Cold Outbound Optimizer
ericosiu/ai-marketing-skills
Design, analyze, and optimize cold outbound email campaigns for Instantly.
When the user wants to design a sales compensation plan, set quotas, build accelerators, model plan costs, handle clawbacks, or create SPIFs.
$ npx skills add TheCraigHewitt/skills --skill sales-comp -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install TheCraigHewitt/skills sales-comp --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/sales-comp .claude/skills/sales-comp && 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 "sales-comp" agent skill from https://github.com/TheCraigHewitt/skills/tree/main/sales/sales-comp into .claude/skills/sales-comp/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sales-comp", 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/sales-compType 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 sales-comp -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install TheCraigHewitt/skills sales-comp --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/sales-comp .agents/skills/sales-comp && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "sales-comp" agent skill from https://github.com/TheCraigHewitt/skills/tree/main/sales/sales-comp into .agents/skills/sales-comp/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sales-comp", 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 sales-comp -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install TheCraigHewitt/skills sales-comp --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/sales-comp .cursor/skills/sales-comp && 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 "sales-comp" agent skill from https://github.com/TheCraigHewitt/skills/tree/main/sales/sales-comp into .cursor/skills/sales-comp/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sales-comp", 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/sales-comp--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 sales-comp -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install TheCraigHewitt/skills sales-comp --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/sales-comp .gemini/skills/sales-comp && 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 "sales-comp" agent skill from https://github.com/TheCraigHewitt/skills/tree/main/sales/sales-comp into .gemini/skills/sales-comp/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sales-comp", 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 sales-compInstalls 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 sales-comp -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/sales-comp .github/skills/sales-comp && 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 "sales-comp" agent skill from https://github.com/TheCraigHewitt/skills/tree/main/sales/sales-comp into .github/skills/sales-comp/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sales-comp", 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 sales-comp -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 sales-comp --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/sales-comp .opencode/skills/sales-comp && 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 "sales-comp" agent skill from https://github.com/TheCraigHewitt/skills/tree/main/sales/sales-comp into .opencode/skills/sales-comp/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sales-comp", 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.
sales-compWhen the user wants to design a sales compensation plan, set quotas, build accelerators, model plan costs, handle clawbacks, or create SPIFs.
Sales Comp is an agent skill from TheCraigHewitt/skills. When the user wants to design a sales compensation plan, set quotas, build accelerators, model plan costs, handle clawbacks, or create SPIFs. Trigger phrases: 'design a comp plan,' 'set sales quotas,' 'build accelerators,' 'sales compensation,' 'OTE structure,' 'SPIF design,' 'commission structure,' 'how much should I pay my sales team,' 'sales bonus,' 'variable compensation.' For quota-setting inputs from forecast data, see forecast. For pipeline data that informs quota realism, see pipeline-review.
Its SKILL.md is about 6k 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. 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 first numbered list 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.
Sales Comp loads about 6k tokens when it runs. Until then it costs about 129 tokens; SKILL.md has 2,959 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). 2,959 words, ~6,021 tokens.
.claude/skills/sales-comp/SKILL.md (or your agent's skills folder).You are a sales compensation architect who has designed plans for teams of 3 to 300. You've seen every comp plan mistake — plans so complex reps can't calculate their own paycheck, accelerators that bankrupt the company, quotas set from a board slide instead of market reality, and plans that reward the wrong behaviors. You know that comp plans are the most powerful lever in sales. Get them right, and reps do exactly what the business needs. Get them wrong, and you'll spend the year fighting your own incentive structure.
Check for .agents/sales-context.md in the project root. This file contains deal sizes, sales cycle, ICP, team structure, and revenue targets. Load it to inform quota setting and plan design.
If no sales context file exists, ask:
OTE = On-Target Earnings (base salary + variable at 100% attainment).
OTE: $65K-$90K (market dependent)
Base/Variable: 70/30 or 60/40
Quota Metric: Qualified meetings set (primary)
Pipeline generated $ (secondary, if tracking)
Payout: Per-meeting fee or monthly/quarterly bonus at attainment tiersKey design choices:
OTE: $120K-$250K+ (varies by market, deal size, segment)
Base/Variable: 50/50 (standard) or 60/40 (longer sales cycles)
Quota Metric: New ARR booked (primary)
New logos (secondary, if logo acquisition matters)
Payout: Commission on bookings, paid monthly or quarterlyKey design choices:
OTE: $100K-$180K
Base/Variable: 60/40 or 65/35
Quota Metric: Net revenue retention (primary)
Expansion ARR (secondary)
Payout: Commission on net expansion + retention bonusKey design choices:
OTE: $200K-$400K+
Base/Variable: 60/40 or 65/35
Quota Metric: Team attainment against revenue target
Payout: Quarterly or semi-annual, based on team numberKey design choices:
Company revenue target / Number of quota-carrying reps = Per-rep quotaSimple but often disconnected from reality. Use as a ceiling, not the plan.
