skills/email-draft-polish/SKILL.md
Use when reviewing a generated cold email draft, polishing email copy before sending, checking an email against brand guidelines, auditing email quality, or validating that an email meets formatting and content rules. Also triggered by: 'review this email,' 'check this draft,' 'polish this email,' 'QA these emails,' 'audit email quality.' NEVER for writing emails from scratch, general copywriting tasks, or non-cold-email correspondence.
npx skillsauth add sharkitect-solutions/sharkitect-claude-toolkit email-draft-polishInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
| File | Purpose | Required |
|------|---------|----------|
| brand/Lead Gen Email Agent Brief.md | Complete ruleset -- authoritative source | YES -- load before reviewing |
| brand/templates/[niche].md | Niche-specific pain points, terminology, golden examples | YES -- load matching niche |
If brand brief is missing: Stop and ask the user to provide it. Do not proceed without it. Every rule in this skill is derived from that document -- QA without it is guesswork.
These are the excuses Claude (or the user) might use to skip a thorough QA pass. None of them are valid.
| Rationalization | Why It Fails | |----------------|-------------| | "The email looks good enough" | "Good enough" sends the wrong impression to cold prospects. One AI tell-tale tanks deliverability and reply rates. | | "This is just a follow-up, less scrutiny needed" | Follow-ups have their own specific structural requirements. FU2 and FU3 especially require trust signals that are easy to miss. | | "The user already approved the template" | Approving a template structure is not approving a specific draft. Each draft requires its own pass. | | "It's close enough to the brand voice" | "Close enough" accumulates. A slightly salesy tone plus a slightly formal opener plus one marketing buzzword = an email that reads as AI-generated. | | "The checklist doesn't apply to this niche" | The checklist applies to all niches. Niche-specific items are additive, not replacements. | | "The user said they just want light polish" | Light polish still requires flagging hard rule violations. Mention all failures; let the user decide what to fix. | | "This email already performed well before" | Past performance on a different draft in a different niche with a different prospect is not a pass on this one. |
Step 1 -- Identify the email type: Confirm: initial, FU1, FU2, FU3, or FU4. This determines which sections of the checklist apply.
Step 2 -- Load the brand brief:
Read brand/Lead Gen Email Agent Brief.md. This is the authoritative source. When in doubt, the brief wins.
Step 3 -- Load the niche template:
Read brand/templates/[niche].md for niche-specific context (industry pain points, terminology, golden examples).
{{CTA}}), no opt-out language (except FU4)Target voice equation: 40% Confident Expert + 25% Friendly Neighbor + 20% Straight Shooter + 15% Curious Diagnostician.
FU1 (Education):
FU2 (Trust/Proof):
FU3 (Objection-Buster):
FU4 (Clean Breakup):
Observable patterns that indicate this skill is being violated or the email has a serious problem.
These patterns immediately signal "AI wrote this" -- flag and rewrite:
When an email fails any check:
Present revisions as before/after pairs so the change is clear.
development
When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ad copy,' 'ad creative,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' or 'audience targeting.' This skill covers campaign strategy, ad creation, audience targeting, and optimization.
testing
--- name: using-sharkitect-methodology description: Use when starting any conversation in a Sharkitect workspace OR before any task involving NEW pricing, positioning, proposal, strategy, plan-execution, or schema-design work — mandates invocation of Sharkitect-specific methodology skills (pricing-strategy, marketing-strategy-pmm, smb-cfo, hq-revenue-ops, executing-plans, brainstorming) under the same anti-rationalization discipline as using-superpowers. Documentation has failed 4 times across H
testing
Use when user says 'end session', 'wrap up', 'stop for the day', 'done for today', 'close out', 'save session', 'wrapping up', or invokes /end-session. Runs the full 9-step end-of-session protocol: resource audit, MEMORY.md update, lessons capture, plan status, pending items, workspace checklist, .tmp/ audit, git commit+push, Supabase brain sync, session brief, summary. Final step schedules a detached self-kill of the current session ONLY (3s delay) so the window closes cleanly. Other claude.exe processes (active workspaces) are NOT touched -- orphan cleanup is handled separately by Claude-Orphan-Cleanup-Hourly with proper age safeguards. Do NOT use for: mid-session quick saves (use session-checkpoint), skill syncing (use sync-skills.py), brain memory queries (use supabase-sync.py pull), document freshness reviews (use document-lifecycle), resource gap detection (use resource-auditor).
testing
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, passive voice, negative parallelisms, and filler phrases.