HuynhSang2005/execute-work
.agents/skills/execute-work/SKILL.md
Execute an approved implementation plan with strict checkpoints, blocker handling, verification, and end-of-branch completion options (merge, PR, keep, or discard).
testing
Updated Apr 16, 2026
$ install --global
skillsauthnpx skillsauth add HuynhSang2005/delivery-app execute-workInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 25, 2026, 9:34 PM1.8s1 file scanned
SKILL.md
- name:
- execute-work
- description:
- Execute an approved implementation plan with strict checkpoints, blocker handling, verification, and end-of-branch completion options (merge, PR, keep, or discard).
Execute Work
Use this skill to run an existing plan from start to completion.
When to use
- User already has a written plan and wants implementation.
- Work should be executed task-by-task with visible progress.
- Branch completion decision is needed after implementation.
Execution protocol
- Announce you are using execute-work.
- Load and critically review the plan before touching code.
- If unclear instructions or blockers exist, stop and ask.
- Execute tasks in order, one checklist item at a time.
- Run verification exactly as specified after each task.
- Track progress by marking completed tasks in the plan.
Legacy guidance migrated
This skill consolidates key behavior previously spread across executing-plans and finishing-a-development-branch:
- critical plan review before execution,
- strict stop-on-blocker behavior,
- verification-gated execution,
- explicit branch-completion decision tree.
Blocker rules
Stop immediately and request guidance when:
- required dependency/tool is missing,
- plan instruction is ambiguous,
- verification repeatedly fails,
- unexpected architectural conflict appears.
Do not guess through blockers.
Verification rules
- Never claim completion without running verification commands.
- Prefer focused tests first, then broader suite if needed.
- Record what passed/failed in concise summary.
Completion workflow (after all tasks pass)
Run final test verification, then present exactly these options:
- Merge back to base branch locally.
- Push branch and create Pull Request.
- Keep branch as-is.
- Discard branch/work.
Use concise prompt format:
Implementation complete. What would you like to do?
1. Merge back to base branch locally
2. Push and create a Pull Request
3. Keep the branch as-is
4. Discard this work
Option handling
- If tests fail, do not offer completion options; fix first.
- If discard is chosen, require explicit confirmation text before deleting.
- Clean up worktree only when workflow calls for it.
- Never perform destructive branch deletion without explicit user confirmation.
Base branch determination
Detect base branch from repository conventions (main/master) or ask user if unclear.
Minimal completion output
## Execution Result
- Plan executed: <path>
- Tasks completed: <N>/<N>
- Verification: <passed/failed summary>
- Branch completion choice: <1|2|3|4>
- Final state: <merged/pr-open/kept/discarded>
Integration
- Upstream planning skill:
plan-work - Technical restructuring skill:
refactor
Related Skills
HuynhSang2005/react-hook-form
tools
VerifiedTrustedCommunity
React Hook Form performance optimization for client-side form validation using useForm, useWatch, useController, and useFieldArray. This skill should be used when building client-side controlled forms with React Hook Form library. This skill does NOT cover React 19 Server Actions, useActionState, or server-side form handling.
SKILL.mdUpdated Apr 16, 2026
HuynhSang2005/react-hook-form-zod
tools
VerifiedTrustedCommunity
Build type-safe validated forms using React Hook Form v7 and Zod v4. Single schema works on client and server with full TypeScript inference via z.infer. Use when building forms, multi-step wizards, or fixing uncontrolled warnings, resolver errors, useFieldArray issues, performance problems with large forms.
SKILL.mdUpdated Apr 16, 2026
HuynhSang2005/prisma-postgres
tools
VerifiedTrustedCommunity
Prisma Postgres setup and operations guidance across Console, create-db CLI, Management API, and Management API SDK. Use when creating Prisma Postgres databases, working in Prisma Console, provisioning with create-db/create-pg/create-postgres, or integrating programmatic provisioning with service tokens or OAuth.
SKILL.mdUpdated Apr 16, 2026
HuynhSang2005/prisma-driver-adapter-implementation
development
VerifiedTrustedCommunity
Required reference for Prisma v7 driver adapter work. Use when implementing or modifying adapters, adding database drivers, or touching SqlDriverAdapter/Transaction interfaces. Contains critical contract details not inferable from code examples — including the transaction lifecycle protocol, error mapping requirements, and verification checklist. Existing implementations do not replace this skill.
SKILL.mdUpdated Apr 16, 2026