parallect-ai-deep-research
v1.0.0Deep research using Parallect.ai. Queries multiple AI research providers (Perplexity, Gemini, OpenAI, Grok, Anthropic) in parallel, then synthesizes results...
⭐ 0· 91·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
Name/description claim multi-provider deep research via Parallect.ai and the runtime instructions only require a Parallect API key and call the Parallect MCP endpoint; these requirements match the stated purpose and there are no unrelated credentials or binaries requested.
Instruction Scope
SKILL.md confines actions to the Parallect MCP API (submit research, poll status, get results, balance/usage, list providers). It instructs the agent to check balance and discuss budget before submitting (good). Two items worth noting: (1) it permits silently reusing a previously set budget preference in the session ('reuse it silently unless the topic warrants a different tier'), which could lead to spending without explicit confirmation; (2) manual install instructions reference writing files into ~/.openclaw which is normal for skills but will create files on disk when the user follows them. There are no instructions to read unrelated local files or other environment variables.
Install Mechanism
This is an instruction-only skill with no install spec and no code files to execute; lowest install risk. The README includes optional manual copy commands which write SKILL.md and reference docs into ~/.openclaw if the user chooses, but there is no automatic download/extract of external code.
Credentials
Only a single required environment variable (PARALLECT_API_KEY) is declared and used as the primary credential — this aligns with the service the skill integrates with. No unrelated secrets or config paths are requested.
Persistence & Privilege
always is false and the skill is user-invocable (normal). The skill does not request elevated or always-on privileges and does not modify other skills or system-wide settings in its instructions.
Assessment
This skill appears to do what it says: it contacts Parallect.ai and uses your PARALLECT_API_KEY to run asynchronous, paid research jobs. Before installing: (1) Confirm you trust parallect.ai and are comfortable sending research queries (possibly sensitive prompts) to a third party; check their privacy and data retention policies. (2) Ensure the PARALLECT_API_KEY has appropriate scope and is stored securely in your OpenClaw config. (3) Be aware the skill spends your credits — the SKILL.md mostly requires explicit budget confirmation, but it does allow reusing a previously set session budget silently; if you want to avoid accidental charges, clear or disable saved budget preferences or require explicit confirmation every time. (4) Manual install copies files into ~/.openclaw if you follow the README — verify those files come from a trusted source. If you want higher assurance, request the skill's source code or an official package on a verified registry before enabling it.Like a lobster shell, security has layers — review code before you run it.
latestvk976pptab4tmyvcmdjjp1e6sdx83km1m
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🔬 Clawdis
EnvPARALLECT_API_KEY
Primary envPARALLECT_API_KEY