Fix blank project.yml files -- add name, goal, genre, audience, chapter counts and correct intent templates for whispers-in-the-dark, echoes-of-the-forest, book-marketing-agency, and marketing-strategy

This commit is contained in:
David Baity
2026-04-30 23:54:16 -04:00
parent 44884eeb60
commit 4c943a30ee
10 changed files with 860 additions and 4 deletions

View File

@@ -0,0 +1,127 @@
name: human_polish_brief
description: "Produces a targeted human polish brief for a chapter that requires voice correction, style diversity improvement, or AI-fingerprint reduction."
debug: false
model: power
system: agent_prompt
agent_prompt:
- "= identity.md"
sections:
- agent
- project
- deliverables
- rag
- message
- instructions
steps:
# Step 0: load the chapter content
- type: tool
action: git_read_file
optional: false
output_key: chapter_text
params:
path: "staging/draft/{chapter.slug}.md"
# Step 1: load the slop gate flag report if available
- type: tool
action: git_read_file
optional: true
output_key: slop_gate_report
params:
path: "staging/flags/slop_gate_flag_{task.parent_id}.md"
# Step 2: load voice signature for comparison
- type: tool
action: git_read_file
optional: true
output_key: voice_signature
params:
path: "agents/{agent.name}/voice_signature.json"
# Step 3: load the chapter outline for this chapter
- type: tool
action: git_read_file
optional: true
output_key: chapter_brief
params:
path: "staging/briefs/brief-{chapter.slug}.md"
# Step 4: produce the full human polish brief
- type: think
max_tokens: 3000
output_key: polish_brief
hint: |
You are {agent.name}, producing a Human Polish Brief for {project.name}.
The brief tells a human editor exactly what to fix in this chapter and why.
Chapter content: the DELIVERABLES section above.
Slop gate report: {slop_gate_report}
Author voice signature: {voice_signature}
Chapter brief / outline: {chapter_brief}
Structure your brief as follows:
## Human Polish Brief -- {chapter.slug}
### Why This Chapter Needs Human Revision
[2-3 sentences: what triggered this brief. Be specific. Cite gate scores if available.]
### Priority Revision Targets
[4-8 numbered items. For each:]
- LOCATION: paragraph N or approximate position in chapter
- QUOTE: the exact passage (1-3 sentences) that needs revision
- PROBLEM: what makes this feel AI-generated or voice-wrong
- DIRECTION: what the human should do instead (specific, not vague)
### Voice Calibration Notes
[3-5 bullet points on what authentic voice for this author and project sounds like.
If voice_signature is available, reference the pacing_profile and register.
If not available, derive from the project genre and character context.]
### Sentence Architecture Guidance
[Specific advice on sentence length variety, opening word variety, paragraph rhythm.
Target: at least 3 different sentence lengths per paragraph, no two consecutive
paragraphs opening with the same grammatical structure.]
### Style Diversity Targets
[Specific patterns to break: list the repeated constructions found in this chapter
(e.g., "5 of 12 paragraphs begin with 'She'") and alternatives.]
### Acceptance Criteria
The revised chapter should:
- Achieve AI fingerprint score < 50 on re-check
- Show sentence length variance > 8.0
- Have opening word repetition rate < 0.25
- Preserve all plot beats and character beats from the chapter brief
- Maintain the genre and audience register
Output ONLY the brief text above. No preamble.
# Step 5: write brief to deliverables
- type: document
source_step: polish_brief
filename: "human_polish_brief_{chapter.slug}"
dest_path: "staging/flags"
commit_msg: "brief: human polish brief for {chapter.slug} -- task {task.id}"
# Step 6: reply to channel
- type: reply
target: channel
channel_name: "crimson_leaf_publishing:live-feed"
hint: |
Post: "Human Polish Brief ready for {chapter.slug}. Saved to staging/flags/.
Assign to a human editor or David for manual revision before re-running the slop gate."
adjudication:
enabled: true
pass_threshold: 65
deliverable_type: brief
criteria:
specificity:
weight: 40
description: "Revision targets quote actual text and give specific direction"
completeness:
weight: 35
description: "All required sections present with meaningful content"
actionability:
weight: 25
description: "A human editor can follow the brief without additional context"