RuleStack

Configs

Stacks

Compare

Diff

RuleStack

Configs

Stacks

Compare

Diff

Read API

RuleStack

Configs

Stacks

Compare

Diff

Read API

Configs/Cursor rules/danielvm-git/bigpowers

Cursor rule

.cursor/rules/inspect-quality.mdc

Interactive QA session where user reports bugs or issues conversationally, and the agent logs them to specs/bugs/registry.yaml with a structured audit schema. Explores the codebase in the background for context and domain language. Use when user wants to report bugs, do QA, or mentions "QA session".

Cursor rules

Quality

58/100

Scores the file, not the repository.

Length

651 words

11 headings · 1 code blocks

Repository

119

— · pushed 1 days ago

Last changed

3 days ago

First indexed 3 days ago.
danielvm-git/bigpowers/.cursor/rules/inspect-quality.mdcRawGitHub
1---
2description: "Interactive QA session where user reports bugs or issues conversationally, and the agent logs them to specs/bugs/registry.yaml with a structured audit schema. Explores the codebase in the background for context and domain language. Use when user wants to report bugs, do QA, or mentions \"QA session\"."
3alwaysApply: false
4---
5 
6# Inspect Quality
7> **HARD GATE** — **HARD GATE** — Quality metrics (coverage, lint, cyclomatic complexity, security scans) must be monitored. If a metric degrades, surface it as a blocker. Do NOT accept regressions.
8 
9 
10Run an interactive QA session. The user describes problems they're encountering. You clarify, explore the codebase for context, and log each issue to `specs/bugs/registry.yaml` with a structured, durable format.
11 
12## For each issue the user raises
13 
14### 1. Listen and lightly clarify
15 
16Let the user describe the problem in their own words. Ask **at most 2–3 short clarifying questions** focused on:
17 
18- What they expected vs what actually happened
19- Steps to reproduce (if not obvious)
20- Whether it's consistent or intermittent
21 
22Do NOT over-interview. If the description is clear enough to log, move on.
23 
24### 2. Explore the codebase in the background
25 
26Kick off an Agent (subagent_type=Explore) to understand the relevant area. The goal is NOT to find a fix — it's to:
27 
28- Learn the domain language used in that area (check `specs/UBIQUITOUS_LANGUAGE_LATEST.md` if present)
29- Understand what the feature is supposed to do
30- Identify the user-facing behavior boundary
31 
32### 3. Assess scope: single issue or breakdown?
33 
34Break down when:
35 
36- The fix spans multiple independent areas
37- There are clearly separable concerns that could be worked on in parallel
38- The user describes something with multiple distinct failure modes
39 
40Keep as a single issue when:
41 
42- It's one behavior that's wrong in one place
43- The symptoms are all caused by the same root behavior
44 
45### 4. Log to specs/bugs/registry.yaml
46 
47Append the issue to `specs/bugs/registry.yaml`. Create the `specs/bugs/` directory if it doesn't exist.
48 
49#### registry.yaml format
50 
51The file maintains a Markdown table with the following columns (derived from structured audit practice):
52 
53| Field | Description |
54|-------|-------------|
55| `bug_id` | `BUG-YYYY-MM-DDTHHMMSS` |
56| `date` | `YYYY-MM-DD` |
57| `severity` | `critical` / `high` / `medium` / `low` |
58| `priority` | `p0` / `p1` / `p2` / `p3` |
59| `scope` | kebab-case area (e.g. `auth`, `checkout`) |
60| `what_happened` | actual behavior (user-facing terms) |
61| `what_expected` | expected behavior |
62| `steps_to_reproduce` | numbered steps |
63| `root_cause` | one-line hypothesis |
64| `files_changed` | filled in after fix |
65| `approach` | filled in after fix |
66| `risk_level` | `low` / `medium` / `high` |
67| `new_tests` | count (filled in after fix) |
68| `type_check` | `pass` / `fail` (filled in after fix) |
69| `lint` | `pass` / `fail` (filled in after fix) |
70| `commit_type` | `fix` / `fix!` / `feat` (filled in after fix) |
71| `release_type` | `patch` / `minor` / `major` (filled in after fix) |
72| `commit_message` | Conventional Commits message (filled in after fix) |
73| `follow_ups` | semicolon-separated follow-up items |
74| `file` | path to detailed `specs/bugs/BUG-*.md` (filled in by investigate-bug) |
75| `status` | `open` / `in-progress` / `fixed` / `wont-fix` |
76 
77When a bug is fixed (via `validate-fix`), update the relevant row with the resolution fields.
78 
79#### Issue body (for context below the table)
80 
81For each bug, also append a detail section:
82 
83```markdown
84### BUG-YYYY-MM-DDTHHMMSS: [short title]
85 
86**What happened:** [actual behavior, plain language]
87**What I expected:** [expected behavior]
88**Steps to reproduce:**
891. [Step 1]
902. [Step 2]
91 
92**Additional context:** [domain-language observations, no file paths]
93```
94 
95#### Rules for all entries
96 
97- **bug_id** uses full timestamp: `BUG-YYYY-MM-DDTHHMMSS` — matches the individual bug file name in `specs/bugs/`
98- **No file paths or line numbers** — these go stale
99- **Use the project's domain language** (check `specs/UBIQUITOUS_LANGUAGE_LATEST.md` if it exists)
100- **Describe behaviors, not code** — "the sync service fails to apply the patch" not "applyPatch() throws"
101- **Reproduction steps are mandatory** — if you can't determine them, ask the user
102 
103### 5. Continue the session
104 
105After logging, ask: "Next issue, or are we done?" Keep going until the user says done. Each issue is independent — don't batch them.
106 

