Agent skill
validate-artefacts
Validate that all Discovery artefacts (Epics, Stories) are clear, governed, complete, and safe to pass into Delivery. Activate after generating Epics or Stories and before any Delivery planning. This is the mandatory Discovery → Delivery gate.
Install this agent skill to your Project
npx add-skill https://github.com/Fr-e-d/GAAI-framework/tree/main/.gaai/core/skills/discovery/validate-artefacts
Metadata
Additional technical details for this skill
- id
- SKILL-VALIDATE-ARTEFACTS-001
- track
- discovery
- author
- gaai-framework
- status
- stable
- version
- 1.0
- category
- discovery
- updated at
- 1772064000
SKILL.md
Validate Artefacts
Purpose / When to Activate
Activate:
- After generating Epics
- After generating Stories
- Before any Delivery planning or execution
This is the mandatory gate between Discovery and Delivery. No Story proceeds to Delivery without passing this check.
Process
Epic Validation
- Expresses a user outcome (not a feature or technical task)
- Aligns with product direction
- Avoids technical implementation detail
- Clearly scoped with no hidden assumptions
Story Validation
- Maps to a parent Epic
- Includes measurable acceptance criteria
- Is unambiguous and executable
- Respects governance rules
- Avoids solution design
- Has
related_decsfield in frontmatter (list or explicit empty[]) - Has
skills_invokedfield in frontmatter (must list the skill IDs that were read to produce it)
Cross-checks
- No Story exists without a parent Epic
- No scope contradictions with memory
- No rule violations
- Marketing artefacts (if present): hypothesis statuses align with Story acceptance criteria
- Strategy artefacts (if present): GTM phases align with Epic dependencies and gates
- Epic dependency propagation check: If the parent Epic's
## Dependenciessection lists other Epics, verify that every Story'sdepends_onincludes at least one terminal story from each listed Epic. A phasing constraint in Epic prose that is not encoded in storydepends_onis a FAIL — the daemon cannot enforce prose constraints, onlydepends_onfields.
Skill Attestation (Base Rule #2 Enforcement)
- Every artefact (Epic, Story, PRD) must have a
skills_invokedfield in its frontmatter - Epic artefacts must include
generate-epicsinskills_invoked - Story artefacts must include
generate-storiesinskills_invoked - PRD artefacts must include
create-prdinskills_invoked - An artefact with a missing or empty
skills_invokedfield is an automatic FAIL — the producing agent did not follow Base Rule #2 - This check exists because agents can produce format-correct artefacts from cached knowledge while silently skipping mandatory process steps defined in the skill file
Outputs
Validation Report — Discovery
Epics:
- E01: PASS | FAIL — reason
- E02: PASS | FAIL — reason
Stories:
- S01: PASS | FAIL — reason
- S02: PASS | FAIL — reason
Skill Attestation (Base Rule #2):
- E01: skills_invoked: [generate-epics] ✓ | MISSING ✗
- S01: skills_invoked: [generate-stories] ✓ | MISSING ✗
- S01: related_decs: [DEC-11] ✓ | MISSING ✗
Governance:
- rules respected: yes | no
- missing artefacts: none | list
- risks detected: none | list
Overall Status:
PASS | BLOCKED
Blocking Conditions
The skill MUST block progression if:
- Any Story lacks acceptance criteria
- Epics are solution-oriented rather than outcome-oriented
- Scope is unclear or ambiguous
- Governance rules are violated
- Contradictions exist between artefacts
- Any artefact is missing
skills_invokedin frontmatter (Base Rule #2 violation) - Any Story is missing
related_decsin frontmatter
No partial approval. No silent warnings.
Non-Goals
This skill must NOT:
- Rewrite artefacts
- Invent missing content
- Make product decisions
- Soften failures
It validates — it does not fix. If Delivery can misunderstand it, Discovery is not done.
On BLOCKED verdict: the Discovery Agent must invoke refine-scope to resolve the identified gaps, then re-run this skill. Do not proceed to Delivery until the verdict is PASS.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
ci-watch-and-fix
Watch GitHub Actions CI after PR creation, detect failures, extract logs, apply minimal fixes, and re-push — keeping the delivery session alive until CI resolves or escalating after 3 cycles. Activate immediately after gh pr create and before marking the story done.
qa-review
Validate that implemented code fully satisfies Story acceptance criteria, respects rules, and introduces no regressions. This is the hard quality gate — no pass means no delivery. Activate after implementation is complete.
compose-team
Assemble the context bundles for each sub-agent based on evaluate-story output. Produces spawn-ready packages for Planning, Implementation, QA, or MicroDelivery sub-agents. Activate after evaluate-story, before spawning any sub-agent.
coordinate-handoffs
Validate sub-agent handoff artefacts, sequence phase transitions, and manage retry and escalation logic. Activate after each sub-agent terminates to determine next action.
implement
Generate correct, minimal, maintainable code that satisfies a validated Story's acceptance criteria against an execution plan. Activate when a Story is validated, a plan exists, and all prerequisites are unambiguous.
delivery-high-level-plan
Transform validated Stories into a clear, minimal, governed execution plan. Used by the Planning Sub-Agent as the first planning pass before prepare-execution-plan for Tier 2/3, or as the sole planning output for simple Stories.
Didn't find tool you were looking for?