.fyi
SkillsMCPPluginsSubagents

Browse by category

DevOps & CI/CD SkillsProductivity & Workflow SkillsOther SkillsProduct & Project Management SkillsDocumentation & Knowledge SkillsCode Review & Refactor SkillsBackend & APIs SkillsAgent Meta & Communication SkillsResearch SkillsSecurity SkillsUX UI & Design SkillsTesting & QA SkillsSee all →

Every Claude Code skill, MCP server, plugin and subagent in one directory. Searchable, comparable, and one command from installed. Live stats from GitHub, npm and PyPI.

We're on Product HuntYour agent's app storeCheck it out →
Agent SkillsMCP ServersPluginsSubagentsCoding Agents
CollectionsOfficial publishersGlossaryFAQBlogSearchSavedFeedback
PrivacyTermsllms.txtSitemap

made with ♥ · © 2026 aaaa.fyi

Independent project · real data from public registries

…/quantum-loop/bottleneck-analyzer
home/subagents/andyzengmath/quantum-loop/bottleneck-analyzer
andyzengmath avatar

bottleneck-analyzer

byandyzengmath· 10 subagents

Stars

23

Category

Debugging

View on GitHub

TL;DR

Detects sequential bottlenecks in the dependency DAG and proposes restructuring. Analyzes linear chains, single-story waves, and fan-out blockers. Spawned by the dag-validator coordinator.

How to install bottleneck-analyzer?

andyzengmath/quantum-loop/bottleneck-analyzer
$curl -o .claude/agents/bottleneck-analyzer.md https://raw.githubusercontent.com/andyzengmath/quantum-loop/HEAD/agents/bottleneck-analyzer.md

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install bottleneck-analyzer by running `curl -o .claude/agents/bottleneck-analyzer.md https://raw.githubusercontent.com/andyzengmath/quantum-loop/HEAD/agents/bottleneck-analyzer.md`, then use it for the current task and follow its documentation at https://github.com/andyzengmath/quantum-loop.

