skillhone-prd
Interactively gather a PRD (Product Requirements Document) for an agent skill that is about to be built or optimized by SkillHone. Use when the user says things like "I want to write a new skill", "help me spec this skill", "what should <x>-skill do", or before running `skillhone new` / `skillhone optim` on a skill whose requirements aren't fully nailed down. The interview is driven through the `AskUserQuestion` tool — every round is a small set of dependent multi-choice questions, and the skill keeps asking until the user says stop. Final artifacts are three files in the paired `<skill>-eval`
npx skills add Tencent/SkillHone --skill skillhone-prd --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# skillhone-prd — Interactive PRD builder for skills ## Why this skill exists Before SkillHone can meaningfully optimize a skill, **three things must be unambiguous**: what the skill is trying to achieve (goal), what environment it runs in (tools), and how its outputs will be judged (evaluation — both the structural format and the scoring rubric). Writing ordinary product PRDs doesn't cut it — a skill PRD is primarily an **evaluation contract**, not a feature list. This skill drives a multi-round interview via `AskUserQuestion` and emits three files into the paired `<skill>-eval` repo: - **`PRD.md`** — full PRD, including evaluation criteria. Visible to the **eval agent only**. - **`PRD.improver_only.md`** — same PRD with section 4 (Evaluation) stripped. Visible to the **improver / iter agent**. - **`PRD.choice.md`** — full question/answer transcript. Eval artifact; never published to the skill wiki. The split is deliberate: if the improver sees its own grading rubric, Goodhart's Law takes over within a few iterations. ## The three dimensions to pin down (in this order) A skill PRD is structurally analogous to an RL problem spec: | RL concept | Skill PRD dimension | Why it comes wh
- Why this skill exists
- The three dimensions to pin down (in this order)
- Interaction contract — use AskUserQuestion, always
- Hard rules for questions
- Choice log
- Question gate — only ask when the answer changes the PRD
- Funnel principle
- Stop condition — only the user can stop
- Workflow (you decide the order)
- Where to write the PRDs
- Forgejo wiki publishing
- What lives in which file
- Gotchas
- Anti-patterns
python3 scripts/write_prd.py \
What does the skillhone-prd skill do?
Interactively gather a PRD (Product Requirements Document) for an agent skill that is about to be built or optimized by SkillHone. Use when the user says things like "I want to write a new skill", "help me spec this skill", "what should <x>-skill do", or before running `skillhone new` / `skillhone optim` on a skill whose requirements aren't fully nailed down. The interview is driven through the `AskUserQuestion` tool — every round is a small set of dependent multi-choice questions, and the skill keeps asking until the user says stop. Final artifacts are three files in the paired `<skill>-eval`
How do I install it?
Run `npx skills add Tencent/SkillHone --skill skillhone-prd --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From Tencent/SkillHone, a repository with 107 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.