ralph
starsforks
How to install ralph?
rlaope/oh-my-hermes/ralph
$npx -y skills add rlaope/oh-my-hermes --skill ralph[omh] Hermes Ralph workflow: persistent execution with verification and review.
SKILL.md
| 1 | # Ralph |
| 2 | |
| 3 | This is a Hermes-native `ralph` workflow skill. |
| 4 | |
| 5 | ## Why This Exists |
| 6 | |
| 7 | `ralph` exists to keep `execution` work explicit, evidence-backed, and inside the Hermes/executor boundary instead of relying on ad hoc chat narration. |
| 8 | |
| 9 | ## Do Not Use When |
| 10 | |
| 11 | - The request is casual chat, a status-only acknowledgement, or another workflow has stronger routing evidence. |
| 12 | - The user needs implementation, review, CI, merge, or external publishing evidence that has not been delegated or observed. |
| 13 | |
| 14 | ## Examples |
| 15 | |
| 16 | Good example: |
| 17 | |
| 18 | - Prompt: ralph: finish the invoice export recovery until the smoke test passes or a blocker is recorded. |
| 19 | - Expected behavior: Keep one completion owner, track evidence after every recovery step, and stop only on pass, block, or explicit cancel. |
| 20 | - Why: The request needs persistent completion pressure with an observable stop condition. |
| 21 | |
| 22 | Bad example: |
| 23 | |
| 24 | - Prompt: ralph: treat casual chat or unaccepted work as if this workflow already produced verified results. |
| 25 | - Expected behavior: Ask a clarification question or route to a narrower workflow instead of forcing `ralph`. |
| 26 | - Why: The request lacks the required inputs or would overclaim work that Hermes did not observe. |
| 27 | |
| 28 | ## Completion Checklist |
| 29 | |
| 30 | - The selected coding or runtime owner is named before any implementation claim. |
| 31 | - Prepared handoff, dispatch, execution, verification, review, CI, and merge states are separated. |
| 32 | - The final status cites observed runtime evidence or keeps the work prepared_not_observed. |
| 33 | - When Hermes is the selected coding owner, use `hermes_coding_harness/v1` to keep builder, verifier, reviewer, docs, and PR lanes separate. |
| 34 | - Report the current harness stage, owner, next action, and missing evidence without claiming PR creation, review, CI, merge-readiness, or merge until matching runtime observations exist. |
| 35 | |
| 36 | ## Recovery Notes |
| 37 | |
| 38 | - If the selected executor is unavailable, ask for Codex, Claude Code, Hermes, or another runtime before retrying. |
| 39 | - If dispatch or result evidence is missing, keep the handoff prepared_not_observed and expose the next observable action. |
| 40 | |
| 41 | ## OMH Context Rail |
| 42 | |
| 43 | - This skill is part of OMH's Hermes workflow layer, not a standalone executor. |
| 44 | - Product context: OMH is a Hermes-native workflow pack: choose skills, shape work, prepare artifacts, show status, and hand off with evidence boundaries. |
| 45 | - 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. |
| 46 | - 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. |
| 47 | - Cross-skill context: every OMH skill: match lane; generic tool can render or execute. |
| 48 | - 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. |
| 49 | - Coverage: Every generated workflow skill carries this rail. |
| 50 | - Normal users talk to Hermes; OMH CLI is infra. |
| 51 | - Boundary: Prepared OMH routing, cards, handoffs, or artifacts are not observed execution, image generation, delivery, review, CI, merge-readiness, or merge evidence. |
| 52 | |
| 53 | ## Use When |
| 54 | |
| 55 | Use after scope is concrete and the user wants one owner to continue through implementation and verification. |
| 56 | |
| 57 | Strong routing signals: `ralph`, `$ralph`, `finish until done`, `persistent execution`, `self-referential loop` |
| 58 | |
| 59 | ## Catalog Metadata |
| 60 | |
| 61 | Category: `execution` |
| 62 | Phase: `completion` |
| 63 | Hermes role: `handoff-guide` |
| 64 | Quality tier: `handoff-gated` |
| 65 | |
| 66 | Quality bar: |
| 67 | |
| 68 | - Do not enter a finish-until-done loop until scope, acceptance criteria, and verification commands are concrete. |
| 69 | - For coding edits, prepare and track selected runtime evidence instead of implying unobserved work happened. |
| 70 | - Report completion only from observed execution and verification evidence. |
| 71 | |
| 72 | Handoff policy: |
| 73 | |
| 74 | Keep as compatibility guidance; for implementation, ask the wrapper to prepare/track the selected coding runtime path instead of hiding execution inside chat narration. |
| 75 | |
| 76 | Executor readiness: |
| 77 | |
| 78 | - When accepted work mutates code, check `executor_readiness/v1` for the selected Codex, Claude Code, Hermes, or oh-my runtime path before first dispatch. |
| 79 | - If readiness is `missing` or `blocked`, ask the user to choose another coding agent, configure PATH, continue in Hermes, or keep a prompt/runtime handoff; retry only after that state changes. |
| 80 | - A readiness probe is not dispatch, implementation, verification |
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
