Blind Spot
Use BEFORE starting work on a task to surface the unknown-unknowns you're about to walk into but can't see. Dispatches a fresh-context Claude subagent that hunts what you don't know you don't know about the codebase, the domain, and the decisions ahead, calibrated to your stated experience, then reports ranked, evidence-backed findings and fixes nothing. Triggers on: blind spot pass, blindspot, unknown unknowns, what don't I know, what am I missing, help me prompt better, I know nothing about, teach me my unknowns, before I start, de-risk this task, surface my blind spots.
Install
/plugin marketplace add adelrioj/claude-skillsThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add adelrioj/claude-skills --skill blind-spotgit clone --depth 1 https://github.com/adelrioj/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/skills/blind-spot ~/.claude/skills/blind-spotPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Blind-Spot Pass — Adversarial Unknown-Unknowns Discovery A **pre-implementation pass that surfaces the unknown-unknowns of a task you're about to start** — what you don't know you don't know about this codebase, this domain, and the decisions ahead — so you can prompt from the territory instead of a partial map. this is a **finder, not a fixer** — it reports ranked, evidence-backed findings and **edits nothing, plans nothing, starts no work**. You fold the briefing into your next prompt, `/brainstorming`, or `/writing-plans`. **Why a fresh subagent (the adversarial mechanism).** The main loop absorbs your framing of the task and inherits your blind spots — the same gap that makes an unknown *unknown* to you also biases a self-review that shares your context. A fresh `Agent` subagent, given only the task + the codebase + your stated experience, re-derives "what's surprising here?" without that inherited framing. Payoff: a Claude subagent, **no external CLI dependency**, installs anywhere. **Why report-only.** The intent is diagnostic — surface what you can't see so *you* decide how to re-scope. Report-only keeps the skill small (no fix / interview / convergence loop) and composable. --- ## Flow ### Step 0 — Preflight & scope 1. **No task described?** If the invocation names no forthcoming task, ask the one blocking question and stop until answered — do not guess: > "What are you about to work on? Tell me the task, and (optionally) how familiar you
Details
- Skill name
blind-spot- Repository
- adelrioj/claude-skills
- Path
skills/blind-spot/SKILL.md- Repo updated
- 24 August 2026
FAQ
What does the Blind Spot skill do?
Use BEFORE starting work on a task to surface the unknown-unknowns you're about to walk into but can't see. Dispatches a fresh-context Claude subagent that hunts what you don't know you don't know about the codebase, the domain, and the decisions ahead, calibrated to your stated experience, then reports ranked, evidence-backed findings and fixes nothing. Triggers on: blind spot pass, blindspot, unknown unknowns, what don't I know, what am I missing, help me prompt better, I know nothing about, teach me my unknowns, before I start, de-risk this task, surface my blind spots.
How do I install the Blind Spot skill?
Claude Code plugin: /plugin marketplace add adelrioj/claude-skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Blind Spot popular?
It lives in adelrioj/claude-skills, which has 5 GitHub stars and 0 forks.
Related skills
Architect Review PR
5adelrioj/claude-skills
Use after a feature is built — e.g. the final step of a ship-it run, right after review-pr — to check it is actually complete and wired, not just line-correct. Dispatches a fresh-context Claude subagent that traces the whole repo to hunt completeness and integration gaps in the branch's changes, reports ranked, evidence-backed findings, then fixes the CRITICAL ones and verifies with a fresh re-review (capped at 3 passes; pass report-only to skip fixing). Triggers on: architect review, architecture review, completeness review, wiring review, is this wired, did we finish this, find the gaps, inc
Claude Md Slim
5adelrioj/claude-skills
Use when CLAUDE.md has grown bloated and is taxing every session's context — the inverse of claude-md-improver. Triages each block into session-invariant rules (stay always-on) vs feature/subsystem detail (page out to docs/ behind a plain-path pointer), moving — never deleting — the detail so nothing is lost and the always-on token bill drops. Triggers on: slim claude.md, minimal claude.md, claude.md is bloated, shrink claude.md, split claude.md, make claude.md minimal, page out claude.md, claude.md too long, reduce project memory, point claude.md to docs, trim claude md.
Linear Groom Ticket
5adelrioj/claude-skills
Use when a Linear ticket needs to be made ready to work on, or judged not worth working on. Analyses one ticket across four dimensions — whether its claims hold in the code, whether it is complete against the team template, whether it duplicates another ticket, and whether it is implementable — then proposes a corrected description and applies it to Linear only after you approve. Triggers on: groom this ticket, prepare NBS-123, is this ticket ready, revisa este ticket, ¿este ticket está listo?, deja el ticket listo para trabajar, candidato a borrar, dedupe this ticket.
Watch Release
9flurdy/agent-skills
Start a recurring release-gatekeeper loop — runs /release-manager on an adaptive cadence (fast when something is in flight, backing off when settled) until end of day. Prompts to push / defer / cancel as services become ready; runs attended.
Agent Discoverability
9sandbaseai/workbuddy-skill
Use when publishing or auditing an MCP or agent endpoint so third-party agents can find it, understand its capabilities, and complete its authorized authentication flow.
Tidy Settings
9flurdy/agent-skills
Sort, dedupe, and audit Claude settings.json / settings.local.json at user/project level. Flags risky permissions, broken references, glob-subsumed entries, and cross-file duplicates. Mechanical fixes auto-apply; judgment calls become triage items.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.