Sections

  • Inspect Quality
  • For each issue the user raises
  • 1. Listen and lightly clarify
  • 2. Explore the codebase in the background
  • 3. Assess scope: single issue or breakdown?
  • 4. Log to specs/bugs/registry.yaml
  • BUG-YYYY-MM-DDTHHMMSS: [short title]
  • 5. Continue the session

What it covers

architecturegit-pr

Stack — with the evidence

shell

(0.80)

node

(0.70)

react

(0.70)

astro

(0.70)

express

(0.70)

vitest

(0.70)

typescript

(0.60)

javascript

(0.60)

python

(0.60)

github-actions

(0.60)

Format

Cursor rules

The most expressive format here. Many small .mdc files, each with frontmatter declaring when it should load, so a rule about migrations only enters context when a migration is open. Costs the most to maintain and only one editor reads it.

What the corpus says about it

Repository

Owner
danielvm-git
Language
—
License
—
Archived
no

All configs in this repo

Also in danielvm-git/bigpowers

Diff this repo’s formats

One repository carrying more than one format is the comparison this product exists for: does anyone actually write different content in each file, or is one a copy of the other?

The other instruction files in this repository
RepositoryFormatStackCoversScoreChanged
danielvm-git/bigpowers.cursor/rules/align-grid.mdc · 119Cursor rulesnodeshell+8lint-formatdo-notagent-behaviour65/1003 days ago
danielvm-git/bigpowers.cursor/rules/assess-impact.mdc · 119Cursor rulesshellnode+8testtesting-strategydeployment66/1003 days ago
danielvm-git/bigpowers.cursor/rules/audit-code.mdc · 119Cursor rulesshellnode+8setuptestlint-formatstyle+466/1003 days ago
danielvm-git/bigpowers.cursor/rules/audit-plan.mdc · 119Cursor rulesnodeshell+8buildteststylegit74/1003 days ago
danielvm-git/bigpowers.cursor/rules/build-epic.mdc · 119Cursor rulesshellnode+8buildgit58/1003 days ago
danielvm-git/bigpowers.cursor/rules/change-request.mdc · 119Cursor rulesshellnode+8no sections48/1003 days ago
danielvm-git/bigpowers.cursor/rules/commit-message.mdc · 119Cursor rulesshellnode+8lint-formatstyletypesgit+382/1003 days ago
danielvm-git/bigpowers.cursor/rules/compose-workflow.mdc · 119Cursor rulesshellnode+8styledo-notagent-behaviour65/1003 days ago
danielvm-git/bigpowers.cursor/rules/context7-mcp.mdc · 119Cursor rulesshellnode+8style54/1003 days ago
danielvm-git/bigpowers.cursor/rules/deepen-architecture.mdc · 119Cursor rulesshellnode+8testtesting-strategydo-not57/1003 days ago
danielvm-git/bigpowers.cursor/rules/define-language.mdc · 119Cursor rulesshellnode+8lint-formatdo-not65/1003 days ago
danielvm-git/bigpowers.cursor/rules/delegate-task.mdc · 119Cursor rulesshellnode+8git62/1003 days ago
danielvm-git/bigpowers.cursor/rules/deploy.mdc · 119Cursor rulesnodeshell+8setupbuildtestdeployment77/1003 days ago
danielvm-git/bigpowers.cursor/rules/develop-tdd.mdc · 119Cursor rulesshellnode+8teststylearchtesting-strategy+585/1003 days ago
danielvm-git/bigpowers.cursor/rules/diagnose-root.mdc · 119Cursor rulesshellnode+8no sections39/1003 days ago
danielvm-git/bigpowers.cursor/rules/dispatch-agents.mdc · 119Cursor rulesshellnode+8git54/1003 days ago
danielvm-git/bigpowers.cursor/rules/edit-document.mdc · 119Cursor rulesshellnode+8no sections39/1003 days ago
danielvm-git/bigpowers.cursor/rules/elaborate-spec.mdc · 119Cursor rulesshellnode+8test58/1003 days ago
danielvm-git/bigpowers.cursor/rules/enforce-first.mdc · 119Cursor rulesshellnode+8no sections50/1003 days ago
danielvm-git/bigpowers.cursor/rules/evolve-skill.mdc · 119Cursor rulesshellnode+8no sections50/1003 days ago
Diff against .cursor/rules/align-grid.mdc Diff against .cursor/rules/assess-impact.mdc Diff against .cursor/rules/audit-code.mdc Diff against .cursor/rules/audit-plan.mdc Diff against .cursor/rules/build-epic.mdc Diff against .cursor/rules/change-request.mdc Diff against .cursor/rules/commit-message.mdc Diff against .cursor/rules/compose-workflow.mdc Diff against .cursor/rules/context7-mcp.mdc Diff against .cursor/rules/deepen-architecture.mdc Diff against .cursor/rules/define-language.mdc Diff against .cursor/rules/delegate-task.mdc Diff against .cursor/rules/deploy.mdc Diff against .cursor/rules/develop-tdd.mdc Diff against .cursor/rules/diagnose-root.mdc Diff against .cursor/rules/dispatch-agents.mdc Diff against .cursor/rules/edit-document.mdc Diff against .cursor/rules/elaborate-spec.mdc Diff against .cursor/rules/enforce-first.mdc Diff against .cursor/rules/evolve-skill.mdc

