batch-process

Name: batch-process
Author: indranilbanerjee

16stars6forks

How to install batch-process?

indranilbanerjee/contentforge/batch-process

$npx -y skills add indranilbanerjee/contentforge --skill batch-process

Installs into the current project.

Summary

Process multiple content pieces through a prioritized, checkpointed queue with progress tracking and per-piece quality gates

Files · 1

View on GitHub

SKILL.md

1	# Batch Content Processing
2
3	Process multiple content requirements through the ContentForge pipeline as a sequential, checkpointed queue with priority-based scheduling and event-driven progress tracking. Each piece runs the full 10-phase pipeline (plus Step 0.5) with all 10 quality gates — batch mode changes the intake, not the standards.
4
5	## When to Use
6
7	Use `/contentforge:batch-process` when:
8	- You have 2+ content pieces to produce
9	- You want hands-off production of a whole queue (each piece needs a pre-set title — batch runs are non-interactive)
10	- You need priority scheduling (urgent pieces first)
11	- You want per-piece progress visibility and resumability
12	- You're running agency-scale production (10-50+ pieces)
13
14	## What This Command Does
15
16	1. Intake Multiple Requirements — Read from the brand's tracking backend: local JSON (default), Google Sheets, Airtable, or a CSV file
17	2. Build Execution Queue — Validate rows and sort by priority
18	3. Sequential Orchestration — Run one full ContentForge pipeline per piece, in queue order; every phase of every piece is checkpointed, so an interrupted batch resumes where it stopped
19	4. Progress Tracking — Status table redrawn after each piece/phase event (piece started, gate passed, piece finished)
20	5. Error Handling — Automatic retry for transient failures (resuming from checkpoints), human escalation for persistent issues
21	6. Completion Report — Summary of all pieces: APPROVED, review_required, failed, with quality scores and output locations
22
23	## Required Inputs
24
25	Tracking backend (per brand, via `tracking.backend` in the brand profile — `local` is the default):
26	- Local JSON — requirements managed by `scripts/local-tracker.py`
27	- Google Sheets — sheet with columns: `Requirement ID`, `Content Type`, `Title`, `Target Audience`, `Brand`, `Word Count Target`, `Priority` (1-5), `Status`
28	- Airtable — base with the same fields
29
30	CSV (alternative intake):
31	```csv
32	requirement_id,content_type,title,target_audience,brand,word_count,priority,status
33	REQ-001,article,AI in Healthcare,Healthcare CIOs,acmemed,2000,1,pending
34	REQ-002,blog,10 Tips for Remote Teams,HR Managers,techcorp,1500,3,pending
35	```
36
37	Note: the `title` column doubles as the `--title` bypass — batch pieces skip interactive title curation and use it verbatim.
38
39	## How to Use
40
41	### Basic Usage
42	```
43	/contentforge:batch-process
44	```
45	Prompt: "Where are your content requirements? (local queue / Google Sheet URL / Airtable / CSV)"
46
47	### With Direct Sheet URL
48	```
49	/contentforge:batch-process https://docs.google.com/spreadsheets/d/ABC123/edit
50	```
51
52	### With CSV Upload
53	```
54	/contentforge:batch-process batch-requirements.csv
55	```
56
57	## What Happens
58
59	### Step 1: Queue Building
60	- Load all requirements from source
61	- Validate each row (required fields, brand exists, content type supported, word count within the type's canonical range)
62	- Sort by priority (1=highest, 5=lowest)
63	- Display queue summary: total pieces, priority mix, execution order
64
65	### Step 2: Sequential Execution
66	- Run one ContentForge pipeline per piece, front-to-back
67	- Each pipeline runs the full protocol from `skills/contentforge/SKILL.md` — Step 0 init, title bypass, phases 1–8 with orchestrator-verified gates, per-phase checkpoints
68	- When one piece finishes (or is escalated), the next starts automatically
69
70	### Step 3: Progress Table (event-driven)
71	Redrawn after each piece/phase event — not on a timer:
72	```
73	CONTENTFORGE BATCH — 2/5 complete \| 1 review_required \| 0 failed
74	─────────────────────────────────────────────────────────────
75	▶ REQ-003 \| SEO Whitepaper \| Phase 4 (Validation)
76	✓ REQ-001 \| AI in Healthcare \| APPROVED 8.4
77	✓ REQ-004 \| FAQ Product Launch \| APPROVED 7.6
78	⚠ REQ-002 \| Remote Teams Blog \| review_required (6.1)
79	· REQ-005 \| Case Study Acme \| queued
80	```
81
82	### Step 4: Completion Report
83	- Total pieces processed
84	- APPROVED count (reviewer composite ≥7.0, industry-adjusted, all dimension minimums met)
85	- review_required count (5.0-6.9 after loop limits, or <5.0)
86	- Failed count
87	- Output locations: `~/Documents/ContentForge/{Brand}/` (+ Drive folder if configured)
88
89	## Priority Scheduling
90
91	Priority Levels:
92	- 1 (Urgent): Processed first, deadline-driven (e.g., press release for tomorrow)
93	- 2 (High): Campaign-critical content
94	- 3 (Normal): Standard blog posts, articles
95	- 4 (Low): Evergreen content, no deadline
96	- 5 (Backlog): Nice-to-have, filler content
97
98	## Execution Model
99
100	- Sequential, one piece at a time — no concurrent pipelines. Shared per-brand state, API rate limits, and context limits make in-session parallelism unsafe; resilience comes from per-phase checkpointing instead.
101	- Each piece is fully independent (own checkpoint run directory, own quality gates)
102	- If a p

