.
- **Boundary violations** — private functions accessed via string names; cross-module reaches that skip the public API.
- **Missing tests** — paths and branches not exercised by any test.
Per Schreiber & Tippe 2025, 12.1% of AI-generated files contain ≥1 CWE, and per Zhong et al. 2026 (278k conversations) AI suggestions increase cyclomatic complexity 10-50× more than human edits. Without an explicit cleanup step, every autonomous run accumulates slop.
`ql-deslop` adds an explicit cleanup pass AFTER the story's review gate passes but BEFORE the merge to the feature branch. Borrowed directly from OMC Ralph Steps 7.5 (deslop) + 7.6 (regression re-verify).View the complete source on GitHubql-execute
When your agent uses it
Part of the quantum-loop autonomous development pipeline (brainstorm → spec → plan → execute → review → verify). Run the autonomous execution loop. Reads quantum.json, queries the dependency DAG, implements stories with TDD and two-stage review gates. Supports parallel execution via native worktree isolation. Use after /quantum-loop:plan has created quantum.json. Triggers on: execute, run loop, start building, ql-execute.
What it loads into context
Frontmatter
112 tokensAlways available to the agent
SKILL.md
2,073 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Execution
- Orchestrator liveness gate (N14 / US-002 — v0.7.0)
- Autonomous CLI Alternative
- Signals
- Post-review slop-cleanup hook (Phase 9 / P1.6)
- Post-pipeline review hook (Phase 8 / P1.1 + P1.2)
Scripts executed separately
../../lib/deep-review.sh../../lib/deep-review.sh../../lib/deep-review.sh../../lib/deep-review.sh../../lib/deep-review.sh../../lib/deep-review.sh../../lib/deslop.sh../../lib/deslop.sh../../lib/deslop.sh../../lib/deslop.sh../../lib/deslop.sh../../lib/deslop.sh../../lib/deslop.sh../../lib/deslop.sh../../lib/orchestrator-liveness.sh../../lib/orchestrator-liveness.sh../../lib/orchestrator-liveness.sh../../lib/orchestrator-liveness.sh../../lib/orchestrator-liveness.sh../../lib/wave-boundary.sh../../lib/wave-boundary.sh../../lib/wave-boundary.sh../../lib/wave-boundary.sh
Files
../../lib/deep-review.shruns23,759 bytes../../lib/deep-review.shruns23,759 bytes../../lib/deep-review.shruns23,759 bytes../../lib/deep-review.shruns23,759 bytes../../lib/deep-review.shruns23,759 bytes../../lib/deep-review.shruns23,759 bytes../../lib/deslop.shruns8,915 bytes../../lib/deslop.shruns8,915 bytes../../lib/deslop.shruns8,915 bytes../../lib/deslop.shruns8,915 bytes../../lib/deslop.shruns8,915 bytes../../lib/deslop.shruns8,915 bytes../../lib/deslop.shruns8,915 bytes../../lib/deslop.shruns8,915 bytes../../lib/orchestrator-liveness.shruns12,598 bytes../../lib/orchestrator-liveness.shruns12,598 bytes../../lib/orchestrator-liveness.shruns12,598 bytes../../lib/orchestrator-liveness.shruns12,598 bytes../../lib/orchestrator-liveness.shruns12,598 bytes../../lib/wave-boundary.shruns7,366 bytes../../lib/wave-boundary.shruns7,366 bytes../../lib/wave-boundary.shruns7,366 bytes../../lib/wave-boundary.shruns7,366 bytesSKILL.mdcore8,109 bytesSKILL.mdcore8,109 bytesSKILL.mdcore8,109 bytesSKILL.mdcore8,109 bytesSKILL.mdcore8,109 bytes
Read SKILL.md
# Quantum-Loop: Execute
Run the autonomous execution loop to implement all stories in quantum.json.
## Prerequisites
Before starting:
1. `quantum.json` must exist (created by `/quantum-loop:plan`)
2. The project must be a git repository
3. Project build tools must be available (npm, pip, cargo, etc.)
If prerequisites are not met, inform the user and stop.
## ExecutionView the complete source on GitHubql-housekeep
When your agent uses it
Detect repo-hygiene issues that accumulate during long-running autonomous development (merge-conflict markers, orphan worktrees, CPC-variant duplicates, stale branches, version-manifest drift). Detection-only by default — reports findings, never deletes or modifies without explicit user confirmation.
What it loads into context
Frontmatter
73 tokensAlways available to the agent
SKILL.md
2,224 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- When to use
- What it detects
- Anti-rationalization guards
- How to run
- What it does NOT do
- Output format
- Integration with other skills
- Known limitations
Files
SKILL.mdcore8,269 bytesSKILL.mdcore8,269 bytesSKILL.mdcore8,269 bytesSKILL.mdcore8,269 bytesSKILL.mdcore8,269 bytesSKILL.mdcore8,269 bytesSKILL.mdcore8,269 bytesSKILL.mdcore8,269 bytesSKILL.mdcore8,269 bytesSKILL.mdcore8,269 bytesSKILL.mdcore8,269 bytes
Read SKILL.md
# ql-housekeep — repo hygiene detector
## Purpose
`ql-housekeep` surfaces the hygiene failures that accumulate when an autonomous development pipeline runs for weeks without human sweep. It is a **detector**, not an actuator. Auto-fix is explicitly out of scope.
This skill exists because `idea-stage/AUDIT_QL.md` catalogued eight categories of hygiene failure on master. The first job of the next pipeline iteration is to not produce that state again.
## When to use
- Before starting a new `/ql-brainstorm` cycle on a repo that has been running parallel execution for weeks.
- As a gate in `ql-execute` between waves if you suspect accumulated drift.
- Manually, when you want a structured view of "what is wrong with the repo right now that the runtime cannot see".
View the complete source on GitHubql-intent-check
When your agent uses it
Intent-drift audit for quantum-loop. Compares the user's original intent (immutable snapshot) against downstream artifacts (design.md → PRD → quantum.json ACs → implementation) to detect semantic divergence. Flags drift with file:line evidence. Use before merge or when specs feel "rewritten."
What it loads into context
Frontmatter
80 tokensAlways available to the agent
SKILL.md
2,228 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Immutable intent snapshot
- Stages audited
- Detection rules
- Input
- Output
- Anti-rationalization guards
- How to invoke
- Integration with existing skills
- Required quantum.json schema extension
- Known limitations (honest)
Files
SKILL.mdcore8,902 bytesSKILL.mdcore8,902 bytes
Read SKILL.md
# ql-intent-check — intent-drift audit
## Purpose
Long pipelines (brainstorm → spec → plan → execute → review) paraphrase. Each stage re-reads an upstream artifact and rewrites it in its own format. Over 5 stages and 20+ agent invocations, the user's original intent can drift significantly — ACs silently reinterpreted, non-goals forgotten, constraints softened.
Academic backing:
- **Semantic Consensus Framework (SCF, arXiv:2604.16339)**: formally names "Semantic Intent Divergence" as the root cause of multi-agent SWE failures. Prescribes per-agent Semantic Intent Graph + Drift Monitor.
- **Agent Drift (arXiv:2601.04170)**: introduces Agent Stability Index (ASI) and shows all models drift under pressure.
- **Goal Drift in LM Agents (arXiv:2505.02709)**: Claude 3.5 Sonnet holds goals for 100K tokens but drifts under competing objectives.
`ql-intent-check` operationalizes a lean version of SCF's Drift Monitor for quantum-loop's pipeline.
## Immutable intent snapshotView the complete source on GitHubql-plan
When your agent uses it
Part of the quantum-loop autonomous development pipeline (brainstorm → spec → plan → execute → review → verify). Convert a PRD into machine-readable quantum.json with dependency DAG, granular 2-5 minute tasks, and execution metadata. Use after creating a spec with /quantum-loop:spec. Triggers on: create plan, convert to json, plan tasks, generate quantum json, ql-plan.
