Agent skill

Win Loss Analysis

by TheCraigHewitt in 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.

MITAuto-check passedMarketing & SEO

Install Win Loss Analysis

skills CLI
$ npx skills add TheCraigHewitt/skills --skill win-loss-analysis -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install TheCraigHewitt/skills win-loss-analysis --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ 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-src

Use ~/.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/

Facts

Skill name
win-loss-analysis
GitHub stars
157
Token cost
~5.8k tokens
SKILL.md length
3,049 words
Files
1
Skills in repo
65
Repo updated
First seen
Licence
MIT

At a glance

When the user wants to analyze why deals were won or lost, find patterns across closed deals, or extract competitive intelligence from deal outcomes.

  • Works in 5 steps: What do you sell? (Product/service,… → Who's your ICP? (Industry, company size,… → Who do you compete with? (Direct… → …
  • Wants to analyze why deals were won
  • SKILL.md covers Before Starting, Core Principles, Loss Categories and Individual Deal Analysis, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

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.

When your agent uses it

  • 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

Example prompts

  • “why did we lose that deal,”
  • “win-loss review,”
  • “analyze our closed deals,”
  • “/win-loss-analysis”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. What do you sell? (Product/service, typical deal size, sales cycle length)
  2. Who's your ICP? (Industry, company size, buyer title)
  3. Who do you compete with? (Direct competitors, alternatives, status quo)
  4. How many deals are we analyzing? (Single deal deep-dive or batch analysis?)
  5. Do you have deal data to share? (Notes, CRM exports, call transcripts, post-mortem notes)

What it can do on your machine

Read from SKILL.md and the folder at commit fdbf39b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    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.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

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.

Always · name and description, kept in context so the agent knows when to use it
~139
When it runs · the whole SKILL.md, loaded when a task matches
~5.8k

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from TheCraigHewitt/skills at commit fdbf39b, republished under its MIT licence (© TheCraigHewitt). 3,049 words, ~5,840 tokens.

Download SKILL.mdSave it as .claude/skills/win-loss-analysis/SKILL.md (or your agent's skills folder).
name
win-loss-analysis
description
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 understanding, see buyer-persona.
metadata.version
1.0.0

Win-Loss Analysis

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.

Before Starting

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:

  1. What do you sell? (Product/service, typical deal size, sales cycle length)
  2. Who's your ICP? (Industry, company size, buyer title)
  3. Who do you compete with? (Direct competitors, alternatives, status quo)
  4. How many deals are we analyzing? (Single deal deep-dive or batch analysis?)
  5. Do you have deal data to share? (Notes, CRM exports, call transcripts, post-mortem notes)

Core Principles

  1. The stated reason is almost never the real reason. "Price" usually means "I didn't see enough value." "Timing" usually means "this wasn't a priority." "Went with a competitor" tells you nothing about why. Dig deeper.
  2. Wins are as important as losses. Most teams only analyze losses. That's half the picture. Understanding why you win tells you what to double down on. Winning for the wrong reasons (discounting, heroic sales efforts) is a red flag too.
  3. Patterns beat anecdotes. One loss to a competitor is a data point. Five losses to the same competitor with the same objection is a pattern that demands action. Always look for clusters.
  4. Separate sales execution from product/market fit. Did you lose because the rep fumbled discovery, or because the product genuinely doesn't solve their problem? These require completely different fixes. Conflating them wastes time and money.
  5. Win-loss is a feedback loop, not a report. The analysis is only valuable if it changes behavior — messaging, targeting, product priorities, sales training, competitive positioning. Every analysis should end with specific recommendations.
  6. The best data comes from the buyer, not the seller. Your rep's version of why a deal was lost is filtered through ego and incomplete information. The buyer's version, captured through a structured interview, is the real intelligence. Both matter. The buyer's matters more.

Loss Categories

Classify every loss into one of these categories. Most teams lump everything into "competitive loss" or "no decision." Be more precise.

