devtu-docs-quality
TOP PRIORITY skill — find and immediately fix or remove every piece of wrong, outdated, or redundant information in ToolUniverse docs. Wrong code, broken links, incorrect counts, and overlapping instructions must be fixed or removed — never left in place. Runs five phases: (D) static method scan, (C) live code execution, (A) automated validation, (B) ToolUniverse audit, (E) less-is-more simplification. Core philosophy: each concept appears exactly once; remove don't add; no emojis; single setup entry point. Use when reviewing docs, before releases, after API changes, or when asked to audit, fix, or simplify documentation.
What this skill does
# Documentation Quality Assurance
## Two Equal Priorities
Both of the following must be satisfied before an audit is done. Neither overrides the other.
**1. Technical correctness** — wrong code is worse than no code; it actively breaks users' workflows.
**2. Less is more** — redundant content is worse than no content; it creates confusion, dilutes trust, and makes maintenance harder.
> When in doubt about technical accuracy: **verify against source** (`src/tooluniverse/execute_function.py`).
> When in doubt about whether content is needed: **delete it**.
---
## Less Is More — The Core Philosophy
ToolUniverse is a serious research tool. Documentation should reflect that with restraint and precision, not volume.
### What "less is more" means in practice
**Remove, don't add.** Every edit should end with fewer words, fewer pages, fewer links. The field moves fast — outdated instructions are actively harmful. When two approaches both work, keep one.
**Each concept appears exactly once.** If setup instructions appear in three places, a user reading one doesn't know the others exist, and maintainers must update all three on every change. Pick one canonical location and cross-link everywhere else.
**No emojis.** Emojis in headings, nav items, card titles, and bullet points signal "AI-generated" and undermine trust in a serious scientific tool. Remove them unconditionally — no exceptions for "emphasis."
**Shrink, don't summarize.** A page reduced from 1000 lines to 30 pointer lines is better than a 1000-line page summarized with a TL;DR box. Do the surgery.
**Size budgets (hard limits):**
| Page type | Max lines |
|-----------|-----------|
| Per-platform setup page (`claude_desktop.rst`, `cursor.rst`, etc.) | 15 |
| Homepage grid sections | 4 cards max per grid |
| "See Also" / "Related" link lists | 4 links max |
| Tutorial pages that duplicate the Python guide | 0 — delete or make a pointer |
### Less-is-more decision tree
When reviewing any piece of content, ask:
1. **Does this content exist elsewhere on the site?** → Remove it; add a cross-link to the canonical location.
2. **Is this content outdated or hard to keep current?** → Remove it; link to the upstream source (e.g., `aiscientist.tools/setup.md`).
3. **Can a user reach this information in 2 clicks from the homepage?** → If yes and the info is already there, remove this copy.
4. **Is this an emoji, decorative header, or filler sentence?** → Remove it unconditionally.
5. **Is this a "Explore More" card pointing somewhere already in the sidebar?** → Remove it.
---
## Apple-Style Simplification Rules
Apply these rules to every file touched during an audit.
**No emojis** in headings, bullet items, card titles, toctree captions, nav bar entries, or button text.
**Single setup entry point.** The canonical installation path is:
```
Read https://aiscientist.tools/setup.md and set up ToolUniverse for me.
```
Per-platform pages must contain exactly three things: (1) official install link, (2) official MCP setup guide link, (3) the setup prompt above. Nothing else — no JSON snippets, no step-by-step instructions, no troubleshooting. Those belong in the setup skill at `aiscientist.tools/setup.md`.
**Consistent tool count.** Always "1000+ tools". Never "600+", "750+", "1200+", "10000+", or any other number.
**Clean navigation bar.** Must not contain "API", "API Keys", or "Contribution" items. Must include a link to `https://aiscientist.tools` as the first item.
**Homepage "Explore More" grid.** Maximum 4 cards. Remove any card whose destination is already reachable from the sidebar or the "Get Started" section.
**No broken `:doc:` references.** Every `:doc:`some/path`` must resolve to an `.rst` or `.md` file on disk. Broken links are never acceptable — remove or replace immediately.
