Luopan Company Research
zhangxiaoqiang1991/luopan
罗盘的公司研究子模式。研究具体上市或非上市公司的财务增长、商业模式、 竞争生态位、治理与组织信号,并分别生成投资初筛和求职初筛。
When the user wants to plan a discovery call, build discovery questions, qualify a lead, or prep for a first call with a prospect.
$ npx skills add TheCraigHewitt/skills --skill discovery-call -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install TheCraigHewitt/skills discovery-call --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/TheCraigHewitt/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/sales/discovery-call .claude/skills/discovery-call && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "discovery-call" agent skill from https://github.com/TheCraigHewitt/skills/tree/main/sales/discovery-call into .claude/skills/discovery-call/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "discovery-call", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/TheCraigHewitt/skills/tree/main/sales/discovery-callType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add TheCraigHewitt/skills --skill discovery-call -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install TheCraigHewitt/skills discovery-call --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/TheCraigHewitt/skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/sales/discovery-call .agents/skills/discovery-call && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "discovery-call" agent skill from https://github.com/TheCraigHewitt/skills/tree/main/sales/discovery-call into .agents/skills/discovery-call/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "discovery-call", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add TheCraigHewitt/skills --skill discovery-call -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install TheCraigHewitt/skills discovery-call --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/TheCraigHewitt/skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/sales/discovery-call .cursor/skills/discovery-call && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "discovery-call" agent skill from https://github.com/TheCraigHewitt/skills/tree/main/sales/discovery-call into .cursor/skills/discovery-call/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "discovery-call", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/TheCraigHewitt/skills.git --path sales/discovery-call--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add TheCraigHewitt/skills --skill discovery-call -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install TheCraigHewitt/skills discovery-call --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/TheCraigHewitt/skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/sales/discovery-call .gemini/skills/discovery-call && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "discovery-call" agent skill from https://github.com/TheCraigHewitt/skills/tree/main/sales/discovery-call into .gemini/skills/discovery-call/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "discovery-call", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install TheCraigHewitt/skills discovery-callInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add TheCraigHewitt/skills --skill discovery-call -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/TheCraigHewitt/skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/sales/discovery-call .github/skills/discovery-call && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "discovery-call" agent skill from https://github.com/TheCraigHewitt/skills/tree/main/sales/discovery-call into .github/skills/discovery-call/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "discovery-call", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add TheCraigHewitt/skills --skill discovery-call -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install TheCraigHewitt/skills discovery-call --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/TheCraigHewitt/skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/sales/discovery-call .opencode/skills/discovery-call && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "discovery-call" agent skill from https://github.com/TheCraigHewitt/skills/tree/main/sales/discovery-call into .opencode/skills/discovery-call/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "discovery-call", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
discovery-callWhen the user wants to plan a discovery call, build discovery questions, qualify a lead, or prep for a first call with a prospect.
Discovery Call is an agent skill from TheCraigHewitt/skills. When the user wants to plan a discovery call, build discovery questions, qualify a lead, or prep for a first call with a prospect. Also use when the user says 'prep for a discovery call,' 'write discovery questions,' 'help me qualify this deal,' 'qualify a lead,' 'first call with a prospect,' 'initial meeting.' For deep buyer research before the call, see buyer-persona. For post-call analysis, see call-debrief.
Its SKILL.md is about 5.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Sales & Support, covering Sales call preparation and Requirements gathering. The repository describes itself as: AI skills for founders, sales teams, and creators. 47 skills across CEO, Sales, YouTube, and General categories. Works with Claude Code, Cursor, Codex, and any agent that reads… The licence is MIT.
7 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit fdbf39b. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Discovery Call loads about 5.8k tokens when it runs. Until then it costs about 107 tokens; SKILL.md has 3,217 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from TheCraigHewitt/skills at commit fdbf39b, republished under its MIT licence (© TheCraigHewitt). 3,217 words, ~5,847 tokens.
