agentsociety-research-pipeline

Use when starting or resuming an AgentSociety research workspace, deciding which research skill to invoke next, checking current pipeline state, or sizing a simulation before configuration and module creation.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, clearly sequenced orchestrator skill with strong validation discipline, held back by command-table redundancy and a lack of file-based progressive disclosure for a body of this length.

Suggestions

Collapse the Progress File Quick Reference table or the repeated git-commit examples into one canonical block to remove duplication and recover tokens.

Move the Skill Index and Pipeline Map (or the reroute state-machine detail) into a references/ file linked from a short overview, enabling genuine one-level-deep progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is dense and free of concepts Claude already knows, but the Progress File Quick Reference table duplicates the inline command blocks and the git-commit pattern is restated several times, so it could be tightened.	2 / 3
Actionability	Copy-paste-ready commands with concrete flags ('$PYTHON_PATH .agentsociety/bin/ags.py research-pipeline reroute STAGE --reason "TEXT" --source-artifact PATH') plus explicit current_stage → skill routing tables give fully executable guidance.	3 / 3
Workflow Clarity	The pipeline is clearly sequenced with a DOT graph, entry conditions, hard constraints, and explicit checkpoints (git commit after every update-stage, 'Always run experiment-config check before run-experiment') plus reroute feedback loops for error recovery.	3 / 3
Progressive Disclosure	Sections and tables are well organized, but the ~250-line SKILL.md is monolithic with no signaled one-level-deep references (the bundled scripts/progress.py is never linked from the body), so reference-style content lives inline.	2 / 3
	Total	10 / 12 Passed

Description

85%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A well-structured description with an explicit Use-when trigger and several concrete actions, though its trigger phrasing is more procedural than conversational and its routing role overlaps with the skills it dispatches to.

Suggestions

Add natural user-facing trigger phrases (e.g., 'where am I in the research pipeline', 'what skill should I run next', 'size a simulation') alongside the procedural wording.

Sharpen distinctiveness by foregrounding the orchestrator/state-checking role (e.g., 'Routes and resumes the AgentSociety research pipeline; use this to check progress or pick the next skill, not to run a single stage directly').

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'starting or resuming an AgentSociety research workspace, deciding which research skill to invoke next, checking current pipeline state, or sizing a simulation before configuration and module creation' — matching the multi-action anchor.	3 / 3
Completeness	An explicit 'Use when...' clause supplies the trigger conditions while the enumerated actions answer what the skill does, satisfying both what and when.	3 / 3
Trigger Term Quality	Relevant terms ('research workspace', 'pipeline state', 'sizing a simulation') are present but lean procedural/technical rather than the natural phrasings a user would say, and common variations are missing.	2 / 3
Distinctiveness Conflict Risk	The AgentSociety research niche is identifiable, but as a meta-router it dispatches to the same sibling skills it could be confused with, leaving overlap risk with similar research skills.	2 / 3
	Total	10 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: tsinghua-fib-lab/AgentSociety
Path: extension/skills/agentsociety-research-pipeline/v1.0.0/SKILL.md
Commit: 1832bcb

Reviewed: about 6 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.