execute-task

Name: execute-task
Author: jgamaraalv

10installs0forks

How to install execute-task?

jgamaraalv/ts-dev-kit/execute-task

$npx -y skills add jgamaraalv/ts-dev-kit --skill execute-task

Installs into the current project.

Summary

Executes a task, either from a TASK_N.md file or a free-form description. Use when: (1) implementing a task from a TASK_N.md file, (2) the user provides a task file path or says 'execute this task', 'implement TASK_02', or 'run this task', (3) the user describes a task directly w

Files · 1

View on GitHub

SKILL.md

1	<trigger_examples>
2	- "Execute TASK_02"
3	- "Implement docs/features/search/TASK_01.md"
4	- "Run this task"
5	- "Execute the task"
6	- "Implement the search feature"
7	- "Build the user creation flow end-to-end"
8	- "Add the notifications endpoint to the API"
9	</trigger_examples>
10
11	<task>
12	$ARGUMENTS
13	</task>
14
15	<workflow>
16	Follow each phase in order. Each one feeds the next.
17
18	<phase_0_intake>
19	Resolve the input and ensure the task document is complete before executing.
20
21	Step 1 — Determine input type:
22	- If `$ARGUMENTS` looks like a file path (ends in `.md`, or starts with `/`, `./`, `docs/`, or contains a directory separator): read the file.
23	- Otherwise: treat it as a free-form task description — skip to Step 3.
24
25	Step 2 — Validate the task document:
26	A task document is ready for execution when it contains ALL of:
27	- `## Scope — Files` with at least one file entry
28	- `## Success Criteria` with at least one testable criterion
29	- `## Verification Plan` with baseline and post-change checks
30
31	If all required sections are present → proceed to phase 1.
32
33	Step 3 — Generate the task document:
34	If the document is missing any required section, OR the input was a free-form description:
35
36	1. Inform the user:
37	> Task document incomplete. Generating a structured task document via `/generate-tasks` before proceeding.
38	2. Call `Skill(skill: "generate-tasks")` passing the original input as context.
39	3. After generation, note the path of the saved `TASK_N.md` file.
40	4. Read the generated file and confirm all required sections are present.
41	5. Resume execution using the generated document — continue to phase 1.
42	</phase_0_intake>
43
44	<phase_1_context_analysis>
45	Before writing any code, build a mental model of the task scope.
46
47	1. Read the resolved task document fully (path determined in phase 0).
48	2. Read the project CLAUDE.md and root package.json — understand project structure, available commands, and dependency graph.
49	3. Search the codebase for existing patterns — use Grep/Glob to find related files, similar implementations, and reusable code relevant to the task's file scope.
50	4. Identify the affected packages/directories from the task's "Scope — Files" section.
51	</phase_1_context_analysis>
52
53	<phase_2_role_assignment>
54	Determine the full execution context: role persona, domain area, domain technologies, project context, required skills, and available MCPs.
55
56	<domain_areas>
57	Map the task to one or more domain areas AND sub-areas. Sub-areas determine the specialist agent type and skill set.
58
59	Backend
60	\| Sub-area \| Agent type \| When \| Key skills \|
61	\|----------\|-----------\|------\|------------\|
62	\| Database \| `database-expert` \| Schema design, migrations, complex queries, indexes \| drizzle-pg, postgresql \|
63	\| Endpoints \| `api-builder` \| Routes, validation, handlers, API contracts \| fastify-best-practices \|
64	\| Queues \| `general-purpose` \| Job processing, workers, schedulers \| bullmq, ioredis \|
65	\| Security \| `security-scanner` \| Auth flows, RBAC, input sanitization \| owasp-security-review \|
66
67	Frontend
68	\| Sub-area \| Agent type \| When \| Key skills \|
69	\|----------\|-----------\|------\|------------\|
70	\| Components \| `react-specialist` \| Component architecture, hooks, state management, composition \| react-best-practices, composition-patterns \|
71	\| Pages/routing \| `general-purpose` \| Pages, layouts, data fetching, RSC boundaries \| nextjs-best-practices \|
72	\| UI/UX \| `ux-optimizer` \| User flows, form UX, friction reduction \| ui-ux-guidelines \|
73	\| Accessibility \| `accessibility-pro` \| WCAG compliance, keyboard nav, screen readers \| — \|
74	\| Performance \| `performance-engineer` \| Core Web Vitals, bundle size, re-renders \| react-best-practices \|
75
76	Shared packages — `typescript-pro` or `general-purpose` (shared types, schemas, utilities)
77
78	Cross-cutting specialists (use alongside any domain)
79	\| Agent type \| When \|
80	\|-----------\|------\|
81	\| `test-generator` \| Writing test suites, improving coverage \|
82	\| `debugger` \| Investigating errors, stack traces \|
83	\| `docker-expert` \| Dockerfiles, compose, container config \|
84	\| `code-reviewer` \| Post-implementation review \|
85	\| `playwright-expert` \| E2E browser tests \|
86
87	A single task may require agents from multiple sub-areas. For example, "add a new resource endpoint with list UI" needs `database-expert` (schema) + `api-builder` (route) + `react-specialist` (component).
88	</domain_areas>
89
90	<domain_technologies>
91	Read the relevant package.json to identif

People who liked this also viewed

6 picks

Type

execute-task

10installs0forks

View on GitHub

How to install execute-task?

jgamaraalv/ts-dev-kit/execute-task

$npx -y skills add jgamaraalv/ts-dev-kit --skill execute-task

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	<trigger_examples>
2	- "Execute TASK_02"
3	- "Implement docs/features/search/TASK_01.md"
4	- "Run this task"
5	- "Execute the task"
6	- "Implement the search feature"
7	- "Build the user creation flow end-to-end"
8	- "Add the notifications endpoint to the API"
9	</trigger_examples>
10
11	<task>
12	$ARGUMENTS
13	</task>
14
15	<workflow>
16	Follow each phase in order. Each one feeds the next.
17
18	<phase_0_intake>
19	Resolve the input and ensure the task document is complete before executing.
20
21	Step 1 — Determine input type:
22	- If `$ARGUMENTS` looks like a file path (ends in `.md`, or starts with `/`, `./`, `docs/`, or contains a directory separator): read the file.
23	- Otherwise: treat it as a free-form task description — skip to Step 3.
24
25	Step 2 — Validate the task document:
26	A task document is ready for execution when it contains ALL of:
27	- `## Scope — Files` with at least one file entry
28	- `## Success Criteria` with at least one testable criterion
29	- `## Verification Plan` with baseline and post-change checks
30
31	If all required sections are present → proceed to phase 1.
32
33	Step 3 — Generate the task document:
34	If the document is missing any required section, OR the input was a free-form description:
35
36	1. Inform the user:
37	> Task document incomplete. Generating a structured task document via `/generate-tasks` before proceeding.
38	2. Call `Skill(skill: "generate-tasks")` passing the original input as context.
39	3. After generation, note the path of the saved `TASK_N.md` file.
40	4. Read the generated file and confirm all required sections are present.
41	5. Resume execution using the generated document — continue to phase 1.
42	</phase_0_intake>
43
44	<phase_1_context_analysis>
45	Before writing any code, build a mental model of the task scope.
46
47	1. Read the resolved task document fully (path determined in phase 0).
48	2. Read the project CLAUDE.md and root package.json — understand project structure, available commands, and dependency graph.
49	3. Search the codebase for existing patterns — use Grep/Glob to find related files, similar implementations, and reusable code relevant to the task's file scope.
50	4. Identify the affected packages/directories from the task's "Scope — Files" section.
51	</phase_1_context_analysis>
52
53	<phase_2_role_assignment>
54	Determine the full execution context: role persona, domain area, domain technologies, project context, required skills, and available MCPs.
55
56	<domain_areas>
57	Map the task to one or more domain areas AND sub-areas. Sub-areas determine the specialist agent type and skill set.
58
59	Backend
60	\| Sub-area \| Agent type \| When \| Key skills \|
61	\|----------\|-----------\|------\|------------\|
62	\| Database \| `database-expert` \| Schema design, migrations, complex queries, indexes \| drizzle-pg, postgresql \|
63	\| Endpoints \| `api-builder` \| Routes, validation, handlers, API contracts \| fastify-best-practices \|
64	\| Queues \| `general-purpose` \| Job processing, workers, schedulers \| bullmq, ioredis \|
65	\| Security \| `security-scanner` \| Auth flows, RBAC, input sanitization \| owasp-security-review \|
66
67	Frontend
68	\| Sub-area \| Agent type \| When \| Key skills \|
69	\|----------\|-----------\|------\|------------\|
70	\| Components \| `react-specialist` \| Component architecture, hooks, state management, composition \| react-best-practices, composition-patterns \|
71	\| Pages/routing \| `general-purpose` \| Pages, layouts, data fetching, RSC boundaries \| nextjs-best-practices \|
72	\| UI/UX \| `ux-optimizer` \| User flows, form UX, friction reduction \| ui-ux-guidelines \|
73	\| Accessibility \| `accessibility-pro` \| WCAG compliance, keyboard nav, screen readers \| — \|
74	\| Performance \| `performance-engineer` \| Core Web Vitals, bundle size, re-renders \| react-best-practices \|
75
76	Shared packages — `typescript-pro` or `general-purpose` (shared types, schemas, utilities)
77
78	Cross-cutting specialists (use alongside any domain)
79	\| Agent type \| When \|
80	\|-----------\|------\|
81	\| `test-generator` \| Writing test suites, improving coverage \|
82	\| `debugger` \| Investigating errors, stack traces \|
83	\| `docker-expert` \| Dockerfiles, compose, container config \|
84	\| `code-reviewer` \| Post-implementation review \|
85	\| `playwright-expert` \| E2E browser tests \|
86
87	A single task may require agents from multiple sub-areas. For example, "add a new resource endpoint with list UI" needs `database-expert` (schema) + `api-builder` (route) + `react-specialist` (component).
88	</domain_areas>
89
90	<domain_technologies>
91	Read the relevant package.json to identif

People who liked this also viewed

6 picks

Type