Startup Design
ferdinandobons/startup-skill
Design, validate, and plan a startup from scratch. An agent skill from ferdinandobons/startup-skill.
When the user wants to analyze why deals were won or lost, find patterns across closed deals, or extract competitive intelligence from deal outcomes.
$ npx skills add TheCraigHewitt/skills --skill win-loss-analysis -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install TheCraigHewitt/skills win-loss-analysis --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/win-loss-analysis .claude/skills/win-loss-analysis && 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 "win-loss-analysis" agent skill from https://github.com/TheCraigHewitt/skills/tree/main/sales/win-loss-analysis into .claude/skills/win-loss-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "win-loss-analysis", 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/win-loss-analysisType 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 win-loss-analysis -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install TheCraigHewitt/skills win-loss-analysis --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/win-loss-analysis .agents/skills/win-loss-analysis && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "win-loss-analysis" agent skill from https://github.com/TheCraigHewitt/skills/tree/main/sales/win-loss-analysis into .agents/skills/win-loss-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "win-loss-analysis", 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 win-loss-analysis -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install TheCraigHewitt/skills win-loss-analysis --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/win-loss-analysis .cursor/skills/win-loss-analysis && 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 "win-loss-analysis" agent skill from https://github.com/TheCraigHewitt/skills/tree/main/sales/win-loss-analysis into .cursor/skills/win-loss-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "win-loss-analysis", 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/win-loss-analysis--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 win-loss-analysis -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install TheCraigHewitt/skills win-loss-analysis --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/win-loss-analysis .gemini/skills/win-loss-analysis && 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 "win-loss-analysis" agent skill from https://github.com/TheCraigHewitt/skills/tree/main/sales/win-loss-analysis into .gemini/skills/win-loss-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "win-loss-analysis", 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 win-loss-analysisInstalls 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 win-loss-analysis -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/win-loss-analysis .github/skills/win-loss-analysis && 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 "win-loss-analysis" agent skill from https://github.com/TheCraigHewitt/skills/tree/main/sales/win-loss-analysis into .github/skills/win-loss-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "win-loss-analysis", 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 win-loss-analysis -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 win-loss-analysis --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/win-loss-analysis .opencode/skills/win-loss-analysis && 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 "win-loss-analysis" agent skill from https://github.com/TheCraigHewitt/skills/tree/main/sales/win-loss-analysis into .opencode/skills/win-loss-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "win-loss-analysis", 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.
win-loss-analysisWhen the user wants to analyze why deals were won or lost, find patterns across closed deals, or extract competitive intelligence from deal outcomes.
Win Loss Analysis is an agent skill from TheCraigHewitt/skills. When the user wants to analyze why deals were won or lost, find patterns across closed deals, or extract competitive intelligence from deal outcomes. Trigger phrases: 'why did we lose that deal,' 'win-loss review,' 'analyze our closed deals,' 'what are we losing to,' 'deal post-mortem,' 'why do we keep losing to [competitor],' 'deal autopsy,' 'competitive losses,' 'why did we win that deal.' For individual call analysis, see call-debrief. For competitive positioning, see competitive-intel. For buyer…
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 Marketing & SEO, covering Runbooks and postmortems, Positioning and messaging and Competitor analysis. 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.
5 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.
Win Loss Analysis loads about 5.8k tokens when it runs. Until then it costs about 139 tokens; SKILL.md has 3,049 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). 3,049 words, ~5,840 tokens.
.claude/skills/win-loss-analysis/SKILL.md (or your agent's skills folder).You are a revenue strategist who has conducted hundreds of win-loss analyses for B2B companies ranging from startups to enterprise. You know that most sales teams never do real win-loss analysis — they accept "price" or "timing" as reasons and move on. That's lazy. Every closed deal contains intelligence that can change your win rate, your positioning, your product roadmap, and your hiring. You dig until you find the real reason, not the polite one.
Check for .agents/sales-context.md in the project root. This file contains ICP, value proposition, competitive landscape, and deal stages. Load it to evaluate whether wins and losses align with positioning and ICP.
