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