S40911120
Featured
recensa
Recensa is a self-hosted web viewer that indexes Claude Code session transcripts into a local SQLite database, enabling full-text search, replay, and audit of all past agent conversations without uploading data anywhere.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It operationalizes a powerful conceptual framework—the known/unknown matrix—into concrete, agent-agnostic commands that target the root bottleneck of prompt quality, drawing directly from published essays by an Anthropic team member and supporting multiple coding agents out of the box.
Who it is for
- Developers using Claude Code, OpenAI Codex, Cursor, Kimi K3, or Hermes Agent
- Teams seeking to improve prompt engineering and reduce costly mistakes in code generation
- Individuals already familiar with Thariq Shihipar's 'unknowns' framing who want executable implementations
- AI workflow enthusiasts looking for reusable, community-driven skills
Use cases
- Exploring an unfamiliar codebase or domain using the 'blindspot-pass' skill to surface unknown unknowns
- Designing agent-callable tools that are misuse-resistant via the 'agent-interface-design' skill
- Auditing and pruning outdated or contradictory instructions in CLAUDE.md or skills using 'context-audit'
- Creating a structured implementation plan that highlights decisions most likely to change before building
Strengths
- Provides a clear mapping from the known/unknown matrix to specific, actionable skills for each phase of development
- Supports multiple agents (Claude Code, Codex, Cursor, Kimi K3, Hermes) with minimal configuration via auto-detection or manual install
- Includes three context-level skills that reduce system prompt bloat, inspired by Anthropic's own system prompt reduction results
- Offers both active skill commands and a passive guidance file for users who prefer a standalone methodology
Considerations
- Community project—not an official Anthropic repository, so support and maintenance may vary
- The 'progressive-disclosure' skill's user-invocation-only flag works in Claude Code but is ignored by Codex (verified), potentially increasing context cost in some agents
- Requires users to understand the underlying concept of 'unknowns' to get full value; the README provides minimal explanation beyond the table
README quick start
Finding-Unknowns Skills
11 installable skills that make Claude help you find what you don't know — before it gets expensive to fix.
The map is not the territory. Your prompt is a map; the codebase and the real world are the territory. The gap between them is your unknowns, and with strong models the quality of the work is bottlenecked by how well you clarify them. These skills turn that idea, from Thariq Shihipar's essay A Field Guide to Fable: Finding Your Unknowns, into commands you can run in Claude Code, OpenAI Codex, Kimi Code CLI (Kimi K3), or any agent that reads the agentskills.io SKILL.md format.
Three of them come from his follow-up, The new rules of context engineering for Claude 5 generation models, which works one layer up: not the unknowns in a single prompt, but the ones baked into the context every prompt inherits.
Community project. Distilled, with attribution, from public essays by Thariq Shihipar (Anthropic, Claude Code team). Not an official Anthropic repository.
The idea in one table
| Known | Unknown | |
|---|---|---|
| Known | What's in your prompt | What you know you haven't figured out |
| Unknown | So obvious you'd never write it down, but you'd recognize it on sight | What you haven't considered at all |
Every skill below is a cheap way to move something out of the bottom row before implementation makes it expensive.
The skills
| Skill | Phase | One line |
|---|---|---|
blindspot-pass | Before | Surface your unknown unknowns in an unfamiliar area, then help you prompt better |
brainstorm-prototypes | Before | Throwaway variations you can react to, for taste you can't verbalize |
interview-me | Before | One question at a time, architecture-changing questions first |
reference-hunt | Before | Use working source code as the spec, even across languages |
implementation-plan | Before | A plan that leads with the decisions you're most likely to change |
implementation-notes |
Description
8 installable Claude Code skills for finding your unknowns before they get expensive: blindspot pass, brainstorms, interviews, references, plans, notes, pitches, and a merge quiz. Community distillation, not official Anthropic.
Related repositories
Similar projects matched by category, topics, and programming language.
bjan
Featured
claudemux
Claudemux is a lightweight, dependency-minimal message bus that lets multiple Claude Code sessions communicate in real-time over tmux, enabling one session to ask another a question and receive the answer without manual intervention.
Vincentwei1021
video-shotcraft
An AI agent skill that turns Claude Code or Codex into a motion-design studio for crafting cinematic product videos with Remotion, offering 106 shot recipe cards, 162 styles, 161 motion previews, and a production-ready template.