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

72%

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

Fix and improve this skill with Tessl

tessl review fix ./extension/skills/agentsociety-research-pipeline/v1.0.0/SKILL.md

Quality

Content

70%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 orchestrator skill body: routing, sequencing, validation gates, and audit rules are explicit and executable, with excellent workflow clarity. Its weaknesses are redundant restatement of the git-checkpoint and reroute rules, an undefined `$PYTHON_PATH` placeholder, and no navigation to the bundled `scripts/progress.py`.

Suggestions

Consolidate the git-commit rules into the single Git Checkpoint Discipline section and reference it once from Hard Constraints instead of restating the rules in Workspace Initialization, Stage Transitions, and Rules.

Split the reroute semantics (the 6-step numbered list and stage-state rules) and the command quick reference into a separate reference file, and link to them from the body to reduce inline bulk.

Define how `$PYTHON_PATH` should be resolved (or drop the placeholder), and reference the bundled `scripts/progress.py` so the tooling layer of the skill is discoverable.

Dimension	Reasoning	Score
Conciseness	The body is dominated by dense tables and copy-ready commands with no explanations of known concepts, but the git-commit discipline is repeated across four sections (Workspace Initialization, Stage Transitions, Rules, Hard Constraints) and reroute semantics are restated multiple times, so it could be meaningfully tightened — anchor 3 rather than 4.	3 / 5
Actionability	Concrete, mostly copy-paste commands appear throughout (`research-pipeline update-stage STAGE STATUS`, the fully realized reroute example with reason and source artifact), but `$PYTHON_PATH` is never defined and `ags.py` is not part of the bundle — minor gaps that keep it below anchor 5.	4 / 5
Workflow Clarity	The sequence is explicit with entry-condition routing, a produces/consumes pipeline map, and hard validation gates ("Always run `experiment-config check` before `run-experiment`", "Never run analysis before... `_schema.json`") plus error-recovery feedback loops (failed stage → owning-skill repair, run → config on failed validation, auditable reroute), matching anchor 5.	5 / 5
Progressive Disclosure	Sections are clearly organized, but all detail lives inline in a ~255-line body: the bundle's `scripts/progress.py` (26 KB) is never referenced from the body, and the reroute semantics and command reference are prime candidates for a separate file — anchor 3 ("content that should be separate is inline"), not 4 given the completely un-signaled bundle file.	3 / 5
	Total	15 / 20 Passed

Description

75%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, trigger-rich description that clearly signals when to use the skill and names several concrete actions within the AgentSociety niche. Its main weakness is that the capability statement is buried inside when-clauses rather than led with, and a few natural trigger variations are absent.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "deciding which research skill to invoke next", "checking current pipeline state", "sizing a simulation" — but the core capability (orchestration/routing) is only implicit in the when-clauses rather than explicitly stated, so it falls short of anchor 5's comprehensive action list.	4 / 5
Completeness	An explicit "Use when..." clause is present and detailed, and the what is conveyed through the enumerated actions, but the description leads with when rather than a clear statement of what the skill does, fitting anchor 4 ("'when' could be more explicit or specific" inverted: here 'what' could be more explicit).	4 / 5
Trigger Term Quality	Phrases like "starting or resuming an AgentSociety research workspace" and "checking current pipeline state" read as natural user utterances, but common variations ("which skill next", "where am I", "next step") are missing, matching anchor 4 rather than 5's comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	"AgentSociety research workspace" carves a clear niche, but "sizing a simulation before configuration and module creation" overlaps the experiment-config and create-module skills' territory, giving minor overlap risk consistent with anchor 4 rather than 5's minimal-conflict clear niche.	4 / 5
	Total	16 / 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: 8cc5bb9

Reviewed: 6 days 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.