What it loads into context
Frontmatter
106 tokensAlways available to the agent
SKILL.md
9,807 tokensWhen the skill is activated
Reference documents
4,846 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Phase 0: Phase-skip check (Phase 18 / P2.4)
- Prerequisite: read prior-stage handoffs (Phase 15 / P2.3)
- Step 1: Read the PRD
- Step 2: Analyze Dependencies
- Step 3: Decompose Stories into Tasks
- Step 4: Generate quantum.json
- Step 5: Validate and Save
- Step 6: Set Up Runner Scripts
- Step 7: DAG Validation
- Step 8: Sprint-Contract write per story (G3 / US-004 / v0.6.3)
- Step 9: Post-exit plan-review (P5.B4 / US-008 / v0.6.3 — advisory)
- Anti-Rationalization Guards
Scripts executed separately
../../lib/finding-persist.sh../../lib/finding-persist.sh../../lib/finding-persist.sh../../lib/finding-synth.sh../../lib/finding-synth.sh../../lib/finding-synth.sh../../lib/finding-synth.sh../../lib/handoff.sh../../lib/handoff.sh../../lib/handoff.sh../../lib/handoff.sh../../lib/handoff.sh../../lib/handoff.sh../../lib/phase-skip.sh../../lib/phase-skip.sh../../lib/phase-skip.sh../../lib/phase-skip.sh../../lib/reuse-scan.sh../../lib/reuse-scan.sh../../lib/reuse-scan.sh../../lib/reuse-scan.sh
Files
../../lib/finding-persist.shruns8,455 bytes../../lib/finding-persist.shruns8,455 bytes../../lib/finding-persist.shruns8,455 bytes../../lib/finding-synth.shruns8,054 bytes../../lib/finding-synth.shruns8,054 bytes../../lib/finding-synth.shruns8,054 bytes../../lib/finding-synth.shruns8,054 bytes../../lib/handoff.shruns10,701 bytes../../lib/handoff.shruns10,701 bytes../../lib/handoff.shruns10,701 bytes../../lib/handoff.shruns10,701 bytes../../lib/handoff.shruns10,701 bytes../../lib/handoff.shruns10,701 bytes../../lib/phase-skip.shruns6,185 bytes../../lib/phase-skip.shruns6,185 bytes../../lib/phase-skip.shruns6,185 bytes../../lib/phase-skip.shruns6,185 bytes../../lib/reuse-scan.shruns4,796 bytes../../lib/reuse-scan.shruns4,796 bytes../../lib/reuse-scan.shruns4,796 bytes../../lib/reuse-scan.shruns4,796 bytesSKILL.mdcore40,286 bytesSKILL.mdcore40,286 bytesSKILL.mdcore40,286 bytesSKILL.mdcore40,286 bytesSKILL.mdcore40,286 bytesSKILL.mdcore40,286 bytesSKILL.mdcore40,286 bytesSKILL.mdcore40,286 bytesSKILL.mdcore40,286 bytesSKILL.mdcore40,286 bytesSKILL.mdcore40,286 bytesSKILL.mdcore40,286 bytesSKILL.mdcore40,286 bytesSKILL.mdcore40,286 bytesSKILL.mdcore40,286 bytesreferences/contract-shapes.mddoc8,661 bytesreferences/dag-validation.mddoc10,230 bytes
Read SKILL.md
# Quantum-Loop: Plan
You are converting a Product Requirements Document (PRD) into a machine-readable `quantum.json` file that will drive autonomous execution. Every decision you make here determines whether the execution loop succeeds or fails.
## Phase 0: Phase-skip check (Phase 18 / P2.4)
Before reading the PRD, check whether a prior `/ql-plan` run already converted the same PRD + spec handoff into quantum.json:
```bash
PRD=$(ls -t tasks/prd-*.md 2>/dev/null | head -1)
SPEC_HANDOFF=".handoffs/spec.md"
ARGS=()
[[ -n "$PRD" ]] && ARGS+=("$PRD")
[[ -f "$SPEC_HANDOFF" ]] && ARGS+=("$SPEC_HANDOFF")View the complete source on GitHubql-review
When your agent uses it
Part of the quantum-loop autonomous development pipeline (brainstorm → spec → plan → execute → review → verify). Two-stage code review. Spec compliance first, then code quality. Use after implementation or before merge. Triggers on: review code, code review, check implementation, ql-review.
What it loads into context
Frontmatter
83 tokensAlways available to the agent
SKILL.md
1,627 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Why Two Stages?
- Usage Modes
- Standalone Workflow
- Handling Review Feedback
- Output Format
- Stage 3: Cross-Story Integration Review
- Anti-Rationalization Guards
Files
SKILL.mdcore6,657 bytesSKILL.mdcore6,657 bytesSKILL.mdcore6,657 bytes
Read SKILL.md
# Quantum-Loop: Review
You orchestrate a two-stage code review. Stage 1 (spec compliance) MUST pass before Stage 2 (code quality) begins. This order is absolute.
## Why Two Stages?
Code that doesn't match the spec is waste -- no matter how well-written. Checking spec compliance first prevents spending review effort on code that needs to be rewritten anyway.
## Usage Modes
### Mode 1: Within /quantum-loop:execute (automated)
Called automatically by the execution loop after a story's quality checks pass.
Receives story context from quantum.json.
View the complete source on GitHubql-spec
When your agent uses it
Part of the quantum-loop autonomous development pipeline (brainstorm → spec → plan → execute → review → verify). Generate a structured Product Requirements Document (PRD) with user stories, acceptance criteria, and functional requirements. Use when you have an approved design and need formal requirements, or when starting from scratch. Triggers on: create spec, write prd, spec out, requirements for, ql-spec.
What it loads into context
Frontmatter
106 tokensAlways available to the agent
SKILL.md
3,760 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Phase 0: Phase-skip check (Phase 18 / P2.4)
- Prerequisite: read prior-stage handoffs (Phase 15 / P2.3)
- Step 1: Gather Context
- Step 2: Ask Clarifying Questions
- Step 3: Generate the PRD
- Step 4: Save the PRD
- Acceptance Criteria Quality Standards
- Anti-Rationalization Guards
- Pre-Save Checklist
- Exit: write stage handoff (Phase 15 / P2.3)
- Post-exit prd-review (P5.B4 / US-007 / v0.6.3 — advisory)
Scripts executed separately
../../lib/finding-persist.sh../../lib/finding-persist.sh../../lib/finding-persist.sh../../lib/finding-synth.sh../../lib/finding-synth.sh../../lib/finding-synth.sh../../lib/finding-synth.sh../../lib/handoff.sh../../lib/handoff.sh../../lib/handoff.sh../../lib/handoff.sh../../lib/handoff.sh../../lib/handoff.sh../../lib/phase-skip.sh../../lib/phase-skip.sh../../lib/phase-skip.sh../../lib/phase-skip.sh
Files
../../lib/finding-persist.shruns8,455 bytes../../lib/finding-persist.shruns8,455 bytes../../lib/finding-persist.shruns8,455 bytes../../lib/finding-synth.shruns8,054 bytes../../lib/finding-synth.shruns8,054 bytes../../lib/finding-synth.shruns8,054 bytes../../lib/finding-synth.shruns8,054 bytes../../lib/handoff.shruns10,701 bytes../../lib/handoff.shruns10,701 bytes../../lib/handoff.shruns10,701 bytes../../lib/handoff.shruns10,701 bytes../../lib/handoff.shruns10,701 bytes../../lib/handoff.shruns10,701 bytes../../lib/phase-skip.shruns6,185 bytes../../lib/phase-skip.shruns6,185 bytes../../lib/phase-skip.shruns6,185 bytes../../lib/phase-skip.shruns6,185 bytesSKILL.mdcore14,757 bytesSKILL.mdcore14,757 bytesSKILL.mdcore14,757 bytesSKILL.mdcore14,757 bytesSKILL.mdcore14,757 bytesSKILL.mdcore14,757 bytesSKILL.mdcore14,757 bytesSKILL.mdcore14,757 bytes
Read SKILL.md
# Quantum-Loop: Spec
You are generating a formal Product Requirements Document (PRD). This document will be consumed by `/quantum-loop:plan` to produce machine-readable tasks for autonomous execution. Write for junior developers or AI agents -- be explicit, unambiguous, and verifiable.