CategoryDefinitionWhat It Really Means
Competitive lossChose a specific competitorYour positioning, differentiation, or proof points didn't win
No decisionChose to do nothingPain wasn't big enough, or you didn't make it big enough
Status quoStayed with current solutionSwitching cost > perceived value of change
TimingReal budget/priority shiftLegitimate delay — but verify it's real, not a polite "no"
PriceToo expensiveValue not established, or genuinely wrong ICP (deal too small)
Champion leftYour internal advocate departedSingle-threaded deal — a process failure
Wrong ICPThey were never a good fitLead qualification or targeting failure
Sales executionRep mistakes lost the dealTraining or coaching gap
Product gapMissing a critical capabilityProduct roadmap input
ProcurementLegal, security, or compliance blockerNeed to invest in enterprise readiness

Individual Deal Analysis

For a single deal deep-dive, work through this framework:

Deal Profile
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]
Timeline Reconstruction

Map the key moments in the deal:

  1. How did they enter the pipeline? (Inbound, outbound, referral, event)
  2. What was the initial pain? (What they said in the first conversation)
  3. How did the deal progress? (Key meetings, demos, proposals)
  4. Where did momentum shift? (The moment things started going well or sideways)
  5. What was the final decision moment? (What tipped the decision)
  6. Who made the decision? (Was it who you thought?)
Buyer's Journey Reconstruction

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):

  • "After our demo, what was the internal conversation like? Who was for it, who pushed back?"
  • "Was there a moment where the deal almost died internally? What happened?"
  • "What materials did you share internally, and with whom? What questions came back?"
  • "Were there criteria or requirements that came up internally that we never discussed?"
  • "Who had the most influence on the final decision? What mattered most to them?"

Signals to look for in your own data:

  • Long gaps between your interactions — what was happening during those silences?
  • Sudden changes in the stakeholder group (new people appearing on calls, original champion going quiet)
  • Requests for specific information or materials — these often reflect internal objections you don't know about
  • The prospect quoting language you didn't use — they're getting talking points from somewhere (a competitor, an internal skeptic, a board member)

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.

The Real Reason

Ask these probing questions:

  • What did the prospect tell us? (The polite reason)
  • What do the signals suggest? (The behavioral evidence)
  • What's our honest assessment? (What we think really happened)
  • What could we have done differently? (Be specific — not "sold harder")
Key Moments

Identify 2-3 moments that defined the outcome:

  • The question that opened up the deal (or killed it)
  • The demo that landed (or fell flat)
  • The stakeholder meeting that changed the dynamic
  • The competitor move that shifted perception
  • The internal champion action (or inaction)
  • The pricing conversation that built confidence (or created sticker shock)

Win-Loss Interviews

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.

Who Should Conduct the Interview

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:

  • A product marketing person
  • A sales leader who wasn't on the deal
  • An external consultant (for high-stakes analysis)
  • At minimum: someone the buyer perceives as genuinely curious, not defensive
When to Interview
  • Losses: Within 2 weeks of the decision. Memory fades fast, and their attention moves to the vendor they chose.
  • Wins: Within 30 days of close. They're in the implementation honeymoon and willing to talk.
  • No decisions: Hardest to schedule but often the most revealing. Try within 1 month.
How to Get Reluctant Participants

Most buyers will say yes if you ask right. The key is framing:

  • Don't say: "We'd like to understand why you didn't choose us." (Sounds like you want to re-open the deal.)
  • Say: "We're working on improving our process and would love 20 minutes of candid feedback. There's no sales agenda — we genuinely want to learn."
  • Offer a small incentive (gift card, donation to their preferred charity) — not because they need it, but because it signals you value their time.
  • Keep it to 20-30 minutes. Respect the commitment.
  • If they decline a call, offer a short written survey as an alternative. Some data is better than none.
Interview Questions

Opening (set the frame):

  • "Thanks for taking the time. Just to be clear — this isn't a sales call. We're trying to get better, and your honest feedback is the most valuable thing you can give us."

Decision process:

  • "Walk me through how you made this decision. Who was involved, and what were the key criteria?"
  • "When did you first realize which direction you were leaning? What triggered that?"
  • "Were there internal disagreements about the decision? How were those resolved?"

Your performance:

  • "How well did our team understand your problem?"
  • "Was there a moment in our process where you felt really confident — or where you started to have doubts?"
  • "If you could change one thing about how we engaged with you, what would it be?"

Competitive (for losses):

  • "What did [competitor] do differently that resonated?"
  • "Was there something they showed you that we didn't?"
  • "Was the decision primarily about the product, the team, or something else?"

For wins:

  • "What almost made you go a different direction?"
  • "What would have made this decision easier or faster?"
  • "Now that you're using the product, does your decision feel validated?"
What Not to Do
  • Don't argue with their feedback, even if it's wrong or unfair. Write it down.
  • Don't try to re-open the deal. You promised this wasn't a sales call.
  • Don't ask leading questions ("So you'd say our product was the best, right?").
  • Don't send a junior person. The quality of the interview depends on the interviewer's ability to ask follow-up questions and read between the lines.

Batch Analysis

When analyzing multiple deals, look for patterns across these dimensions:

Win/Loss by Segment
SegmentWinsLossesWin RateTrend
Enterprise
Mid-market
SMB

Also break down by: industry, deal size range, inbound vs. outbound, buyer persona.

Loss Reason Distribution
CategoryCount% of LossesTrend vs. Prior Period
Competitive loss
No decision
Status quo
Price
Timing
Champion left
Wrong ICP
Sales execution
Product gap
Competitive Win/Loss
CompetitorWins AgainstLosses ToWin RatePrimary Reason for Losses
Pattern Analysis

For each pattern found, document:

  1. Pattern: What keeps happening? (e.g., "We lose 70% of deals where the CFO enters late in the process")
  2. Root cause: Why? (e.g., "We're not multi-threading early enough — only talking to the VP of Ops")
  3. Impact: How big is this? (e.g., "This pattern accounts for $X in lost pipeline this quarter")
  4. Recommendation: What do we change? (e.g., "Require a CFO touchpoint before Stage 3")

Win Theme Extraction

For wins, identify repeatable themes:

  • ICP sweet spot: What profile of company do we win most consistently?
  • Pain alignment: What specific pain, when articulated, leads to wins?
  • Proof points that close: Which case studies or metrics resonate?
  • Process advantages: Where in the sales process do we create separation?
  • Competitive positioning: What do we say about competitors that lands?

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.

Win Red Flags

Not all wins are healthy. Watch for these patterns in your wins:

  • Discount-driven wins. If your win rate only looks good because you're discounting 30%+, you have a pricing or positioning problem, not a sales problem.
  • Hero-ball wins. If deals only close when the VP of Sales or CEO gets on the call, your reps aren't equipped. You're scaling on executive time, which doesn't scale.
  • Single-use-case wins. If you keep winning on the same narrow use case but losing everywhere else, your product-market fit is narrower than you think. That's not bad — but your ICP and targeting should reflect it.
  • Slow wins. If your average win takes 90 days but your average loss takes 30 days, prospects are deciding "no" quickly and deciding "yes" slowly. That means you're not creating urgency — the default is to not buy.
Show full SKILL.md (1,177 more words)Show less

CRM Data Collection for Win-Loss

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:

Required Fields at Deal Close
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]
Optional but Valuable Fields
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]
Making Reps Actually Fill This Out

The data is worthless if reps skip the fields. Three tactics:

  1. Gate commission payout on required fields. Sounds aggressive. Works every time.
  2. Make it 5 clicks, not 5 paragraphs. Dropdowns and picklists for structured fields. Only the "reason" field should be free text.
  3. Review it in pipeline meetings. If the manager asks about win-loss data every week, reps fill it out. If nobody ever looks at it, nobody fills it out.

Win-Loss Cadence

How often you run formal win-loss analysis depends on deal volume and deal size. Here's a framework:

Deal VolumeDeal SizeRecommended Cadence
High (50+ deals/quarter)< $25KMonthly batch analysis of patterns. Individual deep-dives for surprising losses only.
Medium (15-50 deals/quarter)$25K-$100KEvery deal over $50K gets an individual analysis. Monthly batch review.
Low (< 15 deals/quarter)> $100KEvery deal gets a full deep-dive. Quarterly trend analysis.
Any volumeAny sizeWin-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.

Worked Example: Full Deal Analysis

Here's a real-sounding deal analysis showing the complete framework in action.

Deal Profile
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 automation
Timeline Reconstruction
  1. Entry (Day 1): Marcus downloaded a whitepaper. SDR followed up. Discovery call booked for Day 5.
  2. Discovery (Day 5): Strong call. Marcus described manual routing process costing 12 FTE hours/day. Quantified pain at ~$380K/year in labor. Asked for a demo.
  3. Demo (Day 14): Demo to Marcus + 2 Directors. Good engagement. Marcus asked about implementation timeline. Directors asked about API integration with their WMS. One Director (Priya) asked pointed questions about uptime SLA — we later learned she'd been burned by a vendor migration before.
  4. Momentum shift (Day 28): Marcus went quiet for a week. When he resurfaced, he mentioned "we're also looking at FlowStack — just want to compare."
  5. Proposal (Day 35): Sent proposal at $84K/year. Marcus said it was "in the range." Asked for a reference call.
  6. Reference call (Day 42): Good reference call. But Marcus mentioned the CFO (Laura) was now involved and had questions about ROI methodology.
  7. CFO meeting (Day 52): Laura joined a call. She was polite but skeptical. Asked: "How do you guarantee the ROI numbers?" and "What happens if adoption is low in the first 90 days?" We gave general answers. FlowStack, we later learned, had a guaranteed ROI clause in their contract.
  8. Decision (Day 67): Marcus emailed: "We decided to go with FlowStack. It was very close. Appreciate your time."
Buyer's Journey Reconstruction