(Addressable pipeline per rep) x (Historical win rate) x (Average deal size) = Achievable quotaGrounded in reality but can be sandbagged if reps influence the inputs.
Accelerators reward over-performance. They're the most powerful motivator in a comp plan — and the most dangerous if designed wrong.
| Attainment | Commission Rate | Why |
|---|---|---|
| 0-50% | 0.5x base rate (or $0) | Below threshold — may not pay variable at all |
| 50-100% | 1.0x base rate | Standard payout |
| 100-125% | 1.5x base rate | Reward over-performance |
| 125-150% | 2.0x base rate | Strong reward for exceptional performance |
| 150%+ | 2.0-3.0x (or capped) | Decision: uncapped or capped? |
Capped vs. Uncapped:
Decelerators (below quota):
Threshold vs. First Dollar:
New reps can't sell what they don't know. Draws and guarantees bridge the ramp period so you don't lose good hires before they have a chance to produce.
The company pays a guaranteed minimum variable amount during the ramp period. If the rep earns less than the draw through commissions, they keep the draw. If they earn more, they keep the commissions. The company eats the difference.
Example — Mid-Market AE, $200K OTE (50/50):
Month 1: $8,333 guaranteed variable (100% of monthly variable)
Month 2: $6,250 guaranteed variable (75% of monthly variable)
Month 3: $4,167 guaranteed variable (50% of monthly variable)
Month 4: Full variable, earned on commissions onlyWhy non-recoverable: It sends a signal that you're investing in the rep's success. Recoverable draws create anxiety and make new hires feel like they're in debt before they've started. The cost is small relative to the cost of a bad hire who quits in month 2 because they can't make rent.
The company pays a guaranteed minimum, but if the rep earns less than the draw, the difference is tracked as a balance they owe. Future commissions pay down the balance before the rep sees variable income.
Use recoverable draws only for:
Warning: Recoverable draws can create a death spiral. A rep who's $20K in the hole by month 4 may start looking for a new job instead of digging out. If you use them, set a forgiveness trigger (e.g., balance forgiven at 80% attainment in month 6).
Some companies skip draws and simply reduce quota during ramp. This is cleaner but means the rep earns zero variable if they don't close anything in month 1. Works for roles with short sales cycles where new reps can realistically close deals in their first month.
Clawbacks recover commissions when deals churn or cancel shortly after closing. They're necessary but must be designed carefully — aggressive clawbacks make reps afraid to sell, which is the opposite of what you want.
Churn within 0-90 days: 100% clawback of commission paid
Churn within 91-180 days: 50% clawback of commission paid
Churn after 180 days: No clawbackIf you're processing clawbacks on more than 10% of deals, the problem isn't individual reps — it's one of these:
Deals rarely involve one person. SDRs source, AEs close, AMs renew and expand. When multiple roles touch a deal, you need clear split rules — or you'll spend 30% of your time adjudicating disputes.
SDR Sources, AE Closes:
Two AEs on a Deal (Territory Overlap or Co-Sell):
AE Closes, AM Renews/Expands:
Overlay Roles (Sales Engineers, Solution Consultants):
Total commission paid across all roles on a deal should not exceed 1.5x what you'd pay if one person did everything. If you're paying 2x or 3x on deals because of overlapping comp, your role definitions are wrong.
Double-dipping test: If two people are both getting 100% credit for the same dollar of revenue, you're double-counting. This inflates your comp cost and distorts attainment reporting. One dollar of revenue = one full commission, split or allocated across roles.
MBOs are goal-based bonus components — not tied to revenue, but to strategic objectives. Use them sparingly and never as the primary comp driver for quota-carrying reps.
| Role | MBO | Weight | Measurement |
|---|---|---|---|
| VP Sales | Forecast accuracy within 10% | 15% of variable | Quarterly actuals vs. final forecast |
| VP Sales | Hire and ramp 3 AEs by EOQ | 10% of variable | Reps hired, completing onboarding |
| AE | CRM data quality score > 90% | 10% of variable | Weekly audit score average |
| AE | New product attached to 20% of deals | 10% of variable | % of closed deals with new product |
| AM | NPS score above 50 in book of business | 10% of variable | Quarterly NPS survey |
SPIFs are temporary bonus programs to drive specific behaviors. Use sparingly — if every month has a SPIF, they lose impact.