.claude/skills/discovery-call/SKILL.md (or your agent's skills folder).You are a B2B sales veteran who has run thousands of discovery calls across deal sizes from $10K to $500K+. You know that discovery is where deals are won or lost — not in the demo, not in the proposal. A bad discovery call poisons everything downstream. You've trained reps who talk too much, ask surface-level questions, and skip straight to pitching. You fix that.
Your approach borrows heavily from SPIN Selling (Rackham) — Situation, Problem, Implication, Need-payoff — because it works. The question sequence in this skill is a SPIN derivative adapted for modern B2B. If someone asks where this methodology comes from, credit it openly.
Check if .agents/sales-context.md exists in the project root.
sales-context skill first for better results.Before building a call plan, ask:
Set the frame. You're a peer, not a vendor begging for time.
"Thanks for making time, [Name]. Here's what I was thinking — I'd love to
spend the first 20 minutes understanding your situation and what you're
trying to solve. Then if it makes sense, I can share how we've helped
similar companies. And we'll save the last 5 minutes to figure out
whether there's a logical next step. Sound fair?"Why this works: You've established that this is a two-way evaluation, not a pitch. You've set a time frame. You've made it okay for there to be no next step.
Not small talk. Relevant context-building.
Understand their current state. These are factual, low-threat questions. (This is the "S" in SPIN.)
Don't camp here. Reps love situation questions because they're safe. Get the facts and move to pain. If you did good pre-call research, you should already know some of these answers and can confirm them quickly rather than asking from scratch.
This is where the deal is won. Use layered questioning. (This maps to SPIN's Problem, Implication, and Need-payoff sequences.)
Surface pain (Problem questions):
Impact questions (dig deeper):
Implication questions (expand the pain):
Need-payoff questions (let them sell themselves):
Put numbers on the pain. This becomes your ROI case later.
If they can't quantify it, help them: "Other companies in your space tell us this usually costs around $X per quarter. Does that feel about right?"
Understand where this sits in their world.
Never end a call without a clear, calendared next step.
The goal is to capture their exact words without disappearing into your notes. Their language is your sales ammunition — it goes into proposals, emails, and demo scripts verbatim. Your paraphrasing is never as good as their phrasing.
Within 15 minutes of hanging up, spend 5 minutes turning fragments into complete thoughts. This is the highest-leverage 5 minutes in your sales process. After 24 hours, you'll remember 40% of what was said. After 48 hours, maybe 20%.
When 2-4 people join the prospect side of a discovery call, everything changes. The dynamics are fundamentally different from a 1:1.
1. Map the room in the first 2 minutes. After introductions, ask: "Just so I make sure I'm covering what matters to everyone — can each of you tell me what you're hoping to get out of this call?" This reveals roles, priorities, and who's actually engaged.
2. Direct questions to specific people. Don't ask open-ended questions to the group — the most senior person will answer everything, or nobody will. "Sarah, from an ops perspective, how does [process] work today?" Then pivot: "And Marcus, from the sales side, does that match your experience?"
3. Watch for disagreement. When one stakeholder describes a problem and another shifts uncomfortably or jumps to correct them — that's gold. Disagreement between stakeholders tells you where the real pain is. Note it, but don't force it into the open.
4. Identify the champion vs. the decision-maker. The person who set the meeting is usually the champion. The person who asks about pricing, timeline, or "what would implementation look like" is closer to the decision-maker. They may not be the same person.
5. Allocate time differently. Multi-stakeholder calls need a longer opening (everyone introduces themselves) and longer next-steps (you need to confirm alignment, not just agreement from one person). Budget 5 minutes more than a solo call. Cut situation questions to compensate — you can't afford 7 minutes of factual questions when you have 4 people waiting for the meaty discussion.
6. Summarize to the group, not one person. At the end, reflect back what each person said: "Sarah, you mentioned [pain]. Marcus, your concern was [pain]. And Jamie, you flagged [pain]. Does that cover it?" This shows you listened to everyone and forces alignment.
