loop
starsforks
How to install loop?
rlaope/oh-my-hermes/loop
$npx -y skills add rlaope/oh-my-hermes --skill loop[omh] Hermes Loop workflow: agentic interviewer -> planner -> researcher -> builder -> reviewer cycles until a real gate.
SKILL.md
| 1 | # Loop |
| 2 | |
| 3 | This is a Hermes-native `loop` workflow skill. |
| 4 | |
| 5 | ## Why This Exists |
| 6 | |
| 7 | `loop` exists for goals whose correct implementation cannot be known upfront but can be discovered through bounded cycles of definition, action, verification, and revision without confusing planned cycles with observed progress. |
| 8 | |
| 9 | ## Do Not Use When |
| 10 | |
| 11 | - The user asks for one bounded delivery cycle; use `ultraprocess` or `ultragoal` instead. |
| 12 | - The user gives only a north-star outcome such as revenue, stars, or adoption and has not accepted a bounded first loop goal. |
| 13 | - The goal is too vague to name an observable problem, next artifact, verification signal, or stop condition. |
| 14 | - The goal depends mainly on external waiting, adoption, revenue, or community response without observable local next actions. |
| 15 | - The permission profile does not allow repeated research, handoff, queue, or feedback cycles. |
| 16 | |
| 17 | ## Examples |
| 18 | |
| 19 | Good example: |
| 20 | |
| 21 | - Prompt: ./loop make OMH a credible Hermes workflow pack with install, docs, QA, and feedback cycles. |
| 22 | - Expected behavior: Start a permission-scoped loop, maintain loop_cycle/v1 state, choose the next concrete task, and keep external outcomes as waiting states. |
| 23 | - Why: The request is long-horizon and needs repeated discovery, verification, feedback, and resume decisions. |
| 24 | |
| 25 | Bad example: |
| 26 | |
| 27 | - Prompt: ./loop merge this already reviewed one-line README fix. |
| 28 | - Expected behavior: Use a direct delivery or PR workflow instead of starting a persistent loop. |
| 29 | - Why: The task is bounded and should stop after merge evidence rather than create ongoing cycles. |
| 30 | |
| 31 | ## Completion Checklist |
| 32 | |
| 33 | - The request is classified as task, project, north-star ambition, external-wait, or unclear before a loop starts. |
| 34 | - The current loop_status_card/v1 names the queue item, tick status, verification_plan, and next action. |
| 35 | - failure_mode_summary checks verification_gap, comprehension_debt, and cognitive_surrender before progress advances. |
| 36 | - Completion is backed by linked goal/runtime evidence; queued loop ticks alone are not observed work. |
| 37 | |
| 38 | ## Recovery Notes |
| 39 | |
| 40 | - If a queued tick is pending, show it as prepared queue state and use loop status/run-once before claiming progress. |
| 41 | - If feedback is unclear, ask one gate question or route back to research/plan rather than advancing the loop. |
| 42 | - If the goal turns into external waiting, record the waiting state and next observable signal instead of continuing locally. |
| 43 | - If context or budget is exhausted, checkpoint the loop artifact and continue from the latest loop_cycle/v1 state. |
| 44 | |
| 45 | ## OMH Context Rail |
| 46 | |
| 47 | - This skill is part of OMH's Hermes workflow layer, not a standalone executor. |
| 48 | - Product context: OMH is a Hermes-native workflow pack: choose skills, shape work, prepare artifacts, show status, and hand off with evidence boundaries. |
| 49 | - Current lane: **Intent -> plan** (`oh-my-hermes`, `deep-interview`, `plan`, `ralplan`, `codebase-onboarding`, `codegraph-refresh`, `ultragoal`, `ultraprocess`, `+3 more`) - clarify, plan, ship, or loop goals. |
| 50 | - If the user intent belongs to another OMH lane, hand back to `oh-my-hermes` or name the adjacent workflow instead of force-fitting this skill. |
| 51 | - Cross-skill context: every OMH skill: match lane; generic tool can render or execute. |
| 52 | - Generic-tool checkpoint: image->img-summary; frontend->frontend/a11y/visual-qa; paper->paper-learning; content->content-operator; media->media-input-operator; file->materials-package; search->web-research; live->live-info-operator; audit->workspace/production/security; failures->build-failure; verify->verification-gate; code->codegraph/onboarding/ultraprocess. |
| 53 | - Coverage: Every generated workflow skill carries this rail. |
| 54 | - Normal users talk to Hermes; OMH CLI is infra. |
| 55 | - Boundary: Prepared OMH routing, cards, handoffs, or artifacts are not observed execution, image generation, delivery, review, CI, merge-readiness, or merge evidence. |
| 56 | |
| 57 | ## Use When |
| 58 | |
| 59 | Use when the user starts a high-level goal or invokes loop. Direct loop invocation means start/continue through interviewer, planner, researcher, builder, reviewer, and loop-controller lanes until a real gate stops it. |
| 60 | |
| 61 | Strong routing signals: `loop`, `./loop`, `$loop`, `goal loop`, `long horizon goal`, `never stop`, `research plan ultragoal feedback`, `token exhaustion resume`, `permission profile`, `star 10k`, `10k star`, `loop engineering`, `루프`, `목표 루프`, `장기 목표`, `끝까지`, `토큰 고갈`, `피드백 루프` |
| 62 | |
| 63 | ## Catalog Metadata |
| 64 | |
| 65 | Category: `goal-loop` |
| 66 | Phase: `continuous-goal-loop` |
| 67 | Hermes role: `planner` |
| 68 | Quality tier: `loop-gated` |
| 69 | |
| 70 | Quality bar: |
| 71 | |
| 72 | - Treat direct `loop`, `./loop`, `$loop`, and OMH loop invocations as a start/continue signal rather than a picker or passive clarification path. |
| 73 | - Classify the go |
People who liked this also viewed
6 picksType
- find-skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skSkillsJul 2026
- grill-meA relentless interview to sharpen a plan or design.SkillsJul 2026
- vercel-react-best-practicesVercel's official collection of agent skillsSkillsJul 2026
- improve-codebase-architectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.SkillsJul 2026
- setup-matt-pocock-skillsConfigure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.SkillsJul 2026
- triageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.SkillsJul 2026