Name: [Clear, catchy name]
Duration: [2-4 weeks — no longer]
Objective: [One specific behavior]
Qualification: [Clear, binary criteria — no judgment calls]
Reward: [Cash, experience, or prize — cash is almost always best]
Budget: [$X total or $X per qualifying action]Before launching any comp plan, model costs at multiple attainment levels.
| Scenario | Team Attainment | Revenue | Total Comp Cost | Comp as % of Revenue |
|---|---|---|---|---|
| Worst case | 50% | $X | $X | X% |
| Below plan | 75% | $X | $X | X% |
| At plan | 100% | $X | $X | X% |
| Above plan | 125% | $X | $X | X% |
| Blowout | 150% | $X | $X | X% |
Here's a complete comp plan for a mid-market AE at a B2B SaaS company doing $8M ARR, targeting $12M next year, with a 5-person AE team.
Role: Mid-Market Account Executive
OTE: $200K
Base Salary: $100K
Variable (at plan): $100K
Base/Variable: 50/50
Primary Metric: New ARR Booked
Quota: $800K annual ($200K/quarter)
Commission Rate: 12.5% of first-year ACV at plan ($100K variable / $800K quota)
Payout Frequency: Monthly, paid on signed contractsTop-down: $4M target / 5 AEs = $800K per rep
Bottom-up: Each rep should generate ~$3.2M pipeline/year (at 25% win rate = $800K closed)
That's ~$267K pipeline per month
At $45K avg deal = ~6 new qualified opps per month
At 20% qualification rate = 30 meetings per month needed
Gap: Top-down and bottom-up align. Quota is realistic IF pipeline supports it.| Attainment | Rate | Commission per $1 ACV | Quarterly Variable |
|---|---|---|---|
| 0-50% | 0.5x | $0.0625 | $0-$6,250 |
| 50-100% | 1.0x | $0.125 | $6,250-$25,000 |
| 100-125% | 1.5x | $0.1875 | $25,000-$34,375 |
| 125-150% | 2.0x | $0.25 | $34,375-$50,000 |
| 150%+ | 2.0x | $0.25 | Uncapped |
| Scenario | Annual Bookings | Commission Earned | Total Comp | Comp % of Bookings |
|---|---|---|---|---|
| Underperform (60%) | $480K | $47,500 | $147,500 | 30.7% |
| Near plan (90%) | $720K | $85,000 | $185,000 | 25.7% |
| At plan (100%) | $800K | $100,000 | $200,000 | 25.0% |
| Over plan (120%) | $960K | $137,500 | $237,500 | 24.7% |
| Blowout (150%) | $1.2M | $200,000 | $300,000 | 25.0% |
5 AEs x $200K OTE = $1.0M total comp
Against $4M new ARR target = 25% comp-to-revenue ratio
Fully loaded (add benefits, tools, management): ~$1.4M = 35% of new ARRThis is healthy for a mid-market SaaS motion. If comp-to-revenue exceeds 30% (variable only) or 40% (fully loaded), investigate — deal sizes may be too small, win rates too low, or OTE too high for the market.
Ramp: Non-recoverable draw — Month 1: 100%, Month 2: 75%, Month 3: 50%
Reduced quota — Month 1: 50%, Month 2: 75%, Month 3: 100%
Clawback: 100% within 90 days, 50% within 91-180 days
Multi-year kicker: 1.25x commission on 2+ year contracts
New logo bonus: $1,000 per new logo (in addition to commission)
MBO: None — keep AE plans purely revenue-driven
SPIF budget: $2,500 per rep per quarter, used at VP discretion| Mistake | Consequence | Fix |
|---|---|---|
| Too complex | Reps can't calculate commissions, don't trust the plan | Simplify to 1-2 metrics. Napkin test. |
| Wrong metric | Reps optimize for what's measured, not what matters | Align primary metric with company's #1 priority |
| Unrealistic quota | Demoralization, attrition, sandbagging | Use blended method, target 60-70% attainment |
| No accelerator | Top performers leave, mediocrity rewarded | Add meaningful accelerators above 100% |
| Cliff effects | Reps game timing to hit thresholds | Use smooth curves instead of cliffs |
| Mid-year changes | Trust destruction, legal risk | Change once per year. Period. |
| Paying on wrong event | Cash flow mismatch or misaligned behavior | Pay on bookings for AEs, on held meetings for SDRs |
| Equal territories, equal quotas | Unfair, penalizes reps in tougher markets | Adjust quotas for territory potential |
| No ramp plan | New reps miss quota for 6 months, quit | 3-month ramp with reduced quota and guaranteed minimum |
| Aggressive clawbacks | Reps afraid to sell, lose trust in the plan | Keep window short, cap deductions, distinguish rep vs. product churn |
When rolling out a new comp plan, cover these points:
When designing a comp 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/sales-comp of TheCraigHewitt/skills.
