القائمة
apply documentation philosophy — explain why, not what. use for jsdocs, READMEs, inline comments.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
| name | document |
| description | apply documentation philosophy — explain why, not what. use for jsdocs, READMEs, inline comments. |
apply documentation philosophy: explain why, not what.
delete this:
/** context provider that wraps children in a DisclosureProvider. */
keep this:
/**
* blocks CompositeContext so nested Lists create isolated focus loops.
* essential for "Simple API" goal — our List is "greedy" and would
* otherwise join parent's arrow-key navigation.
*/
/**
* one-line description of purpose or behavior.
*
* additional context if design rationale is complex (keep brief).
*
* @prop propName - what it does
* @example
* ```tsx
* <Component>content</Component>
* ```
*/
preserve @bdsqqq notes or similar when they explain non-obvious decisions:
/**
* @bdsqqq notes: alpha colors avoided for strokes due to compounding
* overlap issues at intersection points.
*/
jsdocs are source of truth. upon finishing a task, colocate valuable context as jsdocs — only notes that explain non-obvious why. delete everything else.
record context that would help in future sessions. use after learning something, discovering a gotcha, or making a decision worth preserving. test: would a future agent starting fresh benefit from knowing this?
git workflows for agents: ship (stage → commit → push), hunks (selective staging). never force push, never git add -A, conventional commits. triggers on: commit, push, stage, ship, git add, hunks, selective staging.
systematic investigation and debugging methodology. hypothesis-driven analysis with verification agents. use for incident response, codebase archaeology, dependency mapping, root cause analysis, or any investigation requiring verified findings.
write in amp's voice — direct, technical, opinionated, honest. use for technical writing that should feel authoritative without being academic. derived from analysis of amp's content patterns.
epistemic standards for evaluation and analysis. load before reviewing code, debugging, reporting findings, or any task where claims must be defensible. enforces trace-or-delete, confidence labeling, falsification.
prose style guide. use when your output includes ANYTHING other than a code snippet. use during conversation, and every time you write to a file, commit, PR. enforces academish voice: supported claims, precise language, no hyperbole. user tone: lowercase, terse, anti-sycophancy.