← all publishers

AlexZio00

@alexzio00 source repo

Report this profile Claim this profile

• 40 skills
• 0 followers
• 14 hours ago last updated

1. ▌
   Scope 2 · alexzio00 bundle

   Scope definition before implementation — two modes. Quick mode (default): IN/OUT/exit criteria brief → BRIEF.md. Full mode (/scope full): L0→L4 layered spec chain → spec.md. Trigger: '/scope', '/brief', '/specify', 'scope this', '스펙 잡아줘', '범위 잡아줘', 'spec 만들어', '스펙 만들어', '기획 정리해줘', 'plan this'. Do NOT trigger for: bug fixes, single-file changes, existing spec, brainstorming.
   0 installs
2. ▌
   Setup 2 · alexzio00 bundle

   Claude Code infrastructure + agent team setup — rules, hooks, memory, routing, and agent installation from a guided interview. Combines infrastructure + agent team into one flow. Not project scaffolding (CLAUDE.md/ROADMAP/.gitignore/.env.example) — use project-init for that. Triggers: /setup, setup, harness setup, agent team setup.
   0 installs
3. ▌
   Freeze 2 · alexzio00 bundle

   Scope lock for current task. Declares editable zone — everything outside is frozen (read-only). Call before starting implementation to prevent scope creep.
   0 installs
4. ▌
   Pre Push 2 · alexzio00 bundle

   Mandatory pre-push security and quality pipeline. TRIGGER automatically whenever the user requests any git push: 'push my changes', 'push to origin', 'push this', 'push the code', 'commit and push', 'ship it', 'deploy to remote', 'deploy to prod/staging/production', or any git push command. Blocks hardcoded credentials + prompt-injection/exfiltration markers (14 patterns: AWS/GCP/Azure/LLM keys, private keys, connection strings, platform tokens, merge conflicts, embedded prompt-injection strings, non-standard package sources, Slack webhooks), supply chain risks (9-IOC), MCP tool poisoning (3 patterns), auth bypasses, and OWASP Top 10 vulnerabilities. Do NOT skip unless user says 'skip review' or 'force push'.
   0 installs
5. ▌
   Stepback 2 · alexzio00 bundle

   One-shot perspective reset. Scans current work context, generates 1 abstract reframing question + 3 quick checks (scope drift, side effects, better approach) in under 10 lines. No dialogue, no code, no agents.
   0 installs
6. ▌
   Doc Drift 2 · alexzio00 bundle

   Use this skill when the user wants to audit the memory and documents Claude Code loads into context — CLAUDE.md (user global + project + nested), MEMORY.md, @imports, .claude/skills, .claude/agents, .claude/commands, installed plugins — and detect four kinds of issues: outdated claims, mutually contradictory statements, risky-or-ambiguous wording, and session-only context leaked into skills/agents/commands docs. Produces a prioritized improvement list at `.drift-reports/`. Zero config. Trigger phrases: "doc drift", "memory drift", "memory audit", "context drift", "docs audit", "문서 점검", "문서 감사", "메모리 감사", "메모리 점검", "outdated 문서", "문서 충돌". NOT for: exhaustive content audit of an entire area (→ full-audit) · harness maturity scoring (→ check-harness) · single-file verification (→ verification). doc-drift only covers drift (contradiction/staleness/risky wording/session leakage) in already-loaded context.
   0 installs
7. ▌
   Goal Lock 2 · alexzio00 bundle

   Agent Discipline Engine — lock the goal, run PLAN→DO→VERIFY→FINALIZE→OUTPUT loop, detect success masquerading. Triggers: '/goal-lock', '/goal-lock quick', 'goal lock', 'task harness'.
   0 installs
8. ▌
   Skill Ops 2 · alexzio00 bundle

   Skill ops hub: snapshot/rollback + usage health + invocations.
   0 installs
9. ▌
   Clean Room 2 · alexzio00 bundle

   <!-- provenance: adapted from LilMGenius/paperthin "autobahn" skill (MIT license). Core mechanism (carve -> clean subagent -> verify -> ledger) preserved; reformatted to this repo's SKILL.md conventions, renamed to avoid reusing the original author's skill name verbatim. Upgraded after an adversarial 3-lens design critique (adversarial-user / isolation-integrity / systemic-integration-gap) surfaced gaps the source design didn't cover in a harness with shared filesystem state between the main session and its subagents. Reconciled with upstream autobahn v0.14.0 (RUN's risk-lens fan-out folded into VERIFY step 5(e)'s single independent re-sweep, capped at N=1 rather than open-ended). See CHANGELOG.md. -->
   0 installs
10. ▌
    Full Audit 2 · alexzio00 bundle

