Skip to main content
XHXIAIEIN
Profil créateur GitHub

XHXIAIEIN

Vue par dépôt de 36 skills collectés dans 7 dépôts GitHub.

skills collectés
36
dépôts
7
mis à jour
6 sept. 2026
explorateur de dépôts

Dépôts et skills représentatifs

verification-check
Analystes en assurance qualité des logiciels et testeurs

Evidence-gated completion check. Use before committing, creating PRs, or claiming work is done. Pairs with verification-spec at task start.

29 avr. 2026
steal
Analystes en sécurité de l'information

Systematic knowledge extraction from open-source projects. Use when: user shares a repo/link to study, says 偷师/steal/学习/研究, or wants to analyze another project's patterns for adoption.

28 avr. 2026
claude-at
Développeurs de logiciels

Launch a real interactive claude CLI session in a target directory (typically a worktree) with a pre-seeded prompt. Use when the current session cannot absorb the task context — e.g., N parallel worktree jobs that would blow the context window, or when you…

27 avr. 2026
fuzzy-read
Développeurs de logiciels

FileNotFound recovery protocol. Before reporting a missing-file error, suggest near-misses by basename similarity (difflib threshold 0.4) so typos and stale paths fail loudly with actionable hints.

26 avr. 2026
paste-ref
Développeurs de logiciels

Paste-by-reference guard for Edit calls. When new_string would echo >30 lines of existing file content, use {{file:path:start:end}} reference instead and expand before submission.

26 avr. 2026
subagent-io
Développeurs de logiciels

File-IO protocol for parent ↔ subagent communication. Parent writes input.txt + context.json, subagent appends to output.txt with [ROUND END] sentinels. Used with Monitor tool for live observation.

26 avr. 2026
memory-axioms
Analystes en sécurité de l'information

Memory write gate enforcing four axioms (Action-Verified / Sanctity / No Volatile / Minimum Pointer). Triggered before any write to SOUL/, .claude/memory/, or memory storage.

26 avr. 2026
verification-spec
Analystes des systèmes informatiques

Use at task start, before the first write or destructive command, when the owner hands over a code, build, test, deploy, or UI request. Forces upfront success criteria, the proof command, and the working assumptions.

26 avr. 2026
Affichage de 8 skills collectés sur 28.
7 dépôts affichés sur 7
Tous les dépôts sont affichés