---
## Five-Phase Strategy
Run phases in order — **D first** (instant), then **E** (simplification scan), then C/A/B.
| Phase | What it catches | Time |
|-------|----------------|------|
| **D** Static method scan | Wrong method names (`tu.run_batch`, `tu.call_tool`, etc.) | ~2 s |
| **E** Simplification scan | Emojis, wrong counts, broken links, size violations | ~10 s |
| **C** Live code execution | Runtime failures (wrong key, bad return type) | 3-5 min |
| **A** Automated validation | Deprecated commands, term inconsistency | 15 min |
| **B** ToolUniverse audit | Circular nav, duplicate MCP configs, tool counts | 20 min |
---
## Phase D: Static Method Scan
```bash
python3 - <<'EOF'
import re, sys
from pathlib import Path
from collections import defaultdict
DOCS = Path("docs")
EXCLUDE = {"locale", "old", "_build", "__pycache__", "tools", "archive"}
KNOWN_BAD = {
"list_tools", "run_batch", "run_async", "execute_tool", "call_tool",
"list_tools_by_category", "configure_api_keys", "get_tool", "get_exposed_name",
"list_available_methods", "register_tool_from_config", "register_tool",
}
STATIC = [
(r"\.load_tools\([^)]*(?:use_cache|cache_dir)\s*=", "load_tools() invalid kwargs"),
(r"ToolUniverse\([^)]*timeout\s*=", "ToolUniverse(timeout=) invalid"),
(r'"name":\s*"opentarget_', 'old lowercase "opentarget_*" tool name'),
(r"tu\.run_batch\(", "tu.run_batch() — use tu.run(list, max_workers=N)"),
(r'\btu\.[A-Z]\w+\s*\(', "tu.ToolName() shorthand — use tu.run({name:...})"),
]
M = re.compile(r'\b(?:tu|tooluni)\.([\w]+)\s*\(')
issues = defaultdict(list)
for f in sorted(list(DOCS.rglob("*.rst")) + list(DOCS.rglob("*.md"))):
if any(p in f.parts for p in EXCLUDE): continue
t = f.read_text(errors="replace")
code = "\n".join(
re.findall(r"\.\. code-block:: python\n((?:[ \t]+[^\n]*\n|[ \t]*\n)*)", t, re.MULTILINE) +
re.findall(r"```python\n(.*?)```", t, re.DOTALL))
if not code.strip(): continue
rel = str(f.relative_to(DOCS))
for m in M.finditer(code):
if not m.group(1).startswith("_") and m.group(1) in KNOWN_BAD:
issues[rel].append(f"tu.{m.group(1)}()")
for pat, label in STATIC:
if re.search(pat, code): issues[rel].append(label)
if issues:
[print(f" {f}: {i}") for f in sorted(issues) for i in sorted(set(issues[f]))]
sys.exit(1)
else:
print("Phase D clean")
EOF
```
**Fix-or-remove rule — no exceptions:**
- Correct replacement exists → **fix immediately**
- Feature is automatic/internal → **remove the call**, add prose comment if needed
- Feature doesn't exist → **delete the code block or section entirely**
**Most common fixes:**
```python
# wrong → correct
tu.run_batch(list) → tu.run(list, max_workers=4)
tu.run_async(query) → await tu.run(query)
tu.call_tool('X', {...}) → tu.run({"name": "X", "arguments": {...}})
tu.execute_tool('X', {...}) → tu.run({"name": "X", "arguments": {...}})
tu.list_tools() → tu.list_built_in_tools(mode='list_name')
tu.get_tool('X') → tu.get_tool_by_name('X')
tu.register_tool(instance) → tu.register_custom_tool(tool_instance=instance)
tu.register_tool_from_config(c) → tu.register_custom_tool(tool_config=c)
tu.configure_api_keys({}) → REMOVE — use env vars
tu.get_exposed_name(name) → REMOVE — shortening is automatic
ToolUniverse(timeout=30) → ToolUniverse() # no timeout kwarg
load_tools(use_cache=True) → load_tools() # no use_cache kwarg
tu.ToolName(key=val) → tu.run({"name": "ToolName", "arguments": {"key": val}})
opentarget_get_* → OpenTargets_get_* (capital O and T)
```
**Special case:** Change `.. code-block:: python` to `.. code-block:: text` when showing intentionally-wrong code as an error example.
---
## Phase E: Simplification Scan
```bash
python3 - <<'EOF'
import re, sys
from pathlib import Path
DOCS = Path("docs")
EXCLUDE = {"_build", "__pycache__", "locale"}
issues = []
EMOJI_RE = re.compile(
r'[\U0001F300-\U0001F9FF\U00002600-\U000027BF\U0001FA00-\U0001FA9F'
r'\U0001F004\U0001F0CF\U00002702-\U000027B0]'
)
def in_code_blockRelated in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.