synthesize

Stars9

Forks1

UpdatedApril 11, 2026 at 19:39

Cross-references multiple research documents to identify themes, gaps, conflicts, and priority rankings

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Source

jackzhaojin

jackzhaojin/continuous-agent

View GitHub Repository View Creator Repositories

Download

Related occupationsSOC

Based on SOC occupation classification

SociologistsLife, Physical, and Social Science Occupations·SOC 19-3041

SKILL.md

readonly

name	synthesize
description	Cross-references multiple research documents to identify themes, gaps, conflicts, and priority rankings

Synthesize

Analyze multiple research files together to identify cross-cutting themes, knowledge gaps, conflicts, and priorities.

Inputs

{{RESEARCH_DIR}} — Directory containing all research markdown files.
{{OUTPUT_PATH}} — File path where the synthesis report will be written.

Process

Discover and read all research files.
- Use Glob to find all markdown files in {{RESEARCH_DIR}} (pattern: **/*.md).
- Read each file. Track the topic ID, title, and depth of content for each.
Identify cross-cutting themes.
- Use Grep to search for recurring concepts, terms, and patterns across files.
- Group topics that share common underlying principles.
- Note which concepts appear in 3+ different topic areas — these are likely high-priority.
Detect knowledge gaps.
- For each research file, assess whether it has sufficient depth:
  - Does it cover the Overview, Key Concepts, and Technical Details adequately?
  - Are there sections that are thin or vague?
  - Are there referenced subtopics that have no dedicated research file?
- Flag topics that need additional research.
Find conflicting information.
- Look for cases where different research files make contradictory claims.
- Note version-specific differences that could cause confusion.
- Identify areas where "it depends" is the real answer and the nuance needs capturing.
Build a dependency graph.
- Determine which topics build on others (prerequisites).
- Identify foundational topics that should be learned first.
- Note topics that are relatively independent and can be approached in any order.
Rank priorities.
- Consider: importance weight, current depth of research, complexity, number of dependencies.
- Assign each topic area a priority: critical, high, medium, or low.
Write the synthesis.

Output Format

Write a markdown file to {{OUTPUT_PATH}} with this structure:

# Synthesis Report

**Generated:** [ISO 8601 timestamp]
**Research files analyzed:** [count]
**Total topics covered:** [count]

## Cross-cutting Themes

[For each theme that spans multiple topics:]

### [Theme Name]

- **Appears in:** [list of topic IDs]
- **Core concept:** [1-2 sentence explanation]
- **Why it matters:** [relevance to the domain]

## Knowledge Gaps

| Topic ID | Topic Title | Gap Description | Sources Consulted | Severity |
|----------|-------------|-----------------|-------------------|----------|
| ...      | ...         | ...             | [n], [m] from topic's research | high/med/low |

Note which source citations were checked when identifying each gap. If a gap exists because no source covered the subtopic, state "no sources found."

## Conflicting Information

### [Conflict Title]

- **Topics involved:** [topic IDs]
- **Source citations:** [cite the specific `[n]` references from each topic's research that conflict]
- **Conflict:** [description of the contradiction, referencing the cited sources]
- **Resolution:** [if known, how to reconcile; otherwise "needs investigation"]

## Topic Relationships

### Dependency Graph

[Describe the dependency ordering. Which topics are foundational? Which
build on others? Use indented lists or ASCII-style tree notation.]

### Independent Topics

[List topics that can be approached in any order without prerequisites.]

## Priority Rankings

| Priority | Topic ID | Topic Title | Rationale |
|----------|----------|-------------|-----------|
| critical | ...      | ...         | ...       |
| high     | ...      | ...         | ...       |
| medium   | ...      | ...         | ...       |
| low      | ...      | ...         | ...       |

## Recommended Order

[Numbered list of topics in the recommended sequence, considering
dependencies and priorities.]

Guidelines

Be honest about gaps. It is more valuable to flag missing knowledge than to pretend coverage is complete.
Prioritize actionable insights. Each section should help the reader decide what to focus on next.
The dependency graph should be practical, not theoretical. Only list dependencies that actually affect comprehension.
Keep the synthesis focused. This is a decision-making document, not a content summary.

More from this repository

same repository

memory-harvester

jackzhaojin/continuous-agent

The SOLE WRITER to the V3.0 mem0 second brain. Invoked agentically by the executive at write moments — post-run, post-retro, post-spec-merge, manual /harvest. Decides which facts to classify into which memory type (principle/semantic/procedural/episodic/reflective), validates against the schema, and calls the deterministic plumbing in references/ via Bash. Blocks until writes are durable (poll event endpoint for SUCCEEDED). Never invoked from worker code.

2026-05-319

memory-reader

jackzhaojin/continuous-agent

Consult the V3.0 mem0 second brain agentically during executive planning, work selection, pre-spawn memory pack building, and failure diagnosis. Use this skill whenever the executive needs to remember prior runs, retros, or learned principles. Read-only — never writes. Drives the unified `mem0` CLI via Bash, orchestrating multiple iterative search queries (mem0 does not do multi-hop graph traversal natively, so iterative search IS the multi-hop).