What happened in the meetings we weren't in:

  • After our demo, Marcus championed us internally but Priya (Director) was cautious based on her past migration failure. She wanted contractual risk mitigation.
  • When FlowStack entered, they offered a 90-day performance guarantee with a partial refund clause. This directly addressed Priya's concern and gave Laura (CFO) budget cover.
  • The final decision meeting was between Marcus, Priya, and Laura. Marcus preferred us on product. Priya preferred FlowStack on risk. Laura sided with Priya because the guarantee reduced her exposure.
The Real Reason
  • What they told us: "It was very close. We went a different direction."
  • What the signals suggest: The deal was ours to lose after the demo. We lost it when the CFO entered and we couldn't answer the risk/guarantee question. FlowStack didn't have a better product — they had a better offer structure for a risk-averse buyer.
  • Honest assessment: We were single-threaded through Marcus and didn't engage Laura early enough. When she entered at Day 52, we had 15 minutes to build trust that FlowStack had been building for weeks. We also had no answer for the guarantee objection because we don't offer one.
  • What we could have done differently:
    • Asked Marcus on Day 14: "Who else needs to be comfortable with this decision?" and gotten to Laura by Day 20.
    • Addressed the risk question proactively: even without a formal guarantee, we could have proposed a phased rollout, success metrics at 30/60/90, and an executive review cadence.
    • Learned about FlowStack's guarantee earlier and pre-empted it.
Key Moments
  1. Day 14 — Priya's SLA question: This was the signal that risk mitigation would matter. We answered the question technically but didn't probe why she was asking. If we'd asked "Sounds like you've been through a tough migration before — what happened?" we would have uncovered the real buying criteria.
  2. Day 28 — Marcus goes quiet: This was the week FlowStack entered. We didn't ask Marcus what was happening. A simple "Hey, noticed we haven't connected — anything change on your end?" might have surfaced the competitor earlier.
  3. Day 52 — Laura's ROI question: "How do you guarantee the ROI numbers?" is not a pricing question. It's a risk question. We treated it as a pricing objection. It was a trust objection.
Recommendations
  • Quick win: Build a "risk mitigation" talk track for CFO conversations. Phased rollout, success metrics, executive QBR, money-back provisions if applicable.
  • Process change: Require economic buyer identification and engagement before Stage 3 (proposal). Marcus-only deals are single-threaded deals.
  • Strategic question: Should we offer a performance guarantee? FlowStack does. If we keep losing on this, it's a product/packaging issue, not a sales issue.

Recommendations Framework

Every analysis must end with actionable recommendations. Organize by:

Quick Wins (This Week)
  • Messaging changes, talk track updates, battlecard additions
  • Usually addressing a competitive gap or objection pattern
Process Changes (This Month)
  • Qualification criteria updates, stage gate changes, multi-threading requirements
  • Usually addressing sales execution or deal management patterns
Strategic Shifts (This Quarter)
  • ICP refinement, pricing changes, product feedback, competitive positioning
  • Usually addressing product/market or targeting patterns

Output Format

Single Deal Analysis
  1. Deal profile and timeline
  2. Buyer's journey reconstruction (what happened in rooms you weren't in)
  3. The real reason (stated vs. actual)
  4. Key moments that defined the outcome
  5. Lessons learned (specific, not generic)
  6. Recommendations
Batch Analysis
  1. Summary statistics (win rate, average deal size, cycle time)
  2. Loss reason distribution
  3. Competitive landscape
  4. Top 3 patterns with root causes
  5. Win themes to double down on
  6. Prioritized recommendations (quick wins, process changes, strategic shifts)
  • call-debrief — Individual call debriefs are the raw material for win-loss analysis. Better debriefs = better analysis.
  • competitive-intel — Win-loss data feeds competitive battlecards. Losses to specific competitors should update positioning.
  • buyer-persona — Patterns in who you win and lose against should refine your buyer personas.
  • pipeline-review — Win-loss patterns inform what to look for in active deals. "We always lose when X happens" becomes a pipeline review checkpoint.
  • discovery-call — If losses trace back to poor discovery, fix the discovery process.

