synthesize
Force a research-agent run to conclude. Launches the researcher in synthesis mode: it reads state.md and log.md, writes .research/synthesis.md with outcome, key findings, failed approaches, open questions, and recommendations, then exits. Use when current results are good enough or the agent is stalling.
What this skill does
# Synthesize Research
Force the researcher to write its final synthesis and conclude, even if
it would otherwise continue exploring.
## When to use
- Current results are good enough; lock them in
- The agent is stalling (eval flat/declining for several cycles)
- A deadline forces a conclusion regardless of completeness
- The user wants a checkpoint before pivoting to a related research line
## Step 1: Verify .research/ exists
Use the Read tool on `.research/state.md`. If the file does not exist, tell the user there is no research to synthesize and suggest `/research-agent:research` to start one.
## Step 2: Check whether already synthesized
Use the Glob tool for `.research/synthesis.md`. If it already exists, ask the user whether they want to overwrite (re-synthesize, perhaps because more cycles have happened since) or stop.
## Step 3: Launch the researcher with synthesis framing
Spawn the researcher agent (Agent tool, subagent_type `research-agent:researcher`) with this prompt:
<mode>synthesize</mode>
<working_directory>
{absolute path to current working directory}
</working_directory>
Synthesize your research and conclude. Do NOT run new attempts. Do
NOT start new cycles. The user has decided to lock in current
results.
Step 1: Read .research/state.md and .research/log.md in full to
recall every sub-problem, hypothesis, and attempt.
Step 2: Update .research/state.md with final statuses. Mark every
sub-problem as one of: resolved, abandoned, or unresolved. Mark
every hypothesis as one of: confirmed, refuted, inconclusive.
Step 3: Write .research/synthesis.md per the Termination Protocol
in your system prompt. Required sections: Goal, Outcome (one
paragraph), Key Findings, Failed Approaches, Open Questions,
Recommendations.
Step 4: Append a final entry to .research/log.md noting the forced
conclusion and pointing at synthesis.md.
Be honest in the synthesis. If the goal was not achieved, say so
plainly. If results are partial, describe their scope precisely.
The synthesis is the single document a future reader will rely on.
## Step 4: Inform the user
After launching, tell the user:
> Researcher synthesizing. It will read state.md and log.md, finalize statuses, and write .research/synthesis.md. This usually completes in one cycle (no new attempts).
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.