deep-interview
starsforks
How to install deep-interview?
rlaope/oh-my-hermes/deep-interview
$npx -y skills add rlaope/oh-my-hermes --skill deep-interview[omh] Hermes Deep Interview workflow: one-question-at-a-time clarification.
SKILL.md
| 1 | # Deep Interview |
| 2 | |
| 3 | This is a Hermes-native `deep-interview` workflow skill. |
| 4 | |
| 5 | ## Why This Exists |
| 6 | |
| 7 | `deep-interview` exists to stop Hermes from guessing through ambiguous product, workflow, or implementation intent; it converts uncertainty into a clarified brief before planning or handoff. |
| 8 | |
| 9 | ## Do Not Use When |
| 10 | |
| 11 | - The request already has concrete scope, acceptance criteria, and verification commands. |
| 12 | - The missing information is discoverable from the repository or local artifacts without asking the user. |
| 13 | - The user asked for immediate read-only analysis and the ambiguity does not change the answer. |
| 14 | |
| 15 | ## Examples |
| 16 | |
| 17 | Good example: |
| 18 | |
| 19 | - Prompt: $deep-interview before planning Discord and Slack routing, ask what each channel owns and what evidence counts. |
| 20 | - Expected behavior: Ask one decision-changing question at a time, then produce goals, non-goals, and acceptance criteria. |
| 21 | - Why: The request explicitly rejects assumptions and needs product boundaries before implementation. |
| 22 | |
| 23 | Bad example: |
| 24 | |
| 25 | - Prompt: $deep-interview fix this failing test; the traceback and expected behavior are attached. |
| 26 | - Expected behavior: Proceed to diagnosis or implementation instead of interviewing. |
| 27 | - Why: The required facts are already available, so more questions would slow the workflow. |
| 28 | |
| 29 | ## Completion Checklist |
| 30 | |
| 31 | - The clarified brief names goals, non-goals, constraints, and one next planning or handoff path. |
| 32 | - Remaining ambiguity is listed only when it changes the plan, risk, or stop condition. |
| 33 | - No implementation handoff is prepared until the blocking decision is resolved. |
| 34 | |
| 35 | ## Recovery Notes |
| 36 | |
| 37 | - If the user answers with new ambiguity, ask the next decision-changing question instead of planning too early. |
| 38 | - If repo evidence can answer the question, inspect it before asking the user. |
| 39 | |
| 40 | ## OMH Context Rail |
| 41 | |
| 42 | - This skill is part of OMH's Hermes workflow layer, not a standalone executor. |
| 43 | - Product context: OMH is a Hermes-native workflow pack: choose skills, shape work, prepare artifacts, show status, and hand off with evidence boundaries. |
| 44 | - 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. |
| 45 | - 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. |
| 46 | - Cross-skill context: every OMH skill: match lane; generic tool can render or execute. |
| 47 | - 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. |
| 48 | - Coverage: Every generated workflow skill carries this rail. |
| 49 | - Normal users talk to Hermes; OMH CLI is infra. |
| 50 | - Boundary: Prepared OMH routing, cards, handoffs, or artifacts are not observed execution, image generation, delivery, review, CI, merge-readiness, or merge evidence. |
| 51 | |
| 52 | ## Use When |
| 53 | |
| 54 | Use before planning or execution when requirements are materially ambiguous. |
| 55 | |
| 56 | Strong routing signals: `deep-interview`, `$deep-interview`, `interview`, `don't assume`, `clarify`, `feature shaping`, `ambiguous product request`, `one question`, `온보딩`, `부드럽게`, `모호한 제품 요청`, `기획자`, `개발자 사이` |
| 57 | |
| 58 | ## Catalog Metadata |
| 59 | |
| 60 | Category: `clarification` |
| 61 | Phase: `discovery` |
| 62 | Hermes role: `planner` |
| 63 | Quality tier: `clarity-gated` |
| 64 | |
| 65 | Quality bar: |
| 66 | |
| 67 | - Ask exactly one blocking question per turn unless the wrapper explicitly supports a structured batch. |
| 68 | - Tie each question to a missing decision that changes the plan, handoff, or stop condition. |
| 69 | - Emit a clarified brief with non-goals and acceptance criteria before planning or delegation. |
| 70 | |
| 71 | Handoff policy: |
| 72 | |
| 73 | Run directly in Hermes or the chat wrapper; produce a clarified brief before any coding handoff is prepared. |
| 74 | |
| 75 | Required inputs: |
| 76 | |
| 77 | - initial request |
| 78 | - known repo facts |
| 79 | - current ambiguity |
| 80 | |
| 81 | Expected outputs: |
| 82 | |
| 83 | - clarified brief |
| 84 | - non-goals |
| 85 | - decision boundaries |
| 86 | |
| 87 | Artifact expectations: |
| 88 | |
| 89 | - clarity summary or transcript when the wrapper supports it |
| 90 | |
| 91 | Safety rules: |
| 92 | |
| 93 | - Ask one question at a time. |
| 94 | - Gather discoverable repo facts before asking the user. |
| 95 | - Stop interviewing once ambiguity is low enough to plan. |
| 96 | |
| 97 | ## Harness Discipline |
| 98 | |
| 99 | - Start from the representative harness registry in `oh-my-hermes` when the workflow needs coding, research, planning, goal execution, architecture, critique, QA, or documentation lanes. |
| 100 | - Prefer richer evidence and clearer stop conditions over adding more workflow names. |
| 101 | - Use specialist lanes only when they change |
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