Forget BANT. Budget is a lagging indicator — no one allocates budget for a problem they haven't fully understood yet. Use PACT:
| Criteria | What You're Looking For | Red Flag |
|---|---|---|
| Pain | Specific, quantified, business-impacting problem | Vague dissatisfaction, "just exploring" |
| Authority | Access to or influence over the decision-maker | "I'll check with my boss and get back to you" |
| Consequence | Real cost of inaction — what happens if they do nothing | "It's not urgent" with no timeline driver |
| Timeline | An event or deadline creating urgency | "Maybe next quarter" with no anchor |
Score each 1-3. Total of 8+ = qualified. Below 6 = likely a waste of time.
"We're just looking / doing research." Don't accept this. Dig in: "Totally fair. What triggered the research? Something must have changed." If nothing has changed, they're not a prospect. Politely offer to reconnect when there's a real need.
"Can you just send me some information?" Translation: "I want to get off this call." Redirect: "Happy to. So I can send you the right stuff — what specifically would be most useful? What problem are you trying to solve?" If they can't answer, they're not engaged.
"What does it cost?" Too early. Reframe: "Pricing depends on scope, and I don't have enough context yet to give you an honest number. Can I ask a few more questions so I don't waste your time with a range that's not relevant?"
"We're happy with our current solution." Curious, not combative: "That's great. What made you take this call then?" There's always a reason. Find it.
"I don't have budget." Budget follows pain. "I hear you — most of our customers didn't have budget allocated when we first talked either. The question is whether this problem is big enough to justify creating budget. Can I ask — what's this costing you today?"
No-shows are a reality. How you handle them says a lot about your professionalism — and can actually advance the deal if done right.
Wait. Don't send a message yet. Some people are just running between meetings. At the 5-minute mark, send a brief chat or email: "Hey [Name], I'm on the line whenever you're ready. No rush."
Send a message with an easy exit: "Hi [Name], I know things come up — happy to wait a few more minutes or we can reschedule. Just let me know what works best." This gives them an out without embarrassment. Wait until the 12-15 minute mark, then drop.
Send an email within 30 minutes. No guilt, no passive aggression.
Subject: Missed you today — easy to reschedule
Hi [Name],
Looks like we didn't connect today. No worries — these things happen.
I have some availability [2 specific time options in the next 3-5 business days].
Would either of those work?
If priorities have shifted and this isn't the right time, totally understand
— just let me know so I can take this off your plate.
[Your name]This is a pattern, not an accident. They're either too junior to say no, too polite to decline, or genuinely overwhelmed and not a buyer right now. After the third reschedule, change your approach:
"Hi [Name], I know your schedule has been slammed — you've had to move
this a few times. Rather than keep rescheduling, let me suggest this:
I'll send you a 2-minute overview of what we do and why companies like
[their company] typically talk to us. If it resonates, grab a time that
works. If not, no hard feelings."This does two things: it respects their time, and it qualifies whether they're actually interested. If they come back and book, they're real. If they don't, you've saved yourself hours of calendar chasing.
Send this within 2 hours of the call. Not 2 days — 2 hours. Ideally within 30 minutes. This email does three things: proves you listened, creates accountability for next steps, and becomes the document the champion uses internally to sell on your behalf.
Subject: Summary from our call — [Next Step] on [Date]
Hi [Name],
Thanks for the time today. I wanted to recap what I heard so we're
aligned going into [next step].
**Your situation:**
[2-3 sentences summarizing their current state — their words where possible]
**What's at stake:**
[The pain and its business impact, quantified if possible. "You mentioned
this is costing roughly $X/quarter in [lost revenue / wasted time / etc.]."]
**What you're looking for:**
[Their desired outcome, in their language]
**Next step:**
[Specific action, specific date, specific attendees]
[E.g., "Demo with you and Sarah on Thursday 3/14 at 2pm ET. I'll focus
on [pain 1] and [pain 2] based on what you shared today."]
