haru0416-dev/quaere

Process-correction skills that make coding agents ask before they act.

5Stars on the repository
9Mods indexed here, across every type
1mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

quaere-evidence

01

haru0416-dev/quaere

Skill Claude CodeCodex

This skill should be used whenever the user asks to investigate unclear bugs, defend or reject PR review comments, triage CI failures or flaky tests, review risky/security/database/concurrency/external-API changes or multi-file refactors, or make any claim that needs evidence before patching. It enforces a falsifiable…

5 1mo ago A 98 tokens original MIT

quaere-execution

02

haru0416-dev/quaere

Skill Claude CodeCodex

This skill should be used whenever the user authorizes multi-step coding implementation: applying a plan, finishing a feature, implementing review feedback, writing tests, making a refactor, fixing a bug whose cause is already confirmed, or turning a specification into working code. It enforces a Plan → Do → Study →…

5 1mo ago A 130 tokens original MIT

quaere-grounding

03

haru0416-dev/quaere

Skill Claude CodeCodex

This skill should be used whenever implementation or review depends on external, version-sensitive facts: libraries, SDKs, APIs, CLIs, cloud services, security advisories, changelogs, release notes, or documentation that may have changed. The skill anchors local versions, ranks source quality, runs an executable probe…

5 1mo ago A 144 tokens original MIT

quaere-semantic

04

haru0416-dev/quaere

Skill Claude CodeCodex

A code-understanding workflow that analyses the meaning of individual symbols—such as functions, classes, and variables—before explaining or changing existing code.

5 1mo ago A 113 tokens original MIT

quaere-audit

05

haru0416-dev/quaere

Skill Claude CodeCodex

This skill should be used whenever the user asks for a serious security audit, vulnerability review, bug bounty triage, threat-model-driven code review, protocol/spec conformance audit, auth/authz or tenant-isolation review, exploitability analysis, CVE/advisory impact assessment, or security-sensitive PR review when…

5 1mo ago A 146 tokens original MIT

quaere-crucible

06

haru0416-dev/quaere

Skill Claude CodeCodex

A review method that challenges the important claims in a plan, design, decision, or explanation before you commit to it.

5 1mo ago A 222 tokens original MIT

quaere-invention

07

haru0416-dev/quaere

Skill Claude CodeCodex

An idea-development method that checks whether a proposed approach is genuinely different from the usual answer and how it could fail.

5 1mo ago A 163 tokens original MIT

quaere-naming

08

haru0416-dev/quaere

Skill Claude CodeCodex

This skill should be used whenever the user needs to name a product, SaaS tool, brand, library, open source project, CLI, bot, or app, or asks to rename or rebrand a product or project, find a brand name, pick a product name, or escape generic AI-slop names. It enforces a metaphor-driven process that establishes a…

5 1mo ago A 178 tokens original MIT

quaere-prospect

09

haru0416-dev/quaere

Skill Claude CodeCodex

A set of rules for finding worthwhile things to build next in a codebase or product. It requires a confirmed gap, an affected user, evidence of demand, and a small test before recommending work.

5 1mo ago A 202 tokens original MIT