Agent SkillsAjayIrkal23/agentic-mercy-10x › code-execution-standard

code-execution-standard

GitHub

用于在范围和根因已明确时执行安全代码变更的标准化实现模板。根据后端、前端或跨层表面选择加载对应的核心合规技能集,利用工具进行依赖分析与精确验证,确保变更的安全性与规范性。

skills/code-execution-standard/SKILL.md AjayIrkal23/agentic-mercy-10x

Trigger Scenarios

代码范围已知且设计清晰 需要实施已知范围的安全变更并验证

Install

npx skills add AjayIrkal23/agentic-mercy-10x --skill code-execution-standard -g -y
More Options

Use without installing

npx skills use AjayIrkal23/agentic-mercy-10x@code-execution-standard

指定 Agent (Claude Code)

npx skills add AjayIrkal23/agentic-mercy-10x --skill code-execution-standard -a claude-code -g -y

安装 repo 全部 skill

npx skills add AjayIrkal23/agentic-mercy-10x --all -g -y

预览 repo 内 skill

npx skills add AjayIrkal23/agentic-mercy-10x --list

SKILL.md

Frontmatter
{
    "name": "code-execution-standard",
    "schema": 1,
    "category": "general",
    "surfaces": [
        "general"
    ],
    "triggers": {
        "paths": [],
        "intents": [
            "general"
        ],
        "keywords": [
            "already",
            "amount",
            "big",
            "cause",
            "change",
            "changes",
            "code",
            "delivers",
            "execution",
            "feature",
            "feels",
            "file",
            "implement",
            "implementing",
            "incrementally",
            "known-scope",
            "land",
            "large",
            "once",
            "root",
            "safe",
            "safely",
            "scope",
            "standard",
            "step",
            "task",
            "too",
            "touches",
            "understood",
            "validated",
            "validation",
            "write"
        ]
    },
    "platforms": [
        "linux",
        "darwin",
        "windows"
    ],
    "token-cost": 1040,
    "description": "Use when scope and root cause are already understood and the task is implementing a safe, validated, known-scope change.",
    "disable-model-invocation": false
}

Code Execution Standard

Overview

This is the implementation shell.

It does not carry frontend and backend standards by default. It selects the touched surfaces first, then loads only the matching baseline skills and specialists. Use this shell for implementation work in default chat as well as explicit code-mode execution. Do not wait for architect or plan wording before activating it.

Use When

  • The scope is known.
  • The design is already clear enough to implement.
  • The job is to make a safe change and verify it.

Do Not Use

  • Architecture-first work.
  • Unknown failures that need root-cause analysis first.
  • Documentation lookup by itself.

Surface Selection Rule

Choose the touched surface first:

If the prompt is asking for a code change, treat it as implementation and activate this shell before editing, even when the prompt does not explicitly mention mode selection.

  • Backend-only: load the mandatory Backend Core Compliance Set before editing: backend-standards-always-follow, service-layer-standards, backend-api-standards, backend-error-handling, and backend-performance-standards. Preserve api-contract-standards for envelope/contract work, domain-scaffold-patterns for new domain/feature skeleton planning, and scaffold-standards for concrete backend skeleton details.
  • Frontend-only: select and load the matching Build Web Apps plugin skill when available, then load the mandatory Frontend Core Compliance Set: build-web-apps:frontend-app-builder for new/redesign/visual surfaces or build-web-apps:react-best-practices for React/Vite/UI/code work, plus frontend-standards-always-follow, frontend-structure-standards, frontend-response-handling, frontend-server-data-patterns, frontend-api-standards, and react-hooks-patterns.
  • Cross-surface: load the matching Build Web Apps plugin plus Frontend Core Compliance Set and Backend Core Compliance Set, then only the preserved add-ons required by the actual files and contracts being changed.

Use project-reference-linkage for linked modules and shared contracts. Use mcp-usage-standards when external verification or repo-system truth must guide the implementation. Use dead-code-and-change-audit for every coding task and every code change. When the repo is indexed, use jcodemunch first for broad path discovery, symbol search, reference tracing, dependency graphs, context bundles, and blast-radius checks. Use shell/file tools immediately for exact paths, literal text, dirty or untracked files, generated or ignored files, stale or ambiguous indexes, small known scopes, direct verification reads, and command execution.

Workflow

  1. Confirm the touched surfaces and impacted layers, preferring jcodemunch for indexed broad repo discovery and shell/file tools for exact or verification lookups.
  2. Load the matching Build Web Apps plugin for frontend surfaces, the Frontend Core Compliance Set for frontend work, and the Backend Core Compliance Set for backend/server work.
  3. Add dead-code-and-change-audit for code changes and only the other specialists required by the actual change.
  4. Implement the smallest complete change that satisfies the request.
  5. Verify tests, contracts, stale references, and user-visible behavior before closing.

Non-Negotiables

  • No guessing when the repo already shows a pattern.
  • No unnecessary new abstractions.
  • No contract drift without intent.
  • No touched manually maintained source file may remain over 250 lines without an explicit blocker; split frontend/backend files according to the active surface standards before adding more behavior.
  • No completion claims without verification.

Output Contract

  • Completed code changes or a blocked-path explanation.
  • Touched surfaces and loaded standards.
  • Validation results and known gaps.
  • Assumptions that affected implementation.

References

  • Use references/full-guide.md if you need the previous full strict guide.
  • Use workflow-overlay-optimizer when persistent routing friction or missing implementation-skill activation must be corrected across sessions instead of patched ad hoc per prompt.

Version History

  • 581d130 Current 2026-07-19 09:05

Same Skill Collection

attic/2026-07-09/skills-pre-update/taste-skill/SKILL.md
attic/2026-07-09/skills-pre-update/ui-ux-pro-max/SKILL.md
skills/agent-development/SKILL.md
skills/api-and-interface-design/SKILL.md
skills/api-contract-standards/SKILL.md
skills/architect-system-design/SKILL.md
skills/backend-api-standards/SKILL.md
skills/backend-code-review/SKILL.md
skills/backend-error-handling/SKILL.md
skills/backend-performance-standards/SKILL.md
skills/backend-standards-always-follow/SKILL.md
skills/canary-playwright/SKILL.md
skills/caveman/SKILL.md
skills/ci-cd-and-automation/SKILL.md
skills/code-review-and-quality/SKILL.md
skills/code-simplification/SKILL.md
skills/codebase-design/SKILL.md
skills/codebase-start-point-guide/SKILL.md
skills/command-development/SKILL.md
skills/composition-patterns/SKILL.md
skills/context-engineering/SKILL.md
skills/dead-code-and-change-audit/SKILL.md
skills/debug-investigation/SKILL.md
skills/debugging-and-error-recovery/SKILL.md
skills/deprecation-and-migration/SKILL.md
skills/design-extract/SKILL.md
skills/design-review-playwright/SKILL.md
skills/diagnose/SKILL.md
skills/documentation-and-adrs/SKILL.md
skills/domain-modeling/SKILL.md
skills/domain-scaffold-patterns/SKILL.md
skills/doubt-driven-development/SKILL.md
skills/dox-doc-tree/SKILL.md
skills/eval-harness/SKILL.md
skills/fix-lint-format/SKILL.md
skills/forensic-change-coupling/SKILL.md
skills/forensic-complexity-trends/SKILL.md
skills/forensic-debt-quantification/SKILL.md
skills/forensic-hotspot-finder/SKILL.md
skills/frontend-api-standards/SKILL.md
skills/frontend-code-review/SKILL.md
skills/frontend-response-handling/SKILL.md
skills/frontend-server-data-patterns/SKILL.md
skills/frontend-standards-always-follow/SKILL.md
skills/frontend-structure-standards/SKILL.md
skills/frontend-ui-engineering/SKILL.md
skills/git-workflow-and-versioning/SKILL.md
skills/golang-patterns/SKILL.md
skills/golang-testing/SKILL.md
skills/graphify/SKILL.md
skills/gsd-add-tests/SKILL.md
skills/gsd-ai-integration-phase/SKILL.md
skills/gsd-audit-fix/SKILL.md
skills/gsd-audit-milestone/SKILL.md
skills/gsd-audit-uat/SKILL.md
skills/gsd-autonomous/SKILL.md
skills/gsd-capture/SKILL.md
skills/gsd-cleanup/SKILL.md
skills/gsd-code-review/SKILL.md
skills/gsd-complete-milestone/SKILL.md
skills/gsd-config/SKILL.md
skills/gsd-debug/SKILL.md
skills/gsd-discuss-phase/SKILL.md
skills/gsd-docs-update/SKILL.md
skills/gsd-eval-review/SKILL.md
skills/gsd-execute-phase/SKILL.md
skills/gsd-explore/SKILL.md
skills/gsd-extract-learnings/SKILL.md
skills/gsd-fast/SKILL.md
skills/gsd-forensics/SKILL.md
skills/gsd-graphify/SKILL.md
skills/gsd-health/SKILL.md
skills/gsd-import/SKILL.md
skills/gsd-inbox/SKILL.md
skills/gsd-ingest-docs/SKILL.md
skills/gsd-manager/SKILL.md
skills/gsd-map-codebase/SKILL.md
skills/gsd-milestone-summary/SKILL.md
skills/gsd-mvp-phase/SKILL.md
skills/gsd-new-milestone/SKILL.md
skills/gsd-new-project/SKILL.md
skills/gsd-ns-context/SKILL.md
skills/gsd-ns-ideate/SKILL.md
skills/gsd-ns-manage/SKILL.md
skills/gsd-ns-review/SKILL.md
skills/gsd-ns-workflow/SKILL.md
skills/gsd-pause-work/SKILL.md
skills/gsd-phase/SKILL.md
skills/gsd-plan-phase/SKILL.md
skills/gsd-plan-review-convergence/SKILL.md
skills/gsd-pr-branch/SKILL.md
skills/gsd-profile-user/SKILL.md
skills/gsd-progress/SKILL.md
skills/gsd-quick/SKILL.md
skills/gsd-resume-work/SKILL.md
skills/gsd-review-backlog/SKILL.md
skills/gsd-review/SKILL.md
skills/gsd-secure-phase/SKILL.md
skills/gsd-ship/SKILL.md
skills/gsd-sketch/SKILL.md
skills/gsd-spec-phase/SKILL.md
skills/gsd-spike/SKILL.md
skills/gsd-stats/SKILL.md
skills/gsd-surface/SKILL.md
skills/gsd-thread/SKILL.md
skills/gsd-ui-phase/SKILL.md
skills/gsd-ui-review/SKILL.md
skills/gsd-ultraplan-phase/SKILL.md
skills/gsd-undo/SKILL.md
skills/gsd-update/SKILL.md
skills/gsd-validate-phase/SKILL.md
skills/gsd-verify-work/SKILL.md
skills/gsd-workspace/SKILL.md
skills/gsd-workstreams/SKILL.md
skills/huashu-design/SKILL.md
skills/improve-codebase-architecture/SKILL.md
skills/incremental-implementation/SKILL.md
skills/iterative-retrieval/SKILL.md
skills/lean-ctx/SKILL.md
skills/mcp-builder/SKILL.md
skills/mcp-usage-standards/SKILL.md
skills/mmx-cli/SKILL.md
skills/owasp-security/SKILL.md
skills/pdf/SKILL.md
skills/performance-optimization/SKILL.md
skills/plan-exec-stack-guide/SKILL.md
skills/plan-mode-gate/SKILL.md
skills/planning-and-task-breakdown/SKILL.md
skills/postgres-patterns/SKILL.md
skills/project-reference-linkage/SKILL.md
skills/project-structure-map/SKILL.md
skills/qa-playwright/SKILL.md
skills/react-hooks-patterns/SKILL.md
skills/resolving-merge-conflicts/SKILL.md
skills/santa-review/SKILL.md
skills/scaffold-standards/SKILL.md
skills/security-and-hardening/SKILL.md
skills/service-layer-standards/SKILL.md
skills/shadcn/SKILL.md
skills/shipping-and-launch/SKILL.md
skills/skill-linkage-story/SKILL.md
skills/source-driven-development/SKILL.md
skills/spec-driven-development/SKILL.md
skills/strategic-compact/SKILL.md
skills/tailwind-design-system/SKILL.md
skills/taste-skill/SKILL.md
skills/tdd/SKILL.md
skills/tech-debt-audit/SKILL.md
skills/test-driven-development/SKILL.md
skills/tool-and-doc-selection/SKILL.md
skills/using-agent-skills/SKILL.md
skills/verification-loop/SKILL.md
skills/vite-react-best-practices/SKILL.md
skills/web-design-guidelines/SKILL.md
skills/webapp-testing/SKILL.md
skills/workflow-orchestrator/SKILL.md
skills/zoom-out/SKILL.md
attic/2026-07-09/skills-pre-update/huashu-design/SKILL.md
attic/2026-07-09/skills-pre-update/impeccable/SKILL.md
skills/browser-testing-with-devtools/SKILL.md
skills/codebase-intel-first/SKILL.md
skills/docx/SKILL.md
skills/find-skills/SKILL.md
skills/gsd-help/SKILL.md
skills/gsd-ns-project/SKILL.md
skills/gsd-settings/SKILL.md
skills/higgsfield-generate/SKILL.md
skills/higgsfield-marketplace-cards/SKILL.md
skills/higgsfield-product-photoshoot/SKILL.md
skills/higgsfield-soul-id/SKILL.md
skills/higgsfield-websites/SKILL.md
skills/impeccable/SKILL.md
skills/jcodemunch-token-saver/SKILL.md
skills/pptx/SKILL.md
skills/tdd-auto-init/SKILL.md
skills/ui-ux-pro-max/SKILL.md
skills/update-docs/SKILL.md
skills/xlsx/SKILL.md
skills/autoplan/SKILL.md
skills/benchmark/SKILL.md
skills/browse/SKILL.md
skills/careful/SKILL.md
skills/connect-chrome/SKILL.md
skills/context-restore/SKILL.md
skills/design-consultation/SKILL.md
skills/design-html/SKILL.md
skills/design-review/SKILL.md
skills/design-shotgun/SKILL.md
skills/diagram/SKILL.md
skills/document-generate/SKILL.md
skills/freeze/SKILL.md
skills/guard/SKILL.md
skills/investigate/SKILL.md
skills/ios-clean/SKILL.md
skills/ios-design-review/SKILL.md
skills/ios-sync/SKILL.md
skills/landing-report/SKILL.md
skills/make-pdf/SKILL.md
skills/open-gstack-browser/SKILL.md
skills/pair-agent/SKILL.md
skills/plan-design-review/SKILL.md
skills/plan-devex-review/SKILL.md
skills/plan-tune/SKILL.md
skills/qa/SKILL.md
skills/setup-browser-cookies/SKILL.md
skills/setup-deploy/SKILL.md
skills/setup-gbrain/SKILL.md
skills/ship/SKILL.md
skills/skillify/SKILL.md
skills/spec/SKILL.md
skills/sync-gbrain/SKILL.md
skills/unfreeze/SKILL.md
skills/benchmark-models/SKILL.md
skills/canary/SKILL.md
skills/codex/SKILL.md
skills/context-save/SKILL.md
skills/cso/SKILL.md
skills/devex-review/SKILL.md
skills/document-release/SKILL.md
skills/gstack-upgrade/SKILL.md
skills/health/SKILL.md
skills/ios-fix/SKILL.md
skills/ios-qa/SKILL.md
skills/land-and-deploy/SKILL.md
skills/learn/SKILL.md
skills/office-hours/SKILL.md
skills/plan-ceo-review/SKILL.md
skills/plan-eng-review/SKILL.md
skills/qa-only/SKILL.md
skills/retro/SKILL.md
skills/review/SKILL.md
skills/scrape/SKILL.md

Metadata

Files
0
Version
fc73590
Hash
2743d4ee
Indexed
2026-07-19 09:05

Accueil - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-07-22 11:59
浙ICP备14020137号-1 $Carte des visiteurs$