People who liked this also viewed

6 picks

Type

seo-auditWhen the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tagSkillsJul 2026168k41k
copywritingWhen the user wants to write, rewrite, or improve marketing copy for any page — including homepage, landing pages, pricing pages, feature pages, about pages, or product pages. Also use when the user sSkillsJul 2026159k41k
marketing-psychologyWhen the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also use when the user mentions 'psychology,' 'mental models,' 'cognitive bias,' 'persuasion,'SkillsJul 2026116k41k
content-strategyWhen the user wants to plan a content strategy, decide what content to create, or figure out what topics to cover. Also use when the user mentions "content strategy," "what should I write about," "conSkillsJul 2026111k41k
programmatic-seoWhen the user wants to create SEO-driven pages at scale using templates and data. Also use when the user mentions "programmatic SEO," "template pages," "pages at scale," "directory pages," "location pSkillsJul 2026107k41k
marketing-ideasWhen the user needs marketing ideas, inspiration, or strategies for their SaaS or software product. Also use when the user asks for 'marketing ideas,' 'growth ideas,' 'how to market,' 'marketing stratSkillsJul 2026104k41k

batch-process

16stars6forks

View on GitHub

How to install batch-process?

indranilbanerjee/contentforge/batch-process

$npx -y skills add indranilbanerjee/contentforge --skill batch-process

Installs into the current project.

Summary

Process multiple content pieces through a prioritized, checkpointed queue with progress tracking and per-piece quality gates

