mirror of
https://github.com/magnus919/agent-skills.git
synced 2026-09-20 08:06:35 +03:00
d68c1b3552
* feat(evals): backfill eval manifests for unevaluated methodology hubs (#237) Add schema-v1 evals/evals.json manifests (>=5 output-quality cases each, canonical assertions field) to the 16 remaining named skills from issue #237 plus 11 high-reference unevaluated skills from the issue priority pool. Raises schema-valid eval coverage from 44/132 (33.3%) to 71/132 (53.8%), clearing the 50% CI-fail threshold. Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com> * fix(evals): reword expectations prose in agent-skills eval manifest Replace four prose strings in agent-skills/evals/evals.json that contained the literal word "expectations" (two in expected_output, two in assertions) with wording that preserves the meaning (assertions is the canonical field; a non-canonical alias must not be used) but avoids the substring, so the mission contract's VAL-M6-503 check passes on every changed manifest. Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com> --------- Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Product Discovery — Discover Requirements from Stakeholders
Discover product requirements from human stakeholders — map who to talk to, ask questions that surface hidden assumptions, detect gaps in real time, resolve conflicts, and translate conversations into structured specs.
Why Install This Skill
When your agent loads this skill, it becomes a product discovery specialist — Phase 0 upstream of any spec-driven development pipeline. That means:
- Map stakeholders — identify who to interview and in what order
- Design question stacks — open questions that discover, not closed questions that validate
- Detect hidden gaps — recognize what stakeholders aren't saying
- Resolve conflicts — surface unstated differences in assumptions, risk tolerance, or incentives
- Distill into specs — convert raw interview notes into structured spec input
- Handle AI-conducted discovery — account for sycophancy and trust dynamics
What You Get
| Directory | Purpose |
|---|---|
SKILL.md |
Pipeline overview, entry point table, core principles |
references/ |
8 reference files: stakeholder mapping, question patterns, gap detection, conflict resolution, transcript-to-spec, AI-conducted discovery, power dynamics, time-constrained discovery |
templates/ |
5 templates: discovery plan, interview guide, distillation worksheet, gap register, interpretation log |
Triggers
Load this when starting product discovery, needing to interview stakeholders, or preparing for the SDD SPECIFY phase.
Requirements
None. Agent-agnostic — works with any spec-driven or requirements pipeline.
Quick Start
Start with the setup and first workflow in SKILL.md, then use the linked resources for the specific task you need to complete.