unknowns-blindspot-pass
Skill2 starsChanged 4 months agoMITView on GitHub
Surface unknown unknowns before touching unfamiliar code or systems. Use when the user asks for a blindspot pass, "what am I missing", hidden traps, implementation risks, prompt hardening, or wants Codex to inspect a module/repo area before writing code.
In this repository11 other files it gives its agents.
- know-your-unknownsSkill
- unknowns-buy-in-docSkill
- unknowns-design-directionsSkill
- unknowns-domain-bootstrapSkill
- unknowns-implementation-notesSkill
- unknowns-intervention-brainstormSkill
- unknowns-merge-quizSkill
- unknowns-mock-before-wireSkill
- unknowns-reference-mapSkill
- unknowns-spec-interviewSkill
- unknowns-tweakable-planSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 18
Stop condition: implementation should not start until the user accepts or edits the hardened prompt.
- Distinctive: line 22
Do not invent architecture.
- Distinctive: line 24
If an HTML artifact would help, use a card layout with copyable prompt chips and a final copyable implementation prompt.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Unknowns Blindspot Pass
Workflow
Inspect before proposing implementation. Gather evidence from code, tests, docs, config, migrations, feature flags, TODOs, recent history, and local conventions.
Return:
- Original ask and the code/system territory being entered.
- 5-9 blindspot cards.
- For each card: evidence, why it bites, what a naive agent would miss, and a prompt fix.
- A final hardened prompt that folds every important constraint into the user's next request.
- Stop condition: implementation should not start until the user accepts or edits the hardened prompt.
Rules
Do not invent architecture. Mark unsupported concerns as hypotheses and list the evidence needed. Prefer concrete file paths, symbols, tests, and config names over general warnings.
If an HTML artifact would help, use a card layout with copyable prompt chips and a final copyable implementation prompt.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.