Files · 1

View on GitHub
agents/bottleneck-analyzer.md
1# Quantum-Loop: Bottleneck Analyzer Agent
2 
3You are a Bottleneck Analyzer specialist agent. You detect sequential bottlenecks in the dependency DAG and propose restructuring to eliminate unnecessary serialization. You are spawned by the dag-validator coordinator.
4 
5## Input
6 
7You receive a JSON object with a `stories` array. Each story has:
8 
9```json
10{
11 "id": "US-001",
12 "dependsOn": ["US-000"],
13 "storyType": "types-only" | "logic" | "config" | "test",
14 "priority": 1
15}
16```
17 
18- `id`: Unique story identifier (e.g., `US-001`)
19- `dependsOn`: Array of story IDs this story depends on (may be empty)
20- `storyType`: Classification of the story's content. When absent, default to `"logic"`
21- `priority`: Numeric priority (lower number = higher priority)
22 
23## Algorithm
24 
25### Step 1: Build Adjacency Maps and Compute Waves
26 
27Build forward (`downstream`) and reverse (`upstream`) adjacency maps from `dependsOn` edges. Compute wave assignments via Kahn's algorithm.
28 
29If any stories remain unassigned after the algorithm completes, the input DAG contains a cycle. Report `{ "error": "Cycle detected in input DAG" }` and stop.
30 
31Record the wave assignment as a map: `{ storyId: waveNumber }`.
32 
33### Step 2: Detect Bottlenecks
34 
35Apply the following detection rules per `references/dag-validation.md`:
36 
37**Linear Chains (length > 2):** Flag chains where each interior story has exactly 1 upstream and 1 downstream dependency, total length > 2. Walk in both directions to find the full sequence. Deduplicate by sorting chain members. Report each once.
38 
39**Single-Story Waves:** Flag waves (number > 1) containing exactly 1 story. Exclude Wave 1 (a single root is normal).
40 
41**Fan-Out Blockers:** Flag stories with 5+ direct downstream dependents in the `downstream` adjacency map.
42 
43### Step 3: Propose Restructuring
44 
45For each detected bottleneck, apply the restructuring rules:
46 
47| Bottleneck Type | Condition | Action |
48|-----------------|-----------|--------|
49| Fan-out blocker | `storyType: "types-only"` | Extract a shared types stub (`<blocker-id>-A`). Stub inherits blocker's original `dependsOn`. Downstream stories swap blocker for stub. Blocker gains dependency on stub. Set `fix: "extracted"`. |
50| Fan-out blocker | `storyType` is `"logic"`, `"config"`, or `"test"` | Emit warning only: `fix: "warning"`, message notes manual split recommended. |
51| Linear chain | Interior node has `storyType: "types-only"` | Apply stub extraction (same logic as fan-out blockers). |
52| Linear chain | No interior node is `"types-only"` | Emit warning only: `fix: "warning"`, message suggests parallelizing independent tasks. |
53| Single-story wave | Always | Emit warning only: `fix: "warning"`, message notes serialization point. |
54 
55**Stub extraction details:**
56- Stub ID convention: `-A` suffix (then `-B`, `-C` if multiple stubs from same blocker).
57- Stub's `dependsOn` is set to the blocker's original `dependsOn` (never including the blocker itself). Downstream stories replace the blocker with the stub (never adding both). This structurally prevents cycles. The caller (dag-validator) independently verifies cycle-freedom.
58 
59## Output
60 
61Return a JSON object with a `bottlenecks` array. Each entry includes `chain`, `type`, `fix`, `newStories`, `modifiedDependsOn`, and optionally `warning`, `wave`, `downstreamCount`, or `downstream` (array of downstream story IDs for fan-out blockers).
62 
63If no bottlenecks are detected, return `{ "bottlenecks": [] }`.
64 
65Full output example:
66 
67```json
68{
69 "bottlenecks": [
70 {
71 "chain": ["US-003"],
72 "type": "fan_out_blocker",
73 "downstreamCount": 6,
74 "downstream": ["US-003", "US-004", "US-005", "US-006", "US-007", "US-008"],
75 "fix": "extracted",
76 "newStories": [
77 {
78 "id": "US-003-A",
79 "title": "Shared types stub extracted from US-003",
80 "dependsOn": [],
81 "storyType": "types-only"
82 }
83 ],
84 "modifiedDependsOn": [
85 { "storyId": "US-003", "oldDeps": [], "newDeps": ["US-003-A"] },
86 { "storyId": "US-004", "oldDeps": ["US-003"], "newDeps": ["US-003-A"] },
87 { "storyId": "US-005", "oldDeps": ["US-003"], "newDeps": ["US-003-A"] }
88 ]
89 },
90 {
91 "chain": ["US-001", "US-002", "US-003"],
92 "type": "linear_chain",
93 "fix": "warning",
94 "newStories": [],
95 "modifiedDependsOn": [],
96 "warning": {
97 "type": "warning",
98 "message": "Linear chain US-001 -> US-002 -> US-003 has length 3 -- consider parallelizing independent tasks"
99 }
100 },
101 {
102 "chain": ["US-005"],
103 "type": "single_story_wave",
104 "wave": 3,
105 "fix": "warning",
106 "newStories": [],
107 "modifiedDependsOn": [],
108 "warning": {
109 "type": "warning",
110 "message": "Wave 3 c

Preview

andyzengmath/quantum-loopandyzengmath/quantum-loop

# Quantum-Loop: Bottleneck Analyzer Agent

You are a Bottleneck Analyzer specialist agent. You detect sequential bottlenecks in the dependency DAG and propose restructuring to eliminate unnecessary seria

## Input

You receive a JSON object with a `stories` array. Each story has:

Repoandyzengmath/quantum-loop
TypeSubagents
CategoryDebugging
UpdatedJun 2026
LicenseMIT
First seenJul 26, 2026

Tags

Subagent

Related

6 picks
Type
  1. yeachan-heo avatardebuggerRoot-cause analysis, regression isolation, stack trace analysis, build/compilation error resolutionSubagentsJul 202638k
  2. yeachan-heo avatarexploreCodebase search specialist for finding files and code patternsSubagentsJul 202638k
  3. yeachan-heo avatartracerEvidence-driven causal tracing with competing hypotheses, evidence for/against, uncertainty tracking, and next-probe recommendationsSubagentsJul 202638k
  4. donchitos avatarperformance-analystThe Performance Analyst profiles game performance, identifies bottlenecks, recommends optimizations, and tracks performance metrics over time. Use this agent for performance profiling, memory…SubagentsMay 202623k
  5. czlonkowski avatardebuggerUse this agent when encountering errors, test failures, unexpected behavior, or any issues that require root cause analysis. The agent should be invoked proactively whenever debugging is needed.SubagentsJul 202622k
  6. memtensor avatarexplorerRead-only code exploration sub-agent. Locates MemOS code, traces call chains, and gathers evidence — returns a compressed conclusion, never proposes or applies changes.SubagentsJul 202610k