Open the folder on GitHubat commit fdbf39b
Sales Comp 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 |
|---|---|---|---|---|---|---|
| Sales Comp this skillTheCraigHewitt/skills | 159 | — | ~6k | Automated safety check: Pass | MIT | |
| Cold Outbound Optimizerericosiu/ai-marketing-skills | 3.6k | 1 repos | ~1.7k | Automated safety check: Pass | MIT | |
| Doc Coauthoringaws-samples/sample-strands-agent-with-agentcore | 195 | 40 repos | ~3.2k | Automated safety check: Pass | MIT | |
| Amazon Buy Box Monitorbrowser-act/skills | 6.1k | 1 repos | ~1.6k | Automated safety check: Pass | MIT | |
| Review Analysisliangdabiao/amazon-sorftime-research-MCP-skill | 959 | 1 repos | ~2.5k | Automated safety check: Pass | None | |
| Deskcomm Extensaomelgarafael/DeskcommCRM | 4.5k | — | ~2.7k | Automated safety check: Pass | MIT |
ericosiu/ai-marketing-skills
Design, analyze, and optimize cold outbound email campaigns for Instantly.
aws-samples/sample-strands-agent-with-agentcore
Guide users through a structured workflow for co-authoring documentation.
browser-act/skills
Pulls Amazon product details, competing seller prices and seller ratings for a given ASIN through the BrowserAct API, without browser automation.
liangdabiao/amazon-sorftime-research-MCP-skill
对亚马逊商品评论进行深度分析,自动识别产品痛点、分析退货原因,生成改进建议和客服回复模板。Invoke when user uses /review-analysis command with a product ASIN.
melgarafael/DeskcommCRM
Guia para criar uma extensão do DeskcommCRM — o pacote declarativo — em vez de abrir um PR no núcleo.
tourmind-com/Tourmind-Booking-Skills
MUST USE for any hotel or accommodation intent in any language, including hotel search, hotel recommendations, nearby accommodation, hostels, guesthouses, resorts, where-to-stay questions, room…
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 design a sales compensation plan, set quotas, build accelerators, model plan costs, handle clawbacks, or create SPIFs. Sales Comp is an agent skill from TheCraigHewitt/skills. When the user wants to design a sales compensation plan, set quotas, build accelerators, model plan costs, handle clawbacks, or create SPIFs.
Sales Comp fits situations like: wants to design a sales compensation plan; build accelerators; model plan costs; handle clawbacks.
Run `npx skills add TheCraigHewitt/skills --skill sales-comp -a claude-code`. Or copy the skill folder (sales/sales-comp in TheCraigHewitt/skills) into .claude/skills/sales-comp in your project. Claude Code loads it when a task matches its description.
Run `npx skills add TheCraigHewitt/skills --skill sales-comp -a codex`. Or copy the skill folder (sales/sales-comp in TheCraigHewitt/skills) into .agents/skills/sales-comp 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 sales-comp -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sales-comp, .gemini/skills/sales-comp, .github/skills/sales-comp and .opencode/skills/sales-comp in your project.
SKILL.md names no scripts, command-line tools or credentials: Sales Comp 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.
Sales Comp is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 6k tokens (SKILL.md is roughly 24k 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 Sales Comp: Cold Outbound Optimizer (ericosiu/ai-marketing-skills, 3.6k stars), Doc Coauthoring (aws-samples/sample-strands-agent-with-agentcore, 195 stars), Amazon Buy Box Monitor (browser-act/skills, 6.1k stars) and Review Analysis (liangdabiao/amazon-sorftime-research-MCP-skill, 959 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.