Enriches each user story's acceptance criteria with a "Relevant constraints" line pointing to the specific architecture decisions, implementation heuristics, design principles, and UI kit that apply to that story. Use this skill after any phase that introduces new constraints — after architecture decisions are written (Phase 3), after the UI kit is approved (Phase 4), and after implementation heuristics and design principles are established (Phase 5). Also invoke whenever a Phase 6 agent reads the acceptance criteria and lacks a clear picture of which constraints govern a particular story. Safe to re-run at any phase — each invocation only adds constraints not already listed; nothing is ever removed from an existing entry.
70
85%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Passed
No findings from the security scan
Adds a **Relevant constraints:** line to each user story's section in requirements/mvp/acceptance-criteria.md, pointing to the architecture decisions, implementation heuristics, design principles, and UI kit that a Phase 6 agent needs to consult when building and verifying that story.
Acceptance criteria are written in Phase 1, before architecture and implementation guidance exist. A Phase 6 agent reading only the criteria knows what "done" looks like but not which architectural constraints govern how to get there. The **Relevant constraints:** line bridges this gap: it is not a criterion itself but a navigation guide — the specific documents that constrain this story's implementation.
This skill accumulates entries across the project lifecycle. Each invocation appends constraints not already present; it never removes existing entries. After Phases 3, 4, and 5 have each triggered this skill, the acceptance criteria for every story contain the full picture of constraints relevant to Phase 6.
Read the following before starting:
requirements/mvp/acceptance-criteria.md — the file to enrichrequirements/mvp/user-stories.md — to understand each story's scope and subject matterdocs/architecture/decisions/ — all decision files presentdocs/architecture/decisions/design-principles.md — if presentrequirements/mvp/implementation-heuristics.md — if presentChecking for a UI kit: Read requirements/mvp/architecture.md or docs/architecture/decisions/frontend.md to identify where UI components are expected to live in the project. If that component directory exists and contains files, a UI kit is present and should be noted as a constraint for all front-end stories.
For each story section, identify which documents contain constraints that directly govern building or verifying that story. The test: if this constraint were violated during implementation, would this story's verification fail or the implementation be structurally wrong?
Do not list a document as a constraint for every story. Relevance is specific: an agent reading the constraint line should immediately understand why that document matters for this story.
For each story section (## [US-XX] Story title):
**Relevant constraints:** line if it exists — it appears at the bottom of the section, after all criteria checkboxes and before the next ## [US-XX] heading.Place all constraints on a single line. Use the file path as a code span, followed by a brief parenthetical naming the relevant section or concept:
**Relevant constraints:** `docs/architecture/decisions/frontend.md` (rendering model), `docs/architecture/decisions/auth.md` (session model), `requirements/mvp/implementation-heuristics.md` (heuristics 2, 5)For the UI kit, write: UI kit components (all front-end UI must use kit components).
Read only the documents that currently exist. If an expected document is not yet present — for example, requirements/mvp/implementation-heuristics.md before Phase 5 completes — skip it and do not note its absence as a constraint gap. The skill will be re-run after that document is written.
Before finishing, verify:
requirements/mvp/acceptance-criteria.md has a **Relevant constraints:** lineAll output must be in English.
c5bcbb3
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.