    Exhaustive, denominator-driven audit of an entire area (codebase, docs, memory, skills, DB, config). Runs a 6-phase pipeline: scope agreement + prior-map diff -> deterministic sweep (counts/versions/paths/parsing plus cross-index reconciliation) -> parallel read-only content review (citations forced, rule dry-run) -> judgment (false-positive/UNCERTAIN triage) -> fix-vs-addition split, gated by execution mode (AUDIT_ONLY default = read-only, PROPOSE = list only, APPLY_APPROVED = apply approved items only) -> coverage-map recording. A bare 'audit'/'analyze' request defaults to AUDIT_ONLY and never auto-advances to file writes. NOT for single-file or single-question checks (use a regular code review instead) or harness-maturity scoring against a fixed checklist (use a dedicated scoring tool instead). Triggers: '/full-audit', 'audit everything', 'full audit', 'find every gap'.
    0 installs
11. ▌
    Next Action 2 · alexzio00 bundle

    Use when the user wants a next-action recommendation based on current state — reads handoff/git/lessons/STATE and proposes top-3 by impact. Trigger: '/next', 'what should I do next', 'next action'. Proposes only, never executes.
    0 installs
12. ▌
    Code Autopsy 2 · alexzio00 bundle

    🔬 CODE AUTOPSY v7.2
    0 installs
13. ▌
    Collab Audit 2 · alexzio00 bundle

    This skill should be used when the user types /collab-audit or requests AI collaboration diagnosis. Analyzes conversation history, artifacts, and work patterns to generate a 14-section AI Collaboration Audit. Behavioral analysis and feedback are bundled by design — separating them causes users to skip one, defeating the purpose. Saves to ~/.claude/collab-audits/YYYY-MM-DD.md. Compare mode: /collab-audit compare (diffs latest 2 audits). Triggers: '/collab-audit', '/collab-audit compare', 'AI 협업 진단해줘', '협업 진단', '행동 패턴 분석', '나 어떤 사람이야', 'AI collaboration audit', 'work pattern analysis', 'compare audits'. Requires minimum 2 sessions or 100+ messages. Do NOT use self-report surveys — observation-only.
    0 installs
14. ▌
    Project Init 2 · alexzio00 bundle

    Interview-based project setup — generates CLAUDE.md, ROADMAP, .gitignore, .env.example from scratch. Use when: user says '/project-init', 'new project', 'project creation', 'project setup', 'project setup', 'new project', 'create project'. NOT for AI agent/harness configuration (use setup for that). Conversational, one question at a time.
    0 installs
15. ▌
    Project Check 2 · alexzio00 bundle

    Existing project health scan — audits Infrastructure, Security, Quality, and Harness setup. Read-only. Use when: '/project-check', 'project health check', 'project audit', 'what's missing', 'analyze my project', 'check setup'. Ends with /project-init and /setup recommendations. NOT for new projects (use /project-init); project-check = shallow health scan.
    0 installs
16. ▌
    Session Start 2 · alexzio00 bundle

    Load handoff on session start, review lessons, output readiness signal. Triggers: '/session-start', 'start session'. Skip if: first session (no handoff), user requests 'start fresh', or standalone question unrelated to project context.
    0 installs
17. ▌
    Project Overview 2 · alexzio00 bundle

    Use when the user wants a deterministic cross-project status map generated from registered projects' session handoffs. Triggers: '/project-overview', 'project map', 'overall status'. Reads ~/.claude/projects-registry.md (opt-in list), parses each project's memory/session-handoff-LATEST.md state-snapshot v1 block (ts+ctx only), and rewrites the AUTO:START/AUTO:END region of ~/.claude/OVERVIEW.md. Does not touch STATE.md. Does not scan directories automatically.
    0 installs
18. ▌
    Eval Leakage Audit 2 · alexzio00 bundle

    Audits whether a verification (eval/metric/experiment/holdout) actually secures independent external ground truth, or whether the designer, the model, and the scorer are just confirming each other in a circle — via a 21-pattern taxonomy. Read-only. Use before trusting any 'how we'll know it worked' — A/B tests, holdouts, scores, validation — especially when a result feels too clean or self-confirming. 한국어: '이 검증 순환논리 아닌지 봐줘', '이 평가 편파적이야?', '이 벤치마크 셀프체크야?'.
    0 installs
19. ▌
    Integration Intake 2 · alexzio00 bundle

    Gate for deciding whether to adopt an external pattern (skill/agent/rule/plugin/MCP/prompt) into your system. Triggers: '/integration-intake [name]', 'should I integrate this', 'is this worth adopting', or sharing a GitHub repo link and asking what to do with it.
    0 installs
20. ▌
    Session Checkpoint 2 · alexzio00 bundle