Files · 1

View on GitHub

SKILL.md

1	# Batch Content Processing
2
3	Process multiple content requirements through the ContentForge pipeline as a sequential, checkpointed queue with priority-based scheduling and event-driven progress tracking. Each piece runs the full 10-phase pipeline (plus Step 0.5) with all 10 quality gates — batch mode changes the intake, not the standards.
4
5	## When to Use
6
7	Use `/contentforge:batch-process` when:
8	- You have 2+ content pieces to produce
9	- You want hands-off production of a whole queue (each piece needs a pre-set title — batch runs are non-interactive)
10	- You need priority scheduling (urgent pieces first)
11	- You want per-piece progress visibility and resumability
12	- You're running agency-scale production (10-50+ pieces)
13
14	## What This Command Does
15
16	1. Intake Multiple Requirements — Read from the brand's tracking backend: local JSON (default), Google Sheets, Airtable, or a CSV file
17	2. Build Execution Queue — Validate rows and sort by priority
18	3. Sequential Orchestration — Run one full ContentForge pipeline per piece, in queue order; every phase of every piece is checkpointed, so an interrupted batch resumes where it stopped
19	4. Progress Tracking — Status table redrawn after each piece/phase event (piece started, gate passed, piece finished)
20	5. Error Handling — Automatic retry for transient failures (resuming from checkpoints), human escalation for persistent issues
21	6. Completion Report — Summary of all pieces: APPROVED, review_required, failed, with quality scores and output locations
22
23	## Required Inputs
24
25	Tracking backend (per brand, via `tracking.backend` in the brand profile — `local` is the default):
26	- Local JSON — requirements managed by `scripts/local-tracker.py`
27	- Google Sheets — sheet with columns: `Requirement ID`, `Content Type`, `Title`, `Target Audience`, `Brand`, `Word Count Target`, `Priority` (1-5), `Status`
28	- Airtable — base with the same fields
29
30	CSV (alternative intake):
31	```csv
32	requirement_id,content_type,title,target_audience,brand,word_count,priority,status
33	REQ-001,article,AI in Healthcare,Healthcare CIOs,acmemed,2000,1,pending
34	REQ-002,blog,10 Tips for Remote Teams,HR Managers,techcorp,1500,3,pending
35	```
36
37	Note: the `title` column doubles as the `--title` bypass — batch pieces skip interactive title curation and use it verbatim.
38
39	## How to Use
40
41	### Basic Usage
42	```
43	/contentforge:batch-process
44	```
45	Prompt: "Where are your content requirements? (local queue / Google Sheet URL / Airtable / CSV)"
46
47	### With Direct Sheet URL
48	```
49	/contentforge:batch-process https://docs.google.com/spreadsheets/d/ABC123/edit
50	```
51
52	### With CSV Upload
53	```
54	/contentforge:batch-process batch-requirements.csv
55	```
56
57	## What Happens
58
59	### Step 1: Queue Building
60	- Load all requirements from source
61	- Validate each row (required fields, brand exists, content type supported, word count within the type's canonical range)
62	- Sort by priority (1=highest, 5=lowest)
63	- Display queue summary: total pieces, priority mix, execution order
64
65	### Step 2: Sequential Execution
66	- Run one ContentForge pipeline per piece, front-to-back
67	- Each pipeline runs the full protocol from `skills/contentforge/SKILL.md` — Step 0 init, title bypass, phases 1–8 with orchestrator-verified gates, per-phase checkpoints
68	- When one piece finishes (or is escalated), the next starts automatically
69
70	### Step 3: Progress Table (event-driven)
71	Redrawn after each piece/phase event — not on a timer:
72	```
73	CONTENTFORGE BATCH — 2/5 complete \| 1 review_required \| 0 failed
74	─────────────────────────────────────────────────────────────
75	▶ REQ-003 \| SEO Whitepaper \| Phase 4 (Validation)
76	✓ REQ-001 \| AI in Healthcare \| APPROVED 8.4
77	✓ REQ-004 \| FAQ Product Launch \| APPROVED 7.6
78	⚠ REQ-002 \| Remote Teams Blog \| review_required (6.1)
79	· REQ-005 \| Case Study Acme \| queued
80	```
81
82	### Step 4: Completion Report
83	- Total pieces processed
84	- APPROVED count (reviewer composite ≥7.0, industry-adjusted, all dimension minimums met)
85	- review_required count (5.0-6.9 after loop limits, or <5.0)
86	- Failed count
87	- Output locations: `~/Documents/ContentForge/{Brand}/` (+ Drive folder if configured)
88
89	## Priority Scheduling
90
91	Priority Levels:
92	- 1 (Urgent): Processed first, deadline-driven (e.g., press release for tomorrow)
93	- 2 (High): Campaign-critical content
94	- 3 (Normal): Standard blog posts, articles
95	- 4 (Low): Evergreen content, no deadline
96	- 5 (Backlog): Nice-to-have, filler content
97
98	## Execution Model
99
100	- Sequential, one piece at a time — no concurrent pipelines. Shared per-brand state, API rate limits, and context limits make in-session parallelism unsafe; resilience comes from per-phase checkpointing instead.
101	- Each piece is fully independent (own checkpoint run directory, own quality gates)
102	- If a p

People who liked this also viewed

6 picks

Type