## Phase 0: Phase-skip check (Phase 18 / P2.4)
Before asking any clarifying question, check whether a prior `/ql-spec` run already converted the same design + brainstorm handoff into a PRD:
```bash
DESIGN=$(ls docs/plans/*-design.md 2>/dev/null | tail -1)
BS_HANDOFF=".handoffs/brainstorm.md"
ARGS=()
[[ -n "$DESIGN" ]] && ARGS+=("$DESIGN")
[[ -f "$BS_HANDOFF" ]] && ARGS+=("$BS_HANDOFF")View the complete source on GitHubql-verify
When your agent uses it
Part of the quantum-loop autonomous development pipeline (brainstorm → spec → plan → execute → review → verify). Iron Law verification gate. Requires fresh evidence before any completion claim. Use before claiming work is done, before committing, or before marking a story as passed. Triggers on: verify, check, prove it works, ql-verify.
What it loads into context
Frontmatter
95 tokensAlways available to the agent
SKILL.md
2,187 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Inline-vs-adversarial review split (P5.A7 / US-007)
- The Iron Law
- The 5-Step Gate Function
- Verification Requirements by Claim Type
- Red Flags -- STOP Immediately
- Anti-Rationalization Table
- Integration with /quantum-loop:execute
- Standalone Usage
- Integration Verification (for multi-story features)
Files
SKILL.mdcore8,854 bytes
Read SKILL.md
# Quantum-Loop: Verify
## Inline-vs-adversarial review split (P5.A7 / US-007)
The verify gate distinguishes **routine** checks (deterministic verdict, exit-code 0/non-0) from **adversarial** checks (require judgement) and routes them differently:
| Check kind | Examples | Mode | Rationale |
|---|---|---|---|
| Routine | typecheck, lint, full test suite, file-org conventions | **inline-only** in implementer prompt before STORY_PASSED | Verdict is deterministic; subagent round-trip adds 25min for zero signal value |
| Adversarial | cross-story file conflicts, intent drift vs PRD, security review, architecture / API-shape | **subagent dispatch** (spec-reviewer, quality-reviewer, security-reviewer, architect) | Requires judgement, context, and human-readable explanation that grep cannot provide |
Routine checks emit literal tokens the orchestrator greps for evidence:
- `[INLINE-REVIEW] typecheck OK`
- `[INLINE-REVIEW] lint OK`View the complete source on GitHubSkills included
- ql-brainstorm
- ql-deep-review
- ql-deslop
- ql-execute
- ql-housekeep
- ql-intent-check
- ql-plan
- ql-review
- ql-spec
- ql-verify
Repository facts
- License
- MIT
- Created
- Feb 16, 2026
- Last pushed
- Jun 25, 2026
- Forks
- 0
- Open issues
- 5
- Project activity
- Slowing
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 5, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 109 notes
lib/ambiguity.sh:1Analysis incomplete: Referenced executable target unavailable; not analyzedlib/ambiguity.sh:1Analysis incomplete: Referenced executable target unavailable; not analyzedlib/ambiguity.sh:1Analysis incomplete: Referenced executable target unavailable; not analyzedlib/finding-persist.sh:1Analysis incomplete: Referenced executable target unavailable; not analyzedlib/finding-persist.sh:1Analysis incomplete: Referenced executable target unavailable; not analyzedlib/finding-synth.sh:1Analysis incomplete: Referenced executable target unavailable; not analyzedlib/finding-synth.sh:1Analysis incomplete: Referenced executable target unavailable; not analyzedlib/finding-synth.sh:1Analysis incomplete: Referenced executable target unavailable; not analyzedlib/handoff.sh:1Analysis incomplete: Referenced executable target unavailable; not analyzedlib/handoff.sh:1Analysis incomplete: Referenced executable target unavailable; not analyzedlib/handoff.sh:1Analysis incomplete: Referenced executable target unavailable; not analyzedlib/handoff.sh:1Analysis incomplete: Referenced executable target unavailable; not analyzedlib/handoff.sh:1Analysis incomplete: Referenced executable target unavailable; not analyzedlib/phase-skip.sh:1Analysis incomplete: Referenced executable target unavailable; not analyzedlib/phase-skip.sh:1Analysis incomplete: Referenced executable target unavailable; not analyzedlib/phase-skip.sh:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ql-brainstorm/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ql-brainstorm/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ql-brainstorm/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ql-brainstorm/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- 4 broad permissionsin 4 files: ql-deep-review/SKILL.md:1 ql-deslop/SKILL.md:1 ql-housekeep/SKILL.md:1 and 1 more
- 23 dangerous shell commandsin 5 files: lib/finding-persist.sh:109 lib/orchestrator-liveness.sh:142 ql-brainstorm/SKILL.md:244 and 2 more
- 13 network referencesin 2 files: lib/finding-persist.sh:148 ql-plan/SKILL.md:616
- No hidden or obfuscated text
- No instruction overrides
- 82 executable scriptsin 10 files: lib/handoff.sh:1 lib/finding-synth.sh:1 lib/phase-skip.sh:1 and 7 more
- No access to secrets
- No requests to vote in Hot
Show all 122 signals by file
lib/ambiguity.sh
lib/deep-review.sh
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable
lib/deslop.sh
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable
lib/finding-persist.sh
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Dangerous shell operationline 109
cp "$csv" "$tmp" || { rm -f "$tmp"; return 1; } - Dangerous shell operationline 109
cp "$csv" "$tmp" || { rm -f "$tmp"; return 1; } - Dangerous shell operationline 109
cp "$csv" "$tmp" || { rm -f "$tmp"; return 1; } - Dangerous shell operationline 111
printf '%s\n' "$header" > "$tmp" || { rm -f "$tmp"; return 1; } - Dangerous shell operationline 111
printf '%s\n' "$header" > "$tmp" || { rm -f "$tmp"; return 1; } - Dangerous shell operationline 111
printf '%s\n' "$header" > "$tmp" || { rm -f "$tmp"; return 1; } - Dangerous shell operationline 113
printf '%s\n' "$row" >> "$tmp" || { rm -f "$tmp"; return 1; } - Dangerous shell operationline 113
printf '%s\n' "$row" >> "$tmp" || { rm -f "$tmp"; return 1; } - Dangerous shell operationline 113
printf '%s\n' "$row" >> "$tmp" || { rm -f "$tmp"; return 1; } - Dangerous shell operationline 114
mv -f "$tmp" "$csv" || { rm -f "$tmp"; return 1; } - Dangerous shell operationline 114
mv -f "$tmp" "$csv" || { rm -f "$tmp"; return 1; } - Dangerous shell operationline 114
mv -f "$tmp" "$csv" || { rm -f "$tmp"; return 1; } - Network accessline 148
local snap_tmp snap_tmp=$(mktemp "${snap}.XXXXXX") || return 1 if ! jq -nc \ - Network accessline 148
local snap_tmp snap_tmp=$(mktemp "${snap}.XXXXXX") || return 1 if ! jq -nc \ - Network accessline 148
local snap_tmp snap_tmp=$(mktemp "${snap}.XXXXXX") || return 1 if ! jq -nc \ - Network accessline 149
snap_tmp=$(mktemp "${snap}.XXXXXX") || return 1 if ! jq -nc \ --arg stage "$stage" \ - Network accessline 149
snap_tmp=$(mktemp "${snap}.XXXXXX") || return 1 if ! jq -nc \ --arg stage "$stage" \ - Network accessline 149
snap_tmp=$(mktemp "${snap}.XXXXXX") || return 1 if ! jq -nc \ --arg stage "$stage" \ - Network accessline 150
if ! jq -nc \ - Network accessline 150
if ! jq -nc \ - Network accessline 150
if ! jq -nc \ - Dangerous shell operationline 158
rm -f "$snap_tmp" - Dangerous shell operationline 158
rm -f "$snap_tmp" - Dangerous shell operationline 158
rm -f "$snap_tmp" - Dangerous shell operationline 163
