Blocker Scanner
Classifies deal friction and boosts from call transcripts into a fixed taxonomy
Test report
- Verdict
- Works with setup
- Score
- Tested
- Jul 30, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Jul 30, 2026 · 469a477
⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 30, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.
Ran it on a 24-line sales transcript with ten planted signals plus one decoy about a referral partner's own onboarding paperwork. Answering cold produced seven bullets and swallowed the decoy as deal friction; the skill's taxonomy produced ten typed classifications with quotes and confidence tiers, split the in-house comment into build-vs-buy and internal resistance, caught the budget reallocation as a competing-priority objection, and its noise table explicitly excluded the partner item. The gain is structure and consistency rather than new insight - the cold read found most of the same blockers in prose. The part that cannot be judged here is the half that matters most in production: every step writes SQL into di_raw_signals, di_signal_classifications and di_traceability_log, which needs a Supabase project with the repo's eight-table schema plus a CRM and transcript MCP, none of which exist on a fresh install. Expect to fill every {{PLACEHOLDER}} with your own CRM stage IDs before it runs at all.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 4/5
- Triggers reliably 5/5
- Output vs. baseline 7/10
- Docs & honesty 3/5
What Blocker Scanner does
Reads meeting transcripts, CRM emails and notes for one deal and labels every stall and accelerant with a fixed taxonomy - security review, procurement, legal, pricing, ROI, internal resistance, budget cycle, incumbent and build-vs-buy on the friction side, stakeholder and validation events on the boost side. Each label carries a verbatim quote, a confidence tier and a row written to a Supabase deal-intelligence schema. Triggers on 'what's stalling this deal', 'scan friction for X', or 'run the friction reader'.
How to install Blocker Scanner
Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.
Commands — how to trigger Blocker Scanner
-
/blocker-scannerClassifies deal friction and boosts from call transcripts into a fixed taxonomy
It also activates on plain-language prompts like these:
-
What's stalling the Northwind deal? Scan the call transcript for friction -
Run the friction reader on this CRM transcript and classify every blocker -
Scan friction and boosts for the Acme opportunity from our last sync notes
Frequently asked questions
- Is the Blocker Scanner skill free?
- Yes. The skill itself is free from violetfleming47/deal-intelligence. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Blocker Scanner work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 30, 2026. Verdict: Works with setup. Ran it on a 24-line sales transcript with ten planted signals plus one decoy about a referral partner's own onboarding paperwork. Answering cold produced seven bullets and swallowed the decoy as deal friction; the skill's taxonomy produced ten typed classifications with quotes and confidence tiers, split the in-house comment into build-vs-buy and internal resistance, caught the budget reallocation as a competing-priority objection, and its noise table explicitly excluded the partner item. The gain is structure and consistency rather than new insight - the cold read found most of the same blockers in prose. The part that cannot be judged here is the half that matters most in production: every step writes SQL into di_raw_signals, di_signal_classifications and di_traceability_log, which needs a Supabase project with the repo's eight-table schema plus a CRM and transcript MCP, none of which exist on a fresh install. Expect to fill every {{PLACEHOLDER}} with your own CRM stage IDs before it runs at all.
- What is the Blocker Scanner SkillProof Score?
- 7.6/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 3/5.
- How do I install Blocker Scanner?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Blocker Scanner with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.