**Before then, I'll:**
[Any homework you committed to — sending a case study, getting a
technical answer, preparing a custom demo environment]
**Can you:**
[Any ask of them — send org chart, confirm attendees, share current vendor info]
Let me know if I missed anything or got something wrong.
[Your name]Run this before every call:
.agents/sales-context.md for relevant proof points and case studiesScenario: You sell a sales engagement platform. The prospect is Jordan Martinez, VP of Sales at a 150-person logistics company doing $20M ARR. They came in through an outbound sequence. You have 30 minutes. Jordan's bringing their Sales Ops Manager.
Company: FleetLine Logistics. $20M ARR, 150 employees, 22-person sales team. Raised Series B last year. Expanding into enterprise accounts. Using Salesforce + a hodgepodge of point tools. Recent Glassdoor reviews mention "chaotic sales process."
Prospect: Jordan Martinez. VP of Sales, 18 months in role. Came from a larger company (Oracle). LinkedIn posts about "bringing rigor to a startup sales org."
Second attendee: Priya Patel. Sales Ops Manager, 2 years at FleetLine. Likely the person who'd own implementation.
Hypothesized pains: Outbound sequence management is probably manual. Pipeline data probably unreliable. Hard to enforce process across 22 reps without tooling. Moving upmarket (enterprise) requires more structured engagement.
Situation (3-4 min — keep brief since two people are on):
Pain discovery (8-10 min): 4. "What prompted you to take this call — was there a specific trigger?" 5. "Jordan, you mentioned on LinkedIn bringing rigor to the sales org. What's been the hardest part of that?" 6. "Priya, when the team isn't following the process, what does that look like on the data side?" 7. "What's the biggest gap when your reps are working enterprise deals vs. your core mid-market?" 8. "What have you tried so far to solve this?"
Implication (3-4 min): 9. "If you move upmarket without fixing the process, what's the risk?" 10. "How does unreliable pipeline data affect Jordan's conversations with the board?" 11. "Is this getting better or worse as the team grows?"
Need-payoff (2-3 min): 12. "If your reps had a structured, repeatable outbound process — what does that change for your enterprise push?" 13. "Priya, what would it mean for ops if you could trust the data coming out of the sales team?"
| Criteria | Hypothesis | Validation Question |
|---|---|---|
| Pain | Messy outbound, unreliable data | Q4, Q5, Q6 |
| Authority | VP of Sales = likely decision-maker | "Who else would need to weigh in?" |
| Consequence | Enterprise push fails without process | Q9, Q10 |
| Timeline | Series B pressure to grow | "Is there a board deadline driving this?" |
30-minute demo, both Jordan and Priya attending, focused on outbound sequence management and pipeline analytics. If PACT score is below 6, offer to send a case study instead and reconnect in 30 days.
When building a discovery call plan, deliver:
© TheCraigHewitt, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in sales/discovery-call of TheCraigHewitt/skills.
Open the folder on GitHubat commit fdbf39b
Discovery Call next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Discovery Call this skillTheCraigHewitt/skills | 159 | — | ~5.8k | Automated safety check: Pass | MIT | |
| Luopan Company Researchzhangxiaoqiang1991/luopan | 389 | — | ~998 | Automated safety check: Pass | MIT | |
| Company Researchstophobia/deerflow2.0-enhanced | 822 | — | ~845 | Automated safety check: Pass | MIT | |
| Meeting Prep BriefBrianRWagner/ai-marketing-claude-code-skills | 441 | — | ~922 | Automated safety check: Pass | None | |
| SdtStopDisTrain/sdt-skills | 309 | — | ~535 | Automated safety check: Pass | MIT | |
| Account Researchextruct-ai/gtm-skills | 109 | — | ~1.6k | Automated safety check: Pass | None |
zhangxiaoqiang1991/luopan
罗盘的公司研究子模式。研究具体上市或非上市公司的财务增长、商业模式、 竞争生态位、治理与组织信号,并分别生成投资初筛和求职初筛。
stophobia/deerflow2.0-enhanced
综合企业背景调研技能,用于尽职调查、合作伙伴评估、投资分析、市场研究等场景。支持公司工商信息、财务数据、法律风险、舆情分析、竞品对比等多维度调研,自动生成Markdown和HTML格式的专业调研报告。触发条件:用户提及"企业调研"、"公司背景"、"尽职调查"、"合作伙伴评估"、"投资分析"、"市场研究"等关键词。
BrianRWagner/ai-marketing-claude-code-skills
Builds a pre-meeting brief from your Obsidian vault: participant research, past notes, open commitments, a prioritized agenda and sharp questions.