© TheCraigHewitt, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in sales/win-loss-analysis of TheCraigHewitt/skills.

Open the folder on GitHubat commit fdbf39b

Compare with similar skills

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.

Win Loss Analysis compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Win Loss Analysis this skillTheCraigHewitt/skills157—~5.8kAutomated safety check: PassMIT
Startup Designferdinandobons/startup-skill1.2k—~8.1kAutomated safety check: PassMIT
Competitor Teardownirinabuht12-oss/marketing-skills4k—~1.6kAutomated safety check: PassNone
Competitive Analysisw95/awesome-claude-corporate-skills2391 repos~4kAutomated safety check: PassMIT
Competitor Researcherhanzili/hanzi-browse177—~4.7kAutomated safety check: PassCustom licence
Yao Positioning Skillyaojingang/yao-open-skills1.3k—~805Automated safety check: PassMIT

Similar skills

  • Startup Design

    ferdinandobons/startup-skill

    Design, validate, and plan a startup from scratch. An agent skill from ferdinandobons/startup-skill.

    1.2k GitHub stars~8.1k tokensUpdated 3 mo ago
    Marketing & SEOAuto-check passed
  • Competitor Teardown

    irinabuht12-oss/marketing-skills

    Systematic competitive analysis covering positioning, messaging hierarchy, objection handling, and CTA strategy from landing page URLs or screenshots.

    4k GitHub stars~1.6k tokensUpdated 16 days ago
    Marketing & SEOAuto-check passed
  • Competitive Analysis

    w95/awesome-claude-corporate-skills

    Framework for competitive landscape analysis across any industry.

    239 GitHub starsUsed in 1 repo~4k tokens
    Marketing & SEOAuto-check passed
  • Competitor Researcher

    hanzili/hanzi-browse

    Research SaaS and AI-tool competitors in a real browser. An agent skill from hanzili/hanzi-browse.

    177 GitHub stars~4.7k tokensUpdated 5 mo ago
    Marketing & SEOAuto-check passed
  • Yao Positioning Skill

    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…

    1.3k GitHub stars~805 tokensUpdated 1 mo ago
    Marketing & SEOAuto-check passed
  • Competitor Analysis Local

    gmapsscraper/google-maps-agent-skills

    Analyze local competitors from a Google Maps CSV export. An agent skill from gmapsscraper/google-maps-agent-skills.

    132 GitHub stars~1k tokensUpdated 4 mo ago
    Marketing & SEOAuto-check passed

More from TheCraigHewitt/skills

All 65 skills in this repo
  • Carousels

    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.

    157 GitHub stars~2.3k tokensUpdated 4 mo ago
    Auto-check passed
  • Audience Research

    TheCraigHewitt/skills

    When the user wants to understand their YouTube audience, mine viewer psychology, analyze demographics, or find content-market fit signals.

    157 GitHub stars~2.4k tokensUpdated 4 mo ago
    Auto-check passed
  • Brain Dump

    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.

    157 GitHub stars~1.3k tokensUpdated 4 mo ago
    Auto-check passed
  • Channel Audit

    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.

    157 GitHub stars~2.4k tokensUpdated 4 mo ago
    Auto-check passed
  • Channel Strategy

    TheCraigHewitt/skills

    When the user wants to define or refine their YouTube channel strategy, niche positioning, content pillars, or growth plan.

    157 GitHub stars~2.2k tokensUpdated 4 mo ago
    Auto-check passed
  • Cold Call

    TheCraigHewitt/skills

    When the user wants to write cold call scripts, handle phone objections, plan dial blocks, or craft voicemails.

    157 GitHub stars~5k tokensUpdated 4 mo ago
    Auto-check passed

Categories

Questions about Win Loss Analysis

What does Win Loss Analysis do?

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.

When should I use Win Loss Analysis?

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.

How do I install Win Loss Analysis in Claude Code?

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.

How do I install Win Loss Analysis in Codex?

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.

Can I use Win Loss Analysis in Cursor, Gemini CLI or GitHub Copilot?

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.

What does Win Loss Analysis need to run?

SKILL.md names no scripts, command-line tools or credentials: Win Loss Analysis is instructions for the agent only.

Does Win Loss Analysis access the network?

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.

Is Win Loss Analysis safe to install?

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.

What licence does Win Loss Analysis use?

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.

How many tokens does Win Loss Analysis use?

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.

What are the alternatives to Win Loss Analysis?

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.

Who maintains Win Loss Analysis?

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.