Similar configs

Same format, overlapping stack, ranked by quality.

Same format, overlapping stack, ranked by quality
RepositoryFormatStackCoversScoreChanged
TechSquidTV/Hermes.cursor/rules/10-hermes-api.mdc · 45Cursor rulestypescriptpytest+15testlint-formatstylearch+5100/1003 days ago
hiromaily/go-crypto-wallet.cursor/rules/typescript.mdc · 126Cursor rulesgobun+5setupbuildtestlint-format+6100/1003 days ago
markstev/mark-starter.cursor/rules/frontend.mdc · 0Cursor rulestypescriptturborepo+14setuptestlint-formatstyle+699/1003 days ago
dodgecfr/combatfilms-webapp.cursor/rules/frontend.mdc · 0Cursor rulestypescriptturborepo+15setuptestlint-formatstyle+799/1003 days ago
deifos/clipmira-subtitles.cursor/rules/frontend.mdc · 1Cursor rulestypescriptnextjs+5setuptestlint-formatstyle+799/1003 days ago
Allymahmoud/case-intake-platform.cursor/rules/frontend.mdc · 0Cursor rulestypescriptturborepo+13setuptestlint-formatstyle+799/1003 days ago
langflow-ai/langflow.cursor/rules/docs_development.mdc · 153kCursor rulespythonnode+16setupbuildtestlint-format+797/1003 days ago
TechSquidTV/Hermes.cursor/rules/20-hermes-api-tests.mdc · 45Cursor rulestypescriptpytest+15teststyletesting-strategysecurity+397/1003 days ago
RuleStack

Built by

Kynth Studio

Directory

Configs
Stacks
Compare formats
Diff two configs
Best AGENTS.md examples

Formats

AGENTS.md
CLAUDE.md
Cursor rules
Copilot instructions

Reference

Read API
Corpus health
Privacy Policy
Terms

RuleStack

RuleStack

Built by

Kynth Studio

Directory

Configs
Stacks
Compare formats
Diff two configs
Best AGENTS.md examples

Formats

AGENTS.md
CLAUDE.md
Cursor rules
Copilot instructions

Reference

Read API
Corpus health
Privacy Policy
Terms

RuleStack

RuleStack

Built by

Kynth Studio

Directory

Configs
Stacks
Compare formats
Diff two configs
Best AGENTS.md examples

Formats

AGENTS.md
CLAUDE.md
Cursor rules
Copilot instructions

Reference

Read API
Corpus health
Privacy Policy
Terms

RuleStack