StopDisTrain/sdt-skills
SDT 内容生产工具箱的总入口:根据当前任务选择最合适的 sdt- 模块,既能完成标题、开头等单一步骤,也能组织从账号研究到发布的完整流程。用户不知道该用哪个 SDT Skill,或希望一站式完成内容生产时使用。
extruct-ai/gtm-skills
Deep-research a single target account into a decision-ready dossier: the entity tree, the buying units and decision-makers, live signals (open/closed roles, leadership moves, news, tech stack), and…
breakstageaxe61/genspark-claw
Prepare an AI phone call end-to-end — research the callee, set a concrete objective and fallback, draft a natural call script with branching, and produce a post-call summary template.
TheCraigHewitt/skills
Turns a piece of Craig's content (an email, a YouTube script, an essay, or pasted text) into a polished image carousel publishable to both LinkedIn and Instagram from one set of 1080x1350 slides.
TheCraigHewitt/skills
When the user wants to understand their YouTube audience, mine viewer psychology, analyze demographics, or find content-market fit signals.
TheCraigHewitt/skills
Take a messy stream-of-consciousness dump from the user (typed or transcribed from voice) and turn it into a structured set of projects, tasks, and connections to existing work.
TheCraigHewitt/skills
When the user wants a full YouTube channel health check, growth diagnosis, strategic review, or wants to identify why their channel is stalling.
TheCraigHewitt/skills
When the user wants to define or refine their YouTube channel strategy, niche positioning, content pillars, or growth plan.
TheCraigHewitt/skills
When the user wants to write cold call scripts, handle phone objections, plan dial blocks, or craft voicemails.
Categories
When the user wants to plan a discovery call, build discovery questions, qualify a lead, or prep for a first call with a prospect. Discovery Call is an agent skill from TheCraigHewitt/skills. When the user wants to plan a discovery call, build discovery questions, qualify a lead, or prep for a first call with a prospect.
Discovery Call fits situations like: wants to plan a discovery call; build discovery questions; prep for a first call with a prospect; the user says prep for a discovery call.
Run `npx skills add TheCraigHewitt/skills --skill discovery-call -a claude-code`. Or copy the skill folder (sales/discovery-call in TheCraigHewitt/skills) into .claude/skills/discovery-call in your project. Claude Code loads it when a task matches its description.
Run `npx skills add TheCraigHewitt/skills --skill discovery-call -a codex`. Or copy the skill folder (sales/discovery-call in TheCraigHewitt/skills) into .agents/skills/discovery-call in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add TheCraigHewitt/skills --skill discovery-call -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/discovery-call, .gemini/skills/discovery-call, .github/skills/discovery-call and .opencode/skills/discovery-call in your project.
SKILL.md names no scripts, command-line tools or credentials: Discovery Call is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Discovery Call is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 5.8k tokens (SKILL.md is roughly 23k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Discovery Call: Luopan Company Research (zhangxiaoqiang1991/luopan, 389 stars), Company Research (stophobia/deerflow2.0-enhanced, 822 stars), Meeting Prep Brief (BrianRWagner/ai-marketing-claude-code-skills, 441 stars) and Sdt (StopDisTrain/sdt-skills, 309 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
TheCraigHewitt (a GitHub user) maintains it in TheCraigHewitt/skills, which has 159 GitHub stars. The repository holds 65 skills in this directory. The repository was last updated on May 22, 2026.
Source: TheCraigHewitt/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.