    Use when saving session state before context compaction, switching tasks, or ending a session. Runs 5-phase pipeline: context extraction → handoff write → memory save → preservation check → compact guidance.
    0 installs
21. ▌
    Clean Room · alexzio00 bundle

    <!-- provenance: adapted from LilMGenius/paperthin "autobahn" skill (MIT license). Core mechanism (carve -> clean subagent -> verify -> ledger) preserved; reformatted to this repo's SKILL.md conventions, renamed to avoid reusing the original author's skill name verbatim. Upgraded after an adversarial 3-lens design critique (adversarial-user / isolation-integrity / systemic-integration-gap) surfaced gaps the source design didn't cover in a harness with shared filesystem state between the main session and its subagents. Reconciled with upstream autobahn v0.14.0 (RUN's risk-lens fan-out folded into VERIFY step 5(e)'s single independent re-sweep, capped at N=1 rather than open-ended). See CHANGELOG.md. -->
    0 installs
22. ▌
    Code Autopsy · alexzio00 bundle

    🔬 CODE AUTOPSY v7.2
    0 installs
23. ▌
    Project Check · alexzio00 bundle

    Existing project health scan — audits Infrastructure, Security, Quality, and Harness setup. Read-only. Use when: '/project-check', 'project health check', 'project audit', 'what's missing', 'analyze my project', 'check setup'. Ends with /project-init and /setup recommendations. NOT for new projects (use /project-init); project-check = shallow health scan.
    2 installs
24. ▌
    Integration Intake · alexzio00 bundle

    Gate for deciding whether to adopt an external pattern (skill/agent/rule/plugin/MCP/prompt) into your system. Triggers: '/integration-intake [name]', 'should I integrate this', 'is this worth adopting', or sharing a GitHub repo link and asking what to do with it.
    1 install
25. ▌
    Session Checkpoint · alexzio00 bundle

    Use when saving session state before context compaction, switching tasks, or ending a session. Runs 5-phase pipeline: context extraction → handoff write → memory save → preservation check → compact guidance.
    1 install
26. ▌
    Setup · alexzio00 bundle

    Claude Code infrastructure + agent team setup — rules, hooks, memory, routing, and agent installation from a guided interview. Combines infrastructure + agent team into one flow. Not project scaffolding (CLAUDE.md/ROADMAP/.gitignore/.env.example) — use project-init for that. Triggers: /setup, setup, harness setup, agent team setup.
    1 install
27. ▌
    Freeze · alexzio00 bundle

    Scope lock for current task. Declares editable zone — everything outside is frozen (read-only). Call before starting implementation to prevent scope creep.
    1 install
28. ▌
    Pre Push · alexzio00 bundle

    Mandatory pre-push security and quality pipeline. TRIGGER automatically whenever the user requests any git push: 'push my changes', 'push to origin', 'push this', 'push the code', 'commit and push', 'ship it', 'deploy to remote', 'deploy to prod/staging/production', or any git push command. Blocks hardcoded credentials + prompt-injection/exfiltration markers (14 patterns: AWS/GCP/Azure/LLM keys, private keys, connection strings, platform tokens, merge conflicts, embedded prompt-injection strings, non-standard package sources, Slack webhooks), supply chain risks (9-IOC), MCP tool poisoning (3 patterns), auth bypasses, and OWASP Top 10 vulnerabilities. Do NOT skip unless user says 'skip review' or 'force push'.
    1 install
29. ▌
    Stepback · alexzio00 bundle

    One-shot perspective reset. Scans current work context, generates 1 abstract reframing question + 3 quick checks (scope drift, side effects, better approach) in under 10 lines. No dialogue, no code, no agents.
    1 install
30. ▌
    Doc Drift · alexzio00 bundle

    Use this skill when the user wants to audit the memory and documents Claude Code loads into context — CLAUDE.md (user global + project + nested), MEMORY.md, @imports, .claude/skills, .claude/agents, .claude/commands, installed plugins — and detect four kinds of issues: outdated claims, mutually contradictory statements, risky-or-ambiguous wording, and session-only context leaked into skills/agents/commands docs. Produces a prioritized improvement list at `.drift-reports/`. Zero config. Trigger phrases: "doc drift", "memory drift", "memory audit", "context drift", "docs audit", "문서 점검", "문서 감사", "메모리 감사", "메모리 점검", "outdated 문서", "문서 충돌". NOT for: exhaustive content audit of an entire area (→ full-audit) · harness maturity scoring (→ check-harness) · single-file verification (→ verification). doc-drift only covers drift (contradiction/staleness/risky wording/session leakage) in already-loaded context.
    1 install
31. ▌
    Goal Lock · alexzio00 bundle

