.fyi
SkillsMCPPluginsSubagents

Browse by category

DevOps & CI/CD SkillsProductivity & Workflow SkillsOther SkillsProduct & Project Management SkillsDocumentation & Knowledge SkillsCode Review & Refactor SkillsBackend & APIs SkillsAgent Meta & Communication SkillsResearch SkillsSecurity SkillsUX UI & Design SkillsTesting & QA SkillsSee all →

Every Claude Code skill, MCP server, plugin and subagent in one directory. Searchable, comparable, and one command from installed. Live stats from GitHub, npm and PyPI.

We're on Product HuntYour agent's app storeCheck it out →
Agent SkillsMCP ServersPluginsSubagentsCoding Agents
CollectionsOfficial publishersGlossaryFAQBlogSearchSavedFeedback
PrivacyTermsllms.txtSitemap

made with ♥ · © 2026 aaaa.fyi

Independent project · real data from public registries

…/orchestrator-supaconductor/loop-executor
home/skills/ibrahim-3d/orchestrator-supaconductor/loop-executor
ibrahim-3d avatar

loop-executor

byibrahim-3d· 43 skills

Stars

369

Forks

38

Category

Product & Project Management

View on GitHub

TL;DR

Evaluate-Loop Step 3: EXECUTE. Use this agent to implement tasks from a verified plan. Works through plan.md tasks sequentially, writes code, updates plan.md after every task, and commits at checkpoints. Uses TDD where applicable. Triggered by: 'execute plan', 'implement track', 'build feature', '/conductor implement' (execution phase). Only runs after plan has passed evaluation.

How to install loop-executor?

ibrahim-3d/orchestrator-supaconductor/loop-executor
$npx -y skills add ibrahim-3d/orchestrator-supaconductor --skill loop-executor

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Use this skill

Run `npx skills use "https://github.com/ibrahim-3d/orchestrator-supaconductor" --skill "ibrahim-3d/orchestrator-supaconductor/loop-executor"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.

Use the whole pack

Use the skills in "https://github.com/ibrahim-3d/orchestrator-supaconductor" that are relevant to the current task. Run `npx skills add "https://github.com/ibrahim-3d/orchestrator-supaconductor"` and select the relevant skills, then follow their instructions.

Files · 1

View on GitHub
SKILL.md
1# Loop Executor Agent
2 
3You are the **Execution Agent** for the Conductor Evaluate-Loop (Step 3). Your job is to implement the tasks defined in the plan.
4 
5## Your Process
6 
7### 1. read_file the Plan
8 
9```javascript
10const plan = await read_file(`conductor/tracks/${trackId}/plan.md`);
11// Find all tasks with [ ] (pending)
12// Skip all tasks with [x] (completed)
13```
14 
15### 2. Execute Each Task
16 
17For each pending task:
18 
191. **Understand** — read_file the task description and acceptance criteria
202. **Check Context** — read_file existing files mentioned in the task
213. **Implement** — write_file/replace the code following project patterns
224. **Verify** — Run tests if applicable (`npm run build`, `npm run typecheck`)
235. **Commit** — Create a git commit with descriptive message
246. **Update** — Mark task complete in plan.md immediately
25 
26### 3. Mark Tasks Complete
27 
28After each task, update plan.md:
29 
30```markdown
31- [x] Task 1.1: Create base component <!-- abc1234 -->
32 - Created src/components/foo.tsx
33 - Added TypeScript types
34```
35 
36### 4. Commit Format
37 
38```
39feat(track-id): Task 1.1 - Create base component
40 
41- Created src/components/foo.tsx
42- Added TypeScript types
43- Unit tests passing
44 
45Co-Authored-By: Claude <noreply@anthropic.com>
46```
47 
48## Rules
49 
501. **One task at a time** — Complete fully before moving on
512. **Always update plan.md** — Mark [x] with commit SHA after each task
523. **Follow existing patterns** — Match codebase style and conventions
534. **Don't skip tests** — Run verification before committing
545. **Never expand scope** — Only implement what's in the task description
556. **Update metadata** — Track progress in metadata.json checkpoints
56 
57## State Update
58 
59After all tasks complete:
60 
61```javascript
62metadata.loop_state.current_step = "EVALUATE_EXECUTION";
63metadata.loop_state.step_status = "NOT_STARTED";
64metadata.loop_state.checkpoints.EXECUTE = {
65 status: "PASSED",
66 tasks_completed: totalTasks,
67 commits: [...commitShas]
68};
69```
70 
71## Discovered Work
72 
73If you discover work not in the plan, add it but DO NOT implement:
74 
75```markdown
76## Discovered Work
77- [ ] [Description of discovered work]
78 - Reason: [Why this is needed]
79 - Recommendation: [Add to current track / Create new track]
80```
81 
82## Output Protocol
83 
84write_file detailed progress to plan.md (task markers, commit SHAs) and metadata.json (checkpoints).
85Return ONLY a concise JSON verdict to the orchestrator:
86 
87```json
88{"verdict": "PASS|FAIL", "summary": "<one sentence>", "files_changed": N}
89```
90 
91Do NOT return full reports in your response — the orchestrator reads files, not conversation.
92 
93## Success Criteria
94 
95A successful execution:
96- [ ] All [ ] tasks converted to [x] with commit SHAs
97- [ ] Code follows project patterns and conventions
98- [ ] Build passes (`npm run build`)
99- [ ] Types check (`npm run typecheck`)
100- [ ] Plan.md updated after every task
101- [ ] Metadata.json updated to EVALUATE_EXECUTION step

Preview

ibrahim-3d/orchestrator-supaconductoribrahim-3d/orchestrator-supaconductor

$ npx -y skills add ibrahim-3d/orchestrator-supaconductor --skill loop-executor

▸ installing to .claude/skills…

✓ loop-executor ready

Repoibrahim-3d/orchestrator-supaconductor
TypeSkills
CategoryProduct & Project Management
ForProduct Manager
UpdatedApr 2026
License—
First seenJul 27, 2026

Tags

Skill

Related

6 picks
Type
  1. mattpocock avatargrill-meA relentless interview to sharpen a plan or design.SkillsJul 2026690k189k
  2. mattpocock avatartriageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.SkillsJul 2026463k189k
  3. larksuite avatarlark-task飞书任务:管理任务、清单和任务智能体。创建待办任务、查看和更新任务状态、拆分子任务、组织任务清单、分配协作成员、上传任务附件、注册或注销任务智能体、更新任务智能体的主页数据、写入智能体任务记录。当用户需要创建待办事项、查看任务列表、跟踪任务进度、管理项目清单或给他人分配任务、为任务上传附件文件、注册注销任务智能体、更…SkillsJul 2026388k16k
  4. larksuite avatarlark-okr飞书 OKR:管理目标与关键结果。查看和编辑 OKR 周期、目标、关键结果、对齐关系、量化指标和进展记录。当用户需要查看或创建 OKR、管理目标和关键结果、查看对齐关系时使用。不负责:待办任务管理(lark-task)、日程/会议安排(lark-calendar)、绩效评估SkillsJul 2026324k16k
  5. obra avatarbrainstormingYou MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior.SkillsJul 2026301k261k
  6. mattpocock avatargrillingGrill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.SkillsJul 2026295k189k