mv -f "$snap_tmp" "$snap" || { rm -f "$snap_tmp"; return 1; } - Dangerous shell operationline 163
mv -f "$snap_tmp" "$snap" || { rm -f "$snap_tmp"; return 1; } - Dangerous shell operationline 163
mv -f "$snap_tmp" "$snap" || { rm -f "$snap_tmp"; return 1; }
lib/finding-synth.sh
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable
lib/handoff.sh
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable
lib/orchestrator-liveness.sh
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Dangerous shell operationline 142
trap 'rm -f "$respawn_tmpfile"' RETURN - Dangerous shell operationline 231
trap 'rm -f "$tmpfile"' RETURN
lib/phase-skip.sh
- Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env bash - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable
lib/reuse-scan.sh
lib/wave-boundary.sh
skills/ql-brainstorm/SKILL.md
- Dangerous shell operationline 244
rm -f "$REVIEW_LOG"
skills/ql-deep-review/SKILL.md
- Broad permissionsline 1
Read, Write, Edit, Grep, Glob, Bash, Agent
skills/ql-deslop/SKILL.md
- Broad permissionsline 1
Read, Grep, Glob, Bash, Edit, Write
skills/ql-housekeep/SKILL.md
- Broad permissionsline 1
Read, Grep, Glob, Bash
skills/ql-intent-check/SKILL.md
- Broad permissionsline 1
Read, Grep, Glob, Bash
skills/ql-plan/SKILL.md
- Network accessline 616
> ```bash > # Download runner scripts from the quantum-loop repo > curl -sO https://raw.githubusercontent.com/andyzengmath/quantum-loop/main/templates/quantum-loop.sh && chmod +x quantum-loop.sh - Network accessline 617
> # Download runner scripts from the quantum-loop repo > curl -sO https://raw.githubusercontent.com/andyzengmath/quantum-loop/main/templates/quantum-loop.sh && chmod +x quantum-loop.sh > curl -sO https://raw.githubusercontent.com/andy - Network accessline 618
> curl -sO https://raw.githubusercontent.com/andyzengmath/quantum-loop/main/templates/quantum-loop.sh && chmod +x quantum-loop.sh - Network accessline 619
> curl -sO https://raw.githubusercontent.com/andyzengmath/quantum-loop/main/templates/quantum-loop.ps1 - Dangerous shell operationline 774
rm -f "$REVIEW_LOG"
skills/ql-spec/SKILL.md
- Dangerous shell operationline 286
rm -f "$REVIEW_LOG"
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Declared and executed: 3 facts
- Allows Bash without restrictions, though it has no scripts or shell blocksql-deep-review/SKILL.md:4High confidence
- Allows Bash without restrictions, though it has no scripts or shell blocksql-deslop/SKILL.md:4High confidence
- Allows Bash without restrictions, though it has no scripts or shell blocksql-intent-check/SKILL.md:4High confidence
Signal confidence: 122 facts
- Executable script in code of a file that runslib/ambiguity.sh:1High confidence
- Executable script in code of a file that runslib/ambiguity.sh:1High confidence
- Executable script in code of a file that runslib/ambiguity.sh:1High confidence
- Executable script in code of a file that runslib/ambiguity.sh:1High confidence
- Executable script in code of a file that runslib/deep-review.sh:1High confidence
- Executable script in code of a file that runslib/deep-review.sh:1High confidence
- Executable script in code of a file that runslib/deep-review.sh:1High confidence
- Executable script in code of a file that runslib/deep-review.sh:1High confidence
- Executable script in code of a file that runslib/deep-review.sh:1High confidence
- Executable script in code of a file that runslib/deep-review.sh:1High confidence
- Executable script in code of a file that runslib/deslop.sh:1High confidence
- Executable script in code of a file that runslib/deslop.sh:1High confidence
- Executable script in code of a file that runslib/deslop.sh:1High confidence