    Agent Discipline Engine — lock the goal, run PLAN→DO→VERIFY→FINALIZE→OUTPUT loop, detect success masquerading. Triggers: '/goal-lock', '/goal-lock quick', 'goal lock', 'task harness'.
    1 install
32. ▌
    Skill Ops · alexzio00 bundle

    Skill ops hub: snapshot/rollback + usage health + invocations.
    1 install
33. ▌
    Full Audit · alexzio00 bundle

    Exhaustive, denominator-driven audit of an entire area (codebase, docs, memory, skills, DB, config). Runs a 6-phase pipeline: scope agreement + prior-map diff -> deterministic sweep (counts/versions/paths/parsing plus cross-index reconciliation) -> parallel read-only content review (citations forced, rule dry-run) -> judgment (false-positive/UNCERTAIN triage) -> fix-vs-addition split, gated by execution mode (AUDIT_ONLY default = read-only, PROPOSE = list only, APPLY_APPROVED = apply approved items only) -> coverage-map recording. A bare 'audit'/'analyze' request defaults to AUDIT_ONLY and never auto-advances to file writes. NOT for single-file or single-question checks (use a regular code review instead) or harness-maturity scoring against a fixed checklist (use a dedicated scoring tool instead). Triggers: '/full-audit', 'audit everything', 'full audit', 'find every gap'.
    1 install
34. ▌
    Next Action · alexzio00 bundle

    Use when the user wants a next-action recommendation based on current state — reads handoff/git/lessons/STATE and proposes top-3 by impact. Trigger: '/next', 'what should I do next', 'next action'. Proposes only, never executes.
    1 install
35. ▌
    Collab Audit · alexzio00 bundle

    This skill should be used when the user types /collab-audit or requests AI collaboration diagnosis. Analyzes conversation history, artifacts, and work patterns to generate a 14-section AI Collaboration Audit. Behavioral analysis and feedback are bundled by design — separating them causes users to skip one, defeating the purpose. Saves to ~/.claude/collab-audits/YYYY-MM-DD.md. Compare mode: /collab-audit compare (diffs latest 2 audits). Triggers: '/collab-audit', '/collab-audit compare', 'AI 협업 진단해줘', '협업 진단', '행동 패턴 분석', '나 어떤 사람이야', 'AI collaboration audit', 'work pattern analysis', 'compare audits'. Requires minimum 2 sessions or 100+ messages. Do NOT use self-report surveys — observation-only.
    1 install
36. ▌
    Project Init · alexzio00 bundle

    Interview-based project setup — generates CLAUDE.md, ROADMAP, .gitignore, .env.example from scratch. Use when: user says '/project-init', 'new project', 'project creation', 'project setup', 'project setup', 'new project', 'create project'. NOT for AI agent/harness configuration (use setup for that). Conversational, one question at a time.
    1 install
37. ▌
    Session Start · alexzio00 bundle

    Load handoff on session start, review lessons, output readiness signal. Triggers: '/session-start', 'start session'. Skip if: first session (no handoff), user requests 'start fresh', or standalone question unrelated to project context.
    1 install
38. ▌
    Project Overview · alexzio00 bundle

    Use when the user wants a deterministic cross-project status map generated from registered projects' session handoffs. Triggers: '/project-overview', 'project map', 'overall status'. Reads ~/.claude/projects-registry.md (opt-in list), parses each project's memory/session-handoff-LATEST.md state-snapshot v1 block (ts+ctx only), and rewrites the AUTO:START/AUTO:END region of ~/.claude/OVERVIEW.md. Does not touch STATE.md. Does not scan directories automatically.
    1 install
39. ▌
    Eval Leakage Audit · alexzio00 bundle

    Audits whether a verification (eval/metric/experiment/holdout) actually secures independent external ground truth, or whether the designer, the model, and the scorer are just confirming each other in a circle — via a 21-pattern taxonomy. Read-only. Use before trusting any 'how we'll know it worked' — A/B tests, holdouts, scores, validation — especially when a result feels too clean or self-confirming. 한국어: '이 검증 순환논리 아닌지 봐줘', '이 평가 편파적이야?', '이 벤치마크 셀프체크야?'.
    1 install
40. ▌
    Scope · alexzio00 bundle

    Scope definition before implementation — two modes. Quick mode (default): IN/OUT/exit criteria brief → BRIEF.md. Full mode (/scope full): L0→L4 layered spec chain → spec.md. Trigger: '/scope', '/brief', '/specify', 'scope this', '스펙 잡아줘', '범위 잡아줘', 'spec 만들어', '스펙 만들어', '기획 정리해줘', 'plan this'. Do NOT trigger for: bug fixes, single-file changes, existing spec, brainstorming.
    1 install