AMindToThink/parse-json
skills/parse-json/SKILL.md
Inspect and extract data from unknown JSON files without fumbling
data-ai
Updated Apr 25, 2026
$ install --global
skillsauthnpx skillsauth add AMindToThink/claude-code-settings parse-jsonInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 25, 2026, 7:08 PM127.3s1 file scanned
SKILL.md
- name:
- parse-json
- description:
- Inspect and extract data from unknown JSON files without fumbling
- user_invocable:
- true
Parse JSON Skill
When the user asks you to parse, inspect, or extract data from a JSON file (or when you encounter an unknown JSON file during work), follow this two-phase approach. Never guess the structure — always inspect first.
Phase 1: Structure Discovery (single call)
Run a single Python snippet that reveals the full structure:
python3 -c "
import json, sys
with open('FILE_PATH') as f:
data = json.load(f)
def describe(obj, path='root', depth=0, max_depth=3):
indent = ' ' * depth
if isinstance(obj, dict):
print(f'{indent}{path}: dict with {len(obj)} keys: {list(obj.keys())[:15]}')
if depth < max_depth:
for k in list(obj.keys())[:5]:
describe(obj[k], f'{path}[\"{k}\"]', depth+1, max_depth)
elif isinstance(obj, list):
print(f'{indent}{path}: list of {len(obj)} items')
if len(obj) > 0 and depth < max_depth:
describe(obj[0], f'{path}[0]', depth+1, max_depth)
else:
val = repr(obj)
if len(val) > 80: val = val[:80] + '...'
print(f'{indent}{path}: {type(obj).__name__} = {val}')
describe(data)
"
Phase 2: Targeted Extraction
Only after structure is known, write extraction code using the actual keys and nesting. Use statistics.mean/stdev for aggregation. Print results in a clean tabular format.
Rules
- Never assume keys exist — use the discovered structure from Phase 1
- One inspection call, then one extraction call — no trial-and-error loops
- For large files (>256KB), use the Python approach rather than the Read tool
- Print scalar summaries, not raw arrays — the user wants insight, not data dumps
- If the file has nested groups (e.g., scenarios with per-prompt results), aggregate with mean +/- std across the group
Related Skills
AMindToThink/accessible-website-check
development
VerifiedTrustedCommunity
Use when the user asks to check, audit, or improve a website or web project for accessibility (a11y), WCAG compliance, screen reader support, keyboard navigation, color contrast, or alt text. Triggers a plan-mode investigation against the TeachAccess design and code checklists, then implements approved fixes.
3SKILL.mdUpdated May 13, 2026
AMindToThink/skills/make-anonymous-branch
development
VerifiedTrustedCommunity
--- name: make-anonymous-branch description: Use when preparing a research repo for double-blind submission via anonymous.4open.science (ICML/NeurIPS/ICLR/workshop). Builds a single `anon-submission` branch with code+data+paper, scrubs identity leaks (author names, home paths, emails, wandb metadata, PDF author fields), patches LaTeX for pdf.js compatibility, and leaves `main` untouched. Triggers: "make an anonymous branch", "anonymize my repo for X submission", "set up anonymous.4open.science",
3SKILL.mdUpdated May 12, 2026
AMindToThink/implement-math
development
VerifiedTrustedCommunity
Translate math (formulas, estimators, algorithms) into code so the implementation faithfully matches what the source actually specifies. Use when writing code from a formula, reviewing an LLM-generated implementation of a formula, debugging a numerical mismatch with a paper, designing a new metric/estimator, or refactoring an existing math-heavy computation. Especially load-bearing whenever aggregation operators (sums, means, expectations, products, geometric means) appear over indices that can be reordered, or whenever the same English label can refer to multiple non-equivalent estimators (e.g. ratio-of-means vs mean-of-ratios, micro-average vs macro-average, sample-weighted vs unweighted). Prevents the failure mode where a code path silently implements the wrong estimator under the same name as the intended one.
3SKILL.mdUpdated May 12, 2026
AMindToThink/finding-old-chats
development
VerifiedTrustedCommunity
Use when the user asks to review, find, summarize, or check Claude Code chat transcripts from a past date or time range ("review my chats from May 1st", "what was I working on yesterday", "any unfinished sessions this week"). Reads transcripts under `~/.claude/projects/`, handles local-time vs UTC correctly so late-evening sessions don't get dropped, and flags chats whose last assistant turn looks like an unanswered question.
3SKILL.mdUpdated May 12, 2026