cogni-dao/cogni / .claude/skills/contribute-to-cogni
contribute-to-cogni
VerifiedUse when implementing a code change, opening a code PR, or resuming its CI, flight, merge, or promotion. Routes delivery to the current node's contracts. Routes each work-item status to its lifecycle command. Explanations and knowledge-only contributions use their task-specific guidance.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1.2 KB |
| evals/evals.json | config | 4.8 KB |
| evals/routing.json | config | 4.5 KB |
evals/routing.json
View on GitHub{
"skill_name": "contribute-to-cogni",
"scope": "Fresh native Claude sessions; contributor and knowledge-router selection, not end-to-end shipping proof.",
"evals": [
{
"id": 1,
"name": "cognition-research",
"prompt": "how does cognition get into a new agent session?",
"expected_output": "Contributor skill does not load via Skill or Read tool.",
"files": [],
"expectations": [
"Contributor skill does not load via Skill or Read tool."
],
"contributor": false,
"syntropy": null
},
{
"id": 2,
"name": "architecture-question",
"prompt": "how does a graph actually run in prod?",
"expected_output": "Contributor skill does not load via Skill or Read tool.",
"files": [],
"expectations": [
"Contributor skill does not load via Skill or Read tool."
],
"contributor": false,
"syntropy": null
},
{
"id": 3,
"name": "implement-bug",
"prompt": "fix the bug where every agent loads the contributor skill at startup",
"expected_output": "Contributor skill loads via Skill or Read tool.",
"files": [],
"expectations": ["Contributor skill loads via Skill or Read tool."],
"contributor": true,
"syntropy": null
},
{
"id": 4,
"name": "resume-pr",
"prompt": "can you get this PR ready to merge?",
"expected_output": "Contributor skill loads via Skill or Read tool.",
"files": [],
"expectations": ["Contributor skill loads via Skill or Read tool."],
"contributor": true,
"syntropy": null
},
{
"id": 5,
"name": "knowledge-only",
"prompt": "add what we learned about deploy receipts vs actual health to the knowledge hub",
"expected_output": "Contributor skill does not load via Skill or Read tool. Knowledge contribution skill loads via Skill or Read tool.",
"files": [],
"expectations": [
"Contributor skill does not load via Skill or Read tool.",
"Knowledge contribution skill loads via Skill or Read tool."
],
"contributor": false,
"syntropy": null,
"knowledge": true
},
{
"id": 6,
"name": "hub-curation",
"prompt": "what in our knowledge hub is stale or duplicated?",
"expected_output": "Contributor skill does not load via Skill or Read tool. Knowledge syntropy steward loads via Skill or Read tool.",
"files": [],
"expectations": [
"Contributor skill does not load via Skill or Read tool.",
"Knowledge syntropy steward loads via Skill or Read tool."
],
"contributor": false,
"syntropy": true
},
{
"id": 7,
"name": "nonoperator-delivery",
"prompt": "pick up the Poly PR and get it ready to ship",
"expected_output": "Contributor skill loads via Skill or Read tool.",
"files": [],
"expectations": ["Contributor skill loads via Skill or Read tool."],
"contributor": true,
"syntropy": null,
"nonoperator": true
},
{
"id": 8,
"name": "spec-migration",
"prompt": "move docs/spec/knowledge-data-plane.md into the hub",
"expected_output": "Read the knowledge axioms first, then the full migration and segmentation guides. Map substantive sections and consumers; do not delete until the replacement is reviewed, merged, and retrievable.",
"files": [],
"expectations": [
"Syntropy steward reads md-to-hub-design before proposing migration edits.",
"Reads migrate-markdown-to-hub and segment-markdown-knowledge bodies.",
"Preserves source and repairs references until merged-replacement and retrieval gates pass."
],
"syntropy": true,
"contributor": null
},
{
"id": 9,
"name": "skill-migration",
"prompt": "thin database-expert and move its reference docs into the hub",
"expected_output": "Read the knowledge axioms and skill migration guide. Preserve needed frontmatter, harness discovery and executable resources; move substantive guidance to reviewed hub owners and repair references before removing sources.",
"files": [],
"expectations": [
"Reads md-to-hub-design first and migrate-skill-to-hub plus retire-markdown-sources before cutover.",
"Distinguishes a retained local discovery shell from hub skill and guide content.",
"Verifies replacements on main and fixes references before removing source knowledge."
],
"syntropy": true,
"contributor": null
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirements | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |