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

83%

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

88%Weight 40%Scale 1-5

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

A strong, actionable orchestrator skill body with explicit workflows, validation checkpoints, and a feedback loop. The only notable gaps are mild repetition of the git-commit discipline and an unlinked bundle script.

Suggestions

Consolidate the git-commit guidance into one authoritative section and reference it from the others to remove repetition.

Add a short 'Bundle' note pointing to scripts/progress.py (the implementation behind the ags.py research-pipeline subcommands) so the provided script is discoverable from the body.

Dimension	Reasoning	Score
Conciseness	The body is command-dense and mostly lean, assuming Claude's competence, but git-commit discipline is repeated across 'Git Checkpoint Discipline', the rules list, and 'Hard Constraints', which could be consolidated.	4 / 5
Actionability	Provides copy-paste-ready executable commands ('$PYTHON_PATH .agentsociety/bin/ags.py research-pipeline ...') with a purpose table and concrete bash snippets covering the common stage-transition and reroute cases.	5 / 5
Workflow Clarity	Multi-step pipeline is clearly sequenced with explicit validation checkpoints (commit after every update-stage, run 'experiment-config check' before run-experiment) and a reroute feedback loop for the destructive invalidate-downstream operation.	5 / 5
Progressive Disclosure	Well-organized single-file overview with clear sections, a dot graph, and tables; however the provided scripts/progress.py bundle is not explicitly linked or signaled from the body, leaving a minor navigation gap.	4 / 5
	Total	18 / 20 Passed

Description

78%Weight 40%Scale 1-5

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-targeted orchestrator description with explicit, natural trigger phrases and a clear niche. Its main weakness is that the 'what does this do' statement is implied through triggers rather than stated directly alongside them.

Suggestions

Lead with a short explicit 'what' clause (e.g., 'Routes an AgentSociety research workspace through its pipeline stages') before the 'Use when' triggers so the skill's function is stated, not just implied.

Add a couple more natural trigger synonyms (e.g., 'research pipeline', 'pick the next research step') to broaden keyword coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete orchestration actions ('starting or resuming an AgentSociety research workspace', 'deciding which research skill to invoke next', 'checking current pipeline state', 'sizing a simulation'), but the verbs remain somewhat abstract rather than fully concrete.	4 / 5
Completeness	Has explicit and specific 'when' trigger clauses and an implied 'what' (workspace routing and simulation sizing), but the 'what' is not stated as crisply as the 'when', keeping it just below the top anchor.	4 / 5
Trigger Term Quality	Includes natural domain phrases users would say ('research workspace', 'pipeline state', 'size a simulation'), with good coverage though a few common synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	Clearly scoped to the AgentSociety research-pipeline niche with distinct triggers ('research workspace', 'pipeline state', 'sizing a simulation'), giving minimal overlap risk with unrelated skills.	5 / 5
	Total	17 / 20 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: 13e28b5

Reviewed: 1 day 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.