sales-coaching
Sales coaching and training — onboarding new reps, skill development, role-play practice, coaching programs, certifications, manager coaching cadences, and measuring coaching impact. Use when new reps ramping too slowly, managers not sure how to coach effectively, role-plays feel awkward or unproductive, no structured way to certify reps, coaching efforts not moving pipeline metrics, or struggling to build a coaching culture. Do NOT use for reviewing specific sales call recordings (use /sales-call-review), Seismic-specific platform help (use /sales-seismic), Allego-specific platform help (use /sales-allego), or sales content creation (use /sales-content).
What this skill does
# Sales Coaching & Training
Help the user build coaching programs, onboard new reps, run role-plays, design certification paths, and measure coaching impact. This skill is tool-agnostic and applies to any enablement platform (Seismic Learning, Allego, MindTickle, SalesHood, Brainshark), conversation intelligence tool (Gong, Chorus, Observe.AI), or manual approach.
## Step 1 — Gather context
If `references/learnings.md` exists, read it first for accumulated knowledge.
Ask the user:
1. **What do you need?**
- A) Build a new rep onboarding program
- B) Create a coaching framework for managers
- C) Design role-play/practice exercises
- D) Build certification or skill assessment paths
- E) Improve ramp time for new hires
- F) Measure coaching effectiveness
- G) Other
2. **Team size and structure?**
- A) Small team (<10 reps, player-coach manager)
- B) Mid-size (10-50 reps, dedicated managers)
- C) Large (50-200, enablement team)
- D) Enterprise (200+, enablement org)
3. **Current coaching tools?**
- A) Seismic Learning
- B) Allego
- C) Gong/Chorus (conversation intelligence)
- D) MindTickle
- E) Brainshark
- F) SalesHood
- G) LMS (generic)
- H) Spreadsheets/manual
- I) Nothing formal
4. **Sales methodology?**
- A) MEDDPICC
- B) SPIN
- C) Challenger
- D) Sandler
- E) Value Selling
- F) Custom/none
**If the user's request already provides most of this context, skip directly to the relevant step.** Lead with your best-effort answer using reasonable assumptions (stated explicitly), then ask only the most critical 1-2 clarifying questions at the end — don't gate your response behind gathering complete context.
## Step 2 — Coaching strategy
### Onboarding program design
**30-60-90 day framework:**
**Days 1-30 (Learn):**
- Company/product knowledge (what we sell, who we sell to, how we win)
- Sales process and methodology
- Tool training (CRM, sales engagement, enablement platform)
- Shadow 5+ calls with top performers
- Complete product certification
- **Milestone**: Pass product knowledge assessment (80%+ score)
**Days 31-60 (Practice):**
- Role-play discovery calls, demos, and objection handling
- Make first prospecting calls with manager listening
- Run first demo (manager shadows)
- Complete methodology certification (MEDDPICC, SPIN, etc.)
- **Milestone**: Successfully run a discovery call solo with positive manager feedback
**Days 61-90 (Perform):**
- Own pipeline independently
- Close first deal (or advance first opportunity past discovery)
- Receive weekly 1:1 coaching from manager
- Peer coaching sessions
- **Milestone**: Hit 50%+ of monthly quota
### Manager coaching framework
**Weekly 1:1 coaching structure (30 min):**
1. **Pipeline review** (10 min) — review top 3-5 deals, identify risks, plan next actions
2. **Skill coaching** (15 min) — review one call/meeting, identify one skill to improve, practice
3. **Goal setting** (5 min) — one specific action item for the week
**Coaching models:**
- **GROW**: Goal → Reality → Options → Will — structured coaching conversation
- **SBI**: Situation → Behavior → Impact — for giving feedback
- **Ask-Tell-Ask**: Ask what they think → Share your observation → Ask how they'll apply it
**Monthly coaching cadence:**
| Activity | Frequency | Duration | Purpose |
|---|---|---|---|
| 1:1 coaching | Weekly | 30 min | Pipeline + skill development |
| Call review | Weekly | 15 min | Review 1 recorded call together |
| Role-play | Bi-weekly | 20 min | Practice specific scenarios |
| Skill assessment | Monthly | 30 min | Evaluate progress on skill goals |
| Peer coaching | Monthly | 45 min | Small group practice and feedback |
### Role-play design
- **Structure**: Scenario brief (2 min) → Role-play (5-10 min) → Self-assessment (2 min) → Coach feedback (5 min)
- **Scenarios to cover**: Cold call, Discovery call, Demo, Objection handling (top 5 objections), Negotiation, Executive conversation
- **Scoring**: Use a rubric (1-5 scale) on specific skills: questioning, listening, positioning, handling objections, next steps
- **AI role-play**: Seismic's Role-Play Agent and similar AI tools can simulate buyer conversations for practice without needing a live partner
### Certification paths
- **Product certification**: Knowledge assessment on features, use cases, competitive positioning
- **Methodology certification**: Demonstrate methodology application in role-play scenarios
- **Skill-based certification**: Tiered badges (Bronze/Silver/Gold) for specific skills (discovery, negotiation, etc.)
