BingHanOfUESTC/open_agent_team

Build persistent multi-agent teams that collaborate like real organizations to deliver complex tasks.

106Stars on the repository
200Mods indexed here, across every type
2mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

contamination-guard

73

BingHanOfUESTC/open_agent_team

Skill Claude CodeCodex

Detect and prevent contamination of skills by Boss-provided target outputs, reference answers, examples, task-specific entities, and overfit structures.

not rated 106 +3 2mo ago A 32 tokens original MIT

iteration-workflow

75

BingHanOfUESTC/open_agent_team

Skill Claude CodeCodex

Versioned workflow for evolving skills, executing tasks, evaluating outputs, and deciding whether to continue or stop.

not rated 106 +3 2mo ago A 25 tokens original MIT

BingHanOfUESTC/open_agent_team

Skill Claude CodeCodex

Build and apply evaluation rubrics for generated outputs against Boss expectations without treating reference outputs as text to copy.

not rated 106 +3 2mo ago A 28 tokens original MIT

BingHanOfUESTC/open_agent_team

Skill Claude CodeCodex

Decompose a desired output into reusable skill capabilities, skill boundaries, input/output contracts, and execution order. Use before authoring skills.

not rated 106 +3 2mo ago A 32 tokens original MIT

BingHanOfUESTC/open_agent_team

Skill Claude CodeCodex

Character desire, pressure, contradiction, and choice design for literary short fiction. Use when a story feels concept-driven, characters feel hollow, or revision needs stronger motivation and irreversible decisions.

not rated 106 +3 2mo ago A 41 tokens original MIT

BingHanOfUESTC/open_agent_team

Skill Claude CodeCodex

Short-story opening and narrative pull craft. Use when designing, drafting, critiquing, or revising the first paragraph, first page, and early story promise so the reader has a concrete reason to continue.

not rated 106 +3 2mo ago A 48 tokens original MIT

BingHanOfUESTC/open_agent_team

Skill Claude CodeCodex

Use this skill when checking creative fiction for originality, name safety, public figure misuse, historical figure misuse, news-event overfitting, recognizable plot borrowing, IP-like names, and high-risk homage. Trigger before drafting and before final delivery for storyteam.

not rated 106 +3 2mo ago A 58 tokens original MIT

prose-critique

86

BingHanOfUESTC/open_agent_team

Skill Claude CodeCodex

Adversarial reading methodology for narrative fiction: find what doesn't work, not confirm what does. Focus-area driven with dedicated resources per area. Use when reviewing drafts, evaluating prose quality, or assessing changes at any stage.

not rated 106 +3 2mo ago A SkillSpector: pass 50 tokens original MIT

prose-writing

87

BingHanOfUESTC/open_agent_team

Skill Claude CodeCodex

Prose-level immersion patterns for narrative fiction. Use when writing or revising prose: the sentence-level and paragraph-level craft that pulls readers into the story. Project-specific voice comes from style files passed alongside this skill.

not rated 106 +3 2mo ago A 47 tokens original MIT

reader-impact-test

88

BingHanOfUESTC/open_agent_team

Skill Claude CodeCodex

Reader-experience testing for fiction drafts. Use when judging whether a story is actually gripping, where attention drops, whether emotional beats land, and whether the ending leaves a memorable aftereffect.

not rated 106 +3 2mo ago A 41 tokens original MIT

BingHanOfUESTC/open_agent_team

Skill Claude CodeCodex

Verify whether a revised fiction draft actually complied with critic and reader feedback. Use after revision output and before critic re-review.

not rated 106 +3 2mo ago A 30 tokens original MIT

revision-routing

90

BingHanOfUESTC/open_agent_team

Skill Claude CodeCodex

Route fiction revision feedback to the correct upstream or downstream agent instead of sending every problem to the editor. Use after critic and reader reports, before revision planning.

not rated 106 +3 2mo ago A SkillSpector: pass 34 tokens original MIT

revision-workflow

91

BingHanOfUESTC/open_agent_team

Skill Claude CodeCodex

Versioned fiction revision workflow. Use when coordinating critique-revision loops, applying review findings, proving that changes were actually made, and deciding whether a draft has passed or needs another revision.

not rated 106 +3 2mo ago A 41 tokens original MIT

scene-construction

92

BingHanOfUESTC/open_agent_team

Skill Claude CodeCodex

How to build scenes: entry, dialogue, pacing, transitions. Use when writing or evaluating how scenes work on the page.

not rated 106 +3 2mo ago A 29 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: