Skill library
Publisher description: Open-source Claude Code skills for GTM engineering: Instantly, HeyReach, Blitz API, campaign analysis, TAM scoring. By OneGTM.
Catalogue scope: 9 entries at separate source paths.
Repository health
GitHub’s own figures, read from its REST API. Commit and contributor totals come from the paging header rather than an estimate.
Repository metadata checked 2026-10-06 · skill files extracted 2026-10-06 · published 2026-09-05
Extraction and automated analysis describe the files at the recorded revision. They are not an editorial review or a test of the skills in use.
- Stars
- 0
- Commits
- 1
- Last 90 days
- 1
- Contributors
- 1
- Last push
- 2026-09-30
- First commit
- 2026-09-30
commits
repo created
9 skill entries
- blitz-api
Search and enrich companies, people, and job postings with the Blitz API (blitz-api.ai) without falling into its silent-failure traps. Use whenever building lead lists, sizing a TAM, pulling hiring signals, finding employees at an account, or enriching emails through Blitz. Covers the real filter schema, pagination, full-text matching traps, and the checks that catch a query that quietly filtered nothing.
Needs a keyActs undeclared813 words - campaign-analyzer
Analyze Instantly email campaign performance by persona, signal type, and copy patterns. Use this skill whenever the user wants to review campaign metrics, compare reply rates across personas or signals, determine statistical significance of performance differences, identify winning vs losing copy patterns, get recommendations for improving campaigns, audit outbound email performance, or asks about which campaigns are working best. Also trigger when the user mentions Instantly analytics, campaign A/B testing results, outbound copy analysis, or wants a campaign performance report. Even casual requests like "how are our campaigns doing" or "which personas convert best" should use this skill.
Self-containedActs undeclared1,388 words - heyreach-api
Operate HeyReach (LinkedIn outreach) end-to-end via API and MCP. Master reference for every operation, exact variable syntax (single-brace; always use custom {FNAME}/{CNAME}), the sequence node tree, connection/message/InMail payloads + fallbacks, schedule/sender/tag/webhook shapes, status-gated edits (Update Sequence/Settings/Schedule/Accounts, now also via MCP), the required-variable preflight guard, the 100-lead cap, delete being UI-only, and workarounds (pause-to-edit, resume-to-restart, note: adding leads does NOT wake a paused campaign). Use whenever creating, editing/modifying, deleting, loading leads into, launching, or analyzing HeyReach campaigns. Pairs with `instantly-copywriter` for copy standards.
Needs a keyInstructions only5,022 words - heyreach-campaign-creator
Create and manage LinkedIn outreach campaigns in Heyreach via the Campaign API. Use this skill whenever the user wants to: push LinkedIn sequences to Heyreach, create Heyreach campaigns, build LinkedIn outreach campaigns, set up Heyreach sequences, update Heyreach campaign settings/schedule/accounts, or manage Heyreach campaigns programmatically. Also trigger when the user mentions Heyreach campaign creation, LinkedIn automation setup, or wants to push copy from copy.json to Heyreach. Even casual requests like 'push the LinkedIn copy to Heyreach' or 'create the Heyreach campaigns' should use this skill.
Needs a keyActs undeclared3,845 words - heyreach-toggle
Pause or unpause all campaigns in a Heyreach instance, including FINISHED campaigns that can't normally be paused. Use this skill whenever the user wants to pause, stop, halt, unpause, resume, reactivate, or restart their Heyreach LinkedIn outreach campaigns - even casually like "pause heyreach", "unpause heyreach", "stop our linkedin campaigns", "resume heyreach", "shut down heyreach outreach", "turn heyreach back on", "pause all outbound on heyreach", or "kill the linkedin campaigns". Also trigger when the user mentions pausing or resuming specific Heyreach campaigns by name or wants to toggle LinkedIn outreach for a client.
Needs a keyActs undeclared237 words - instantly-api
Operate Instantly.ai (cold email) end-to-end via API and MCP, create, modify/edit, delete, activate/pause, push leads, and analyze campaigns. Master reference for every operation, exact variable + spintax syntax, the required-variable preflight guard, campaign/sequence/schedule/sender/lead payloads, what's API-only vs MCP-only, rate limits, and workarounds. Use whenever creating, editing, deleting, pushing leads to, activating, or analyzing Instantly campaigns. Pairs with `instantly-copywriter` (which owns the copy itself).
Needs a keyActs undeclared3,266 words - instantly-copywriter
Create Instantly email campaigns with proper naming, 2x2 thread structure, Instantly-native spintax, humanized copy, variable mapping, and API push. Shared across all client engagements.
Needs a keyActs undeclared2,896 words - instantly-toggle
Pause or unpause all Instantly email campaigns for a client using their API key. Use this skill whenever the user wants to pause, stop, halt, unpause, resume, reactivate, or restart Instantly campaigns - even casually like "pause instantly", "unpause instantly", "toggle instantly", "stop the email campaigns", "resume instantly outreach", "kill the instantly campaigns", or "turn instantly back on". Trigger on any mention of toggling, pausing, or resuming Instantly campaigns.
Needs a keyActs undeclared161 words - scoring-analysis-and-distribution
Audit a TAM scoring model against its underlying data, simulate revised rubrics, and recommend rebalanced bands + weights + multipliers that widen the score distribution so accounts visibly stack-rank instead of piling at the same Final %. Use whenever a client hands over a Clay / Deepline / spreadsheet TAM with a working scoring model and the symptom is "everyone scores the same," "distribution is compressed," "top of the list looks wrong," or "we want a clean DQ cutoff that means something." Triggers on phrases like 'rescore this list', 'fix the scoring', 'why is everyone scoring the same', 'distribution is bad', 'compressed', 'rebuild this scoring model', 'spread out the scores', 'twin-firm test', or any CSV export + scoring rubric.
Self-containedActs undeclared4,337 words
Need help setting it up?
This page tells you what OneGTM/gtm-skills does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.
Book a call →The directory stays free. There is nothing gated behind this.