2026-05-319

memory-hook-failure-diagnosis

jackzhaojin/continuous-agent

Hook D — Failure-Diagnosis memory consultation. Runs at executive Phase 7 (after 3+ consecutive failures on a work item) BEFORE the failure-diagnosis skill itself runs. Consults the second brain for similar prior failures and successful retry strategies, then hands enriched context to the failure-diagnosis skill. Read-only. Invokes the memory-reader skill.

2026-05-169

memory-hook-post-retro-harvest

jackzhaojin/continuous-agent

Hook E — Post-Retrospective Harvest. Runs after a retrospective markdown doc completes (per-run or weekly). Reads the retro fully and decides which durable lessons (reflective, semantic, procedural memories) to write to the second brain. Typically 3–8 writes per weekly retro, 0–3 per per-run retro. Invokes the memory-harvester skill for the actual writes.

2026-05-169

memory-hook-post-run-harvest

jackzhaojin/continuous-agent

Hook C — Post-Run Harvest. Runs after a worker completes (executive Phase 6 success path). Decides agentically which facts from the run to write to the second brain — typically 0–3 memory writes per run (one episodic, optionally a semantic or procedural). Invokes the memory-harvester skill to do the actual writes (with event-polling for durability).

2026-05-169

memory-hook-pre-spawn-pack

jackzhaojin/continuous-agent

Hook B — Pre-Spawn Memory Pack build. Runs before each worker spawn (executive Phase 4 prep). Reads the second brain for project-specific memories and produces a Memory Pack markdown block that worker-spawner injects into the worker's generated CLAUDE.md. Workers consume this as static markdown — they never call mem0 themselves. Read-only. Invokes the memory-reader skill.

2026-05-169

Synthesize

Analyze multiple research files together to identify cross-cutting themes, knowledge gaps, conflicts, and priorities.

Inputs

{{RESEARCH_DIR}} — Directory containing all research markdown files.

{{OUTPUT_PATH}} — File path where the synthesis report will be written.

Process

Discover and read all research files.

Use Glob to find all markdown files in {{RESEARCH_DIR}} (pattern: **/*.md).
Read each file. Track the topic ID, title, and depth of content for each.

Identify cross-cutting themes.

Use Grep to search for recurring concepts, terms, and patterns across files.
Group topics that share common underlying principles.
Note which concepts appear in 3+ different topic areas — these are likely high-priority.

Detect knowledge gaps.

For each research file, assess whether it has sufficient depth:
- Does it cover the Overview, Key Concepts, and Technical Details adequately?
- Are there sections that are thin or vague?
- Are there referenced subtopics that have no dedicated research file?
Flag topics that need additional research.

Find conflicting information.

Look for cases where different research files make contradictory claims.
Note version-specific differences that could cause confusion.
Identify areas where "it depends" is the real answer and the nuance needs capturing.

Build a dependency graph.

Determine which topics build on others (prerequisites).
Identify foundational topics that should be learned first.
Note topics that are relatively independent and can be approached in any order.

Rank priorities.

Consider: importance weight, current depth of research, complexity, number of dependencies.
Assign each topic area a priority: critical, high, medium, or low.

Write the synthesis.

Output Format

Write a markdown file to {{OUTPUT_PATH}} with this structure:

# Synthesis Report **Generated:** [ISO 8601 timestamp] **Research files analyzed:** [count] **Total topics covered:** [count] ## Cross-cutting Themes [For each theme that spans multiple topics:] ### [Theme Name] - **Appears in:** [list of topic IDs] - **Core concept:** [1-2 sentence explanation] - **Why it matters:** [relevance to the domain] ## Knowledge Gaps | Topic ID | Topic Title | Gap Description | Sources Consulted | Severity | |----------|-------------|-----------------|-------------------|----------| | ... | ... | ... | [n], [m] from topic's research | high/med/low | Note which source citations were checked when identifying each gap. If a gap exists because no source covered the subtopic, state "no sources found." ## Conflicting Information ### [Conflict Title] - **Topics involved:** [topic IDs] - **Source citations:** [cite the specific `[n]` references from each topic's research that conflict] - **Conflict:** [description of the contradiction, referencing the cited sources] - **Resolution:** [if known, how to reconcile; otherwise "needs investigation"] ## Topic Relationships ### Dependency Graph [Describe the dependency ordering. Which topics are foundational? Which build on others? Use indented lists or ASCII-style tree notation.] ### Independent Topics [List topics that can be approached in any order without prerequisites.] ## Priority Rankings | Priority | Topic ID | Topic Title | Rationale | |----------|----------|-------------|-----------| | critical | ... | ... | ... | | high | ... | ... | ... | | medium | ... | ... | ... | | low | ... | ... | ... | ## Recommended Order [Numbered list of topics in the recommended sequence, considering dependencies and priorities.]

Guidelines

Be honest about gaps. It is more valuable to flag missing knowledge than to pretend coverage is complete.

Prioritize actionable insights. Each section should help the reader decide what to focus on next.

The dependency graph should be practical, not theoretical. Only list dependencies that actually affect comprehension.

Keep the synthesis focused. This is a decision-making document, not a content summary.