Skip to content

discolike/discolike-skills / skills/score-account-list

score-account-list

Verified

Use when the user asks to "score these 3,000 accounts against our ICP", "which of our customers run HubSpot", or "run research on this list". Follow the discolike skill's access and spend rules.

Rank or filter a list the user already has

Follow the discolike skill's How to work rules first.

"Score these 3,000 accounts against our ICP", "which of our customers run HubSpot", "run research on this list".

  1. Load the list. A saved domain list serves as inclusion scope as well as exclusion; the upload path is the same. MCP save-exclusion-list; CLI discolike queries create-exclusion-list --name "crm-accounts" --domains-file crm.csv; SDK client.queries.create_exclusion_list(CreateExclusionListRequest(query_name="crm-accounts", domains=[...])). Minimum 20 domains. Names first? Load the match-company-domains skill.
  2. Rank it. Discover with inclusion_query_id set to that list plus an icp_prompt or seed domains; the response is the user's own companies ordered by similarity, with firmographics. Available from Starter. CLI --inclusion-query-id <id>; SDK DiscoverParams(inclusion_query_id=[...], icp_prompt=...).
  3. Bucket it. Same call with tech_stack instead of a prompt returns only the companies on that vendor. Repeat per vendor to split the list.
  4. Check and staff it. Use the find-validated-contacts skill to verify fit and find people with a contacts run on the list (run.companies set to a domain list, up to 10,000 domains per run). For questions no filter answers, see Research for the rest in the target-by-tech-and-signals skill.
  5. Explain the gaps. Domains that return no profile are not lost: append with dataset domain_status says why (non-business, parked, dead, redirect, no certificate).
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall