provider-task-execution
Execute a domain-local provider task and return a concrete provider result instead of plans or commentary.
Skill by vectie
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/vectie-provider-task-execution
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 26, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/provider-task-execution
What's inside
- Skill name
provider-task-execution- Description
- Execute a domain-local provider task and return a concrete provider result instead of plans or commentary. Use for provider-backed extension execution.
- License
- Apache-2.0
- Instructions
- 29 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Provider Task Execution Use this skill when MoonClaw delegates work to a domain-local provider boundary. ## Goal Do the task inside the provider workspace and report what actually changed. ## Rules - Do not return plans, outlines, checklists, or commentary about what you intend to do. - Use the listed skill files, policy, routines, pages, and memory as the work method. - Produce durable outputs when the task requires durable book updates. - If durable outputs were created, list them as artifact paths relative to the workspace. - Only emit memory candidates that are worth persisting back into the provider boundary. - If the task cannot produce durable outputs yet, return a concrete blocker summary and say what is missing. - Do not pretend the task succeeded when no durable work happened. ## Durable-output expectations - Prefer concrete source, entity, concept, query, synthesis, or other domain pages over vague completion text. - If nothing durable was created, say so explicitly and explain why. ## Output discipline - Return JSON only. - Follow the exact runtime contract supplied by MoonClaw.
From vectie/moonclaw, Apache-2.0.
More from vectie/moonclaw
- 0.608score
research-report-writer
vectie
Turn research workflow outputs into a compact brief or digest with clear priorities, recommended actions, and unresolved questions.
SkillBFreshness: B★ 25Claude Code +9 - 0.608score
research-paper-summary
vectie
Summarize research papers or small paper sets with emphasis on problem, method, evidence, limitations, and practical relevance.
SkillBFreshness: B★ 25Claude Code +9 - 0.608score
research-novelty-review
vectie
Evaluate the novelty and significance of research papers using grounded comparisons, method changes, and evidence quality.
SkillBFreshness: B★ 25Claude Code +9 - 0.608score
job-planning
vectie
Draft safe MoonClaw job proposals with the exact proposal JSON schema and execution-oriented step decomposition.
SkillBFreshness: B★ 25Claude Code +9 - 0.605score
analysis-adaptation
vectie
Judge whether an analysis step is complete, blocked on external input, or should expand into a child subplan.
SkillBFreshness: B★ 25Claude Code +9 - 0.603score
provider-task-repair
vectie
Repair an invalid provider task output into the exact ProviderTaskResult shape.
SkillBFreshness: B★ 25Claude Code +9 - 0.602score
opc-ship
vectie
Shipping-decision skill for one-person-company controller runs.
SkillBFreshness: B★ 25Claude Code +9 - 0.602score
opc-ceo
vectie
Founder-mode product review for a one-person-company sprint.
SkillBFreshness: B★ 25Claude Code +9 - 0.599score
opc-eng
vectie
Engineering-lead planning skill for OPC feature execution.
SkillBFreshness: B★ 25Claude Code +9 - 0.597score
opc-review
vectie
Staff-level review skill for correctness and regression risk.
SkillBFreshness: B★ 25Claude Code +9 - 0.594score
opc-qa
vectie
QA skill for verifying intended behavior and evidence.
SkillBFreshness: B★ 25Claude Code +9
Signals
- Stars
- 25
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Apr 16, 2026 (6 months ago)
- Last release
- Aug 23, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/vectie/moonclaw
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from vectie
- 0.608score
research-report-writer
vectie
Turn research workflow outputs into a compact brief or digest with clear priorities, recommended actions, and unresolved questions.
SkillBFreshness: B★ 25Claude Code +9 - 0.608score
research-paper-summary
vectie
Summarize research papers or small paper sets with emphasis on problem, method, evidence, limitations, and practical relevance.
SkillBFreshness: B★ 25Claude Code +9 - 0.608score
research-novelty-review
vectie
Evaluate the novelty and significance of research papers using grounded comparisons, method changes, and evidence quality.
SkillBFreshness: B★ 25Claude Code +9 - 0.608score
job-planning
vectie
Draft safe MoonClaw job proposals with the exact proposal JSON schema and execution-oriented step decomposition.
SkillBFreshness: B★ 25Claude Code +9 - 0.605score
analysis-adaptation
vectie
Judge whether an analysis step is complete, blocked on external input, or should expand into a child subplan.
SkillBFreshness: B★ 25Claude Code +9 - 0.603score
provider-task-repair
vectie
Repair an invalid provider task output into the exact ProviderTaskResult shape.
SkillBFreshness: B★ 25Claude Code +9
Cite this page
provider-task-execution skill. Agent Mart. https://agentmart.dev/skills/vectie-provider-task-execution (last updated 2026-10-24)