- Executable script in code of a file that runslib/deslop.sh:1High confidence
- Executable script in code of a file that runslib/deslop.sh:1High confidence
- Executable script in code of a file that runslib/deslop.sh:1High confidence
- Executable script in code of a file that runslib/deslop.sh:1High confidence
- Executable script in code of a file that runslib/deslop.sh:1High confidence
- Executable script in code of a file that runslib/finding-persist.sh:1High confidence
- Executable script in code of a file that runslib/finding-persist.sh:1High confidence
- Executable script in code of a file that runslib/finding-persist.sh:1High confidence
- Executable script in code of a file that runslib/finding-persist.sh:1High confidence
- Executable script in code of a file that runslib/finding-persist.sh:1High confidence
- Executable script in code of a file that runslib/finding-persist.sh:1High confidence
- Executable script in code of a file that runslib/finding-persist.sh:1High confidence
- Executable script in code of a file that runslib/finding-persist.sh:1High confidence
- Executable script in code of a file that runslib/finding-persist.sh:1High confidence
- Dangerous shell operation in code of a file that runslib/finding-persist.sh:109High confidence
- Dangerous shell operation in code of a file that runslib/finding-persist.sh:109High confidence
- Dangerous shell operation in code of a file that runslib/finding-persist.sh:109High confidence
- Dangerous shell operation in code of a file that runslib/finding-persist.sh:111High confidence
- Dangerous shell operation in code of a file that runslib/finding-persist.sh:111High confidence
- Dangerous shell operation in code of a file that runslib/finding-persist.sh:111High confidence
- Dangerous shell operation in code of a file that runslib/finding-persist.sh:113High confidence
- Dangerous shell operation in code of a file that runslib/finding-persist.sh:113High confidence
- Dangerous shell operation in code of a file that runslib/finding-persist.sh:113High confidence
- Dangerous shell operation in code of a file that runslib/finding-persist.sh:114High confidence
- Dangerous shell operation in code of a file that runslib/finding-persist.sh:114High confidence
- Dangerous shell operation in code of a file that runslib/finding-persist.sh:114High confidence
- Network access in code of a file that runslib/finding-persist.sh:148High confidence
- Network access in code of a file that runslib/finding-persist.sh:148High confidence
- Network access in code of a file that runslib/finding-persist.sh:148High confidence
- Network access in code of a file that runslib/finding-persist.sh:149High confidence
- Network access in code of a file that runslib/finding-persist.sh:149High confidence
- Network access in code of a file that runslib/finding-persist.sh:149High confidence
- Network access in code of a file that runslib/finding-persist.sh:150High confidence
- Network access in code of a file that runslib/finding-persist.sh:150High confidence
- Network access in code of a file that runslib/finding-persist.sh:150High confidence
- Dangerous shell operation in code of a file that runslib/finding-persist.sh:158High confidence
- Dangerous shell operation in code of a file that runslib/finding-persist.sh:158High confidence
and 72 more
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/ql-brainstorm/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/ql-brainstorm/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/ql-brainstorm/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/ql-brainstorm/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/ql-brainstorm/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.