- **Renewal**: Certifications expire annually — re-certify to ensure skills stay current
## Step 3 — Platform-specific guidance
For platform-specific coaching guidance (Seismic Learning, Allego, Gong/Chorus, MindTickle, SalesHood, Outdoo, Jiminny, Revenue.io, Enthu.AI, Demodesk, Balto, Cresta, Nooks, Orum, NICE CXone, Convin, MaestroQA, QEval, Solidroad, Playvox, SecondBody, Weflow, Winn.ai, Dialpad, Manual/Spreadsheet), see references/platforms.md.
## Step 4 — Measuring coaching impact
| Metric | What it measures | Target |
|---|---|---|
| Ramp time | Days from start to first quota attainment | Reduce by 20%+ |
| Time to first deal | Days from start to first closed-won | <90 days for new AEs |
| Quota attainment by cohort | % of quota hit by onboarding cohort | 70%+ by month 6 |
| Coaching session completion | % of scheduled 1:1s actually held | 90%+ |
| Certification pass rate | % passing on first attempt | 80%+ |
| Skill improvement score | Change in role-play/assessment scores over time | Positive trend |
| Rep retention | Turnover rate for coached vs uncoached reps | Lower for coached |
## Gotchas
- **Don't build an onboarding program without input from recent hires.** Claude tends to create theoretical programs. The best onboarding programs are designed with feedback from reps who completed onboarding in the last 6 months — they know what was missing.
- **Don't conflate coaching with training.** Training teaches knowledge (product, methodology). Coaching develops skills through practice and feedback. A rep who passed product training but can't run a discovery call needs coaching, not more training.
- **Don't skip the manager enablement.** Most coaching programs fail because managers aren't trained to coach. Build a "coaching the coaches" program before rolling out rep coaching at scale.
- **Don't make role-plays optional.** Reps avoid practice because it's uncomfortable. The best teams make role-play a required, scheduled activity — not a suggestion. Bi-weekly minimum.
- **Don't measure coaching by completion metrics alone.** 100% lesson completion doesn't mean reps are ready. Measure coaching impact by performance outcomes (ramp time, quota attainment, deal velocity) not just activity metrics.
- **Self-improving**: If you discover something not covered here, append it to `references/learnings.md` with today's date.
## Before recommending a specific platform skill
This skill covers a strategy domain across many platforms. **Before pointing the user to any specific platform skill** (any `/sales-{platform}` listed in `## Related skills`, e.g., `/sales-mailshake`, `/sales-klaviyo`, `/sales-apollo`), read that platform skill's actual `SKILL.md` first. The 1-line description in `## Related skills` is enough to *identify* a candidate — it's not enough to *commit* to it or to write a prompt that invokes it well.
**How to read it:**
- If `~/.claude/skills/{skill-name}/SKILL.md` exists locally, `Read` it.
- For `sales-*` skills, `WebFetch` directly from this repo: `https://raw.githubusercontent.com/sales-skills/sales/main/skills/{skill-name}/SKILL.md` — e.g., for `sales-mailshake`: `https://raw.githubusercontent.com/sales-skills/sales/main/skills/sales-mailshake/SKILL.md`.
- For non-`sales-*` skills (third-party), look up `{org}/{repo}` in `~/.claude/skills/sales-do/references/skill-sources.md` if installed and fetch the same `skills/{sRelated in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.