github.com/asklokesh/loki-mode
| Skill | Added | Review |
|---|---|---|
checkpoint-mode examples/agent-skills/checkpoint-mode/SKILL.md Pauses for human review every N tasks (selective autonomy). Use when work needs short autonomous bursts with feedback instead of one long run. | 52 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 30f0227 | |
loki-mode SKILL.md Runs an autonomous software factory that knows what it is supposed to deliver and proves it did, with a signed receipt. Use when the user says Loki Mode or asks to build, fix or verify software autonomously. | 52 Impact — No eval scenarios have been run Securityby — The risk profile of this skill Version: 4861678 | |
loki-mode-openclaw integrations/openclaw/SKILL.md Launch Loki Mode autonomous SDLC agent. Handles PRD-to-deployment with minimal human intervention. Invoke for multi-phase development tasks, bug fixing campaigns, or full product builds. | 64 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 4861678 | |
loki-seal packages/loki-seal/skills/loki-seal/SKILL.md Use when finishing any coding task in a repo with tests. Loki Seal runs the repo's real test suite and refuses to let you declare done while tests newly fail, or while tests or CI config were deleted, skipped, xfailed or weakened. Runs locally with no model calls. | 68 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 4861678 | |
prompt-optimization examples/agent-skills/prompt-optimization/SKILL.md Applies prompt repetition to improve accuracy for non-reasoning LLMs. Use when a Haiku or other non-reasoning agent misses details in a long prompt. | 64 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 30f0227 |