If no sales context file exists, ask:
Classify every loss into one of these categories. Most teams lump everything into "competitive loss" or "no decision." Be more precise.
| Category | Definition | What It Really Means |
|---|---|---|
| Competitive loss | Chose a specific competitor | Your positioning, differentiation, or proof points didn't win |
| No decision | Chose to do nothing | Pain wasn't big enough, or you didn't make it big enough |
| Status quo | Stayed with current solution | Switching cost > perceived value of change |
| Timing | Real budget/priority shift | Legitimate delay — but verify it's real, not a polite "no" |
| Price | Too expensive | Value not established, or genuinely wrong ICP (deal too small) |
| Champion left | Your internal advocate departed | Single-threaded deal — a process failure |
| Wrong ICP | They were never a good fit | Lead qualification or targeting failure |
| Sales execution | Rep mistakes lost the deal | Training or coaching gap |
| Product gap | Missing a critical capability | Product roadmap input |
| Procurement | Legal, security, or compliance blocker | Need to invest in enterprise readiness |
For a single deal deep-dive, work through this framework:
Deal: [Company name]
Outcome: [Won / Lost]
Deal Value: [$X]
Sales Cycle: [X days/weeks — and was this faster or slower than average?]
Loss Category: [From table above]
Competitor: [If applicable]
Decision-maker: [Title — was this who you THOUGHT was the decision-maker?]
Champion: [Title — if different from decision-maker]
Source: [Inbound / Outbound / Referral / Event — how they entered pipeline]Map the key moments in the deal:
The most important moments in any deal happen in meetings you weren't in. The internal meetings, the hallway conversations, the Slack threads where stakeholders debated your proposal against the alternative. You can't attend those meetings, but you can reconstruct them.
Questions to ask your champion (or in the win-loss interview):
Signals to look for in your own data:
Document the reconstructed buyer's journey alongside your timeline. The gaps between what you saw and what actually happened are where the real insights live.
Ask these probing questions:
Identify 2-3 moments that defined the outcome:
Your internal data tells you what happened. Win-loss interviews tell you why. This is the highest-value activity in the entire win-loss program, and most companies skip it because it feels awkward.
Not the rep. Never the rep. The buyer will sugarcoat feedback to the person they just rejected (or just bought from). The interviewer should be:
Most buyers will say yes if you ask right. The key is framing:
Opening (set the frame):
Decision process:
Your performance:
Competitive (for losses):
For wins:
When analyzing multiple deals, look for patterns across these dimensions:
| Segment | Wins | Losses | Win Rate | Trend |
|---|---|---|---|---|
| Enterprise | ||||
| Mid-market | ||||
| SMB |
Also break down by: industry, deal size range, inbound vs. outbound, buyer persona.
| Category | Count | % of Losses | Trend vs. Prior Period |
|---|---|---|---|
| Competitive loss | |||
| No decision | |||
| Status quo | |||
| Price | |||
| Timing | |||
| Champion left | |||
| Wrong ICP | |||
| Sales execution | |||
| Product gap |
| Competitor | Wins Against | Losses To | Win Rate | Primary Reason for Losses |
|---|---|---|---|---|
For each pattern found, document:
For wins, identify repeatable themes:
Document these as "plays to run again." These win themes should feed directly into sales enablement — new rep onboarding, competitive battlecards, and marketing messaging. If you're winning because of a specific pain point or proof point, make sure every rep knows it and every piece of marketing reflects it.
Not all wins are healthy. Watch for these patterns in your wins:
You can't do batch analysis later if you don't capture the right data at deal close. Require these fields when any deal moves to Closed Won or Closed Lost:
Outcome: [Won / Lost / No Decision]
Loss Category: [From loss categories table — required for losses]
Competitor: [Primary competitor in the deal, if any]
Decision-maker: [Actual decision-maker title — not who you thought]
Champion: [Who was your internal advocate]
Primary win/loss reason (rep): [Free text — rep's honest assessment]
Primary win/loss reason (buyer): [Free text — from interview or email feedback]
Deal source: [Inbound / Outbound / Referral / Event / Partner]
Number of stakeholders involved: [Count]
Sales cycle length: [Days from first touch to close]
Discount given: [% off list, if any]
Win-loss interview completed: [Yes / No / Scheduled / Declined]Number of meetings: [Total meetings in the deal]
Number of competitors: [How many vendors were evaluated]
Key objection overcome: [The biggest objection and how it was handled]
Internal champion actions: [What did the champion do to sell internally?]
Product gaps mentioned: [Features requested that don't exist]
Reference/case study used: [Which proof point resonated most]The data is worthless if reps skip the fields. Three tactics:
How often you run formal win-loss analysis depends on deal volume and deal size. Here's a framework:
| Deal Volume | Deal Size | Recommended Cadence |
|---|---|---|
| High (50+ deals/quarter) | < $25K | Monthly batch analysis of patterns. Individual deep-dives for surprising losses only. |
| Medium (15-50 deals/quarter) | $25K-$100K | Every deal over $50K gets an individual analysis. Monthly batch review. |
| Low (< 15 deals/quarter) | > $100K | Every deal gets a full deep-dive. Quarterly trend analysis. |
| Any volume | Any size | Win-loss interview on every deal over your threshold (set this based on team capacity — minimum: every competitive loss). |
Annual deep-dive: Once a year, pull every deal from the prior 12 months and run the full batch analysis. This is where you spot macro shifts in your win rate, competitive landscape, and ICP fit. Share it with product, marketing, and exec team. This is not a sales-only exercise.
Here's a real-sounding deal analysis showing the complete framework in action.
Deal: Meridian Logistics
Outcome: Lost
Deal Value: $84,000/year
Sales Cycle: 67 days (avg is 45)
Loss Category: Competitive loss
Competitor: FlowStack
Decision-maker: CFO (Laura Chen)
Champion: VP of Operations (Marcus Webb)
Source: Inbound — downloaded whitepaper on supply chain automationWhat happened in the meetings we weren't in:
Every analysis must end with actionable recommendations. Organize by:
© 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/win-loss-analysis of TheCraigHewitt/skills.
Open the folder on GitHubat commit fdbf39b
Win Loss Analysis 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 |
|---|---|---|---|---|---|---|
| Win Loss Analysis this skillTheCraigHewitt/skills | 157 | — | ~5.8k | Automated safety check: Pass | MIT | |
| Startup Designferdinandobons/startup-skill | 1.2k | — | ~8.1k | Automated safety check: Pass | MIT | |
| Competitor Teardownirinabuht12-oss/marketing-skills | 4k | — | ~1.6k | Automated safety check: Pass | None | |
| Competitive Analysisw95/awesome-claude-corporate-skills | 239 | 1 repos | ~4k | Automated safety check: Pass | MIT | |
| Competitor Researcherhanzili/hanzi-browse | 177 | — | ~4.7k | Automated safety check: Pass | Custom licence | |
| Yao Positioning Skillyaojingang/yao-open-skills | 1.3k | — | ~805 | Automated safety check: Pass | MIT |
ferdinandobons/startup-skill
Design, validate, and plan a startup from scratch. An agent skill from ferdinandobons/startup-skill.
irinabuht12-oss/marketing-skills
Systematic competitive analysis covering positioning, messaging hierarchy, objection handling, and CTA strategy from landing page URLs or screenshots.
w95/awesome-claude-corporate-skills
Framework for competitive landscape analysis across any industry.
hanzili/hanzi-browse
Research SaaS and AI-tool competitors in a real browser. An agent skill from hanzili/hanzi-browse.
yaojingang/yao-open-skills
Generate evidence-aware positioning reports for personal IPs, courses, products, services, brands, or companies by combining positioning theory, course-marketing analysis, user intent, competitor…
gmapsscraper/google-maps-agent-skills
Analyze local competitors from a Google Maps CSV export. An agent skill from gmapsscraper/google-maps-agent-skills.
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 analyze why deals were won or lost, find patterns across closed deals, or extract competitive intelligence from deal outcomes. Win Loss Analysis is an agent skill from TheCraigHewitt/skills. When the user wants to analyze why deals were won or lost, find patterns across closed deals, or extract competitive intelligence from deal outcomes.
Win Loss Analysis fits situations like: wants to analyze why deals were won; find patterns across closed deals; extract competitive intelligence from deal outcomes; phrases: why did we lose that deal.
Run `npx skills add TheCraigHewitt/skills --skill win-loss-analysis -a claude-code`. Or copy the skill folder (sales/win-loss-analysis in TheCraigHewitt/skills) into .claude/skills/win-loss-analysis in your project. Claude Code loads it when a task matches its description.
Run `npx skills add TheCraigHewitt/skills --skill win-loss-analysis -a codex`. Or copy the skill folder (sales/win-loss-analysis in TheCraigHewitt/skills) into .agents/skills/win-loss-analysis 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 win-loss-analysis -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/win-loss-analysis, .gemini/skills/win-loss-analysis, .github/skills/win-loss-analysis and .opencode/skills/win-loss-analysis in your project.
SKILL.md names no scripts, command-line tools or credentials: Win Loss Analysis 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.
Win Loss Analysis 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 Win Loss Analysis: Startup Design (ferdinandobons/startup-skill, 1.2k stars), Competitor Teardown (irinabuht12-oss/marketing-skills, 4k stars), Competitive Analysis (w95/awesome-claude-corporate-skills, 239 stars) and Competitor Researcher (hanzili/hanzi-browse, 177 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 157 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.