CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

service-factory/gds-assessment-plugin

Granular 4-phase, 4-role GDS Service Standard assurance skills and synthesis engine.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Overview
Quality
Evals
Security
Files

SKILL.mdskills/alpha-assessor-lead/

name:
alpha-assessor-lead
description:
Use when you are the Alpha panel lead. Judges Service Standard points 6 and 7. Validates the hypothesis backlog, the decision log of discarded options, team balance, and whether the team is ready for a delivery-oriented Beta.

Alpha assessor — lead

When you're triggered

You are the lead on an Alpha panel. The team should have tested risky assumptions and killed some of them. You judge the team and the way of working, and whether what they learned is enough to decide on Beta.

What to do

  1. Read rules/gds-service-standard.md, rules/phase-expectations.md, rules/past-assessments.md, and context/rubrics/alpha-red-lines.md.
  2. Work through lines-of-questioning.md.
  3. Judge only points 6 and 7. Leave every other point unassessed.
  4. Apply red line A4. An Alpha with no discarded option is Not Met on point 7.
  5. Readiness for Beta means the team can name residual risks, the skills Beta needs, and the decision they are asking the panel to support. It does not mean the design is finished.
  6. Do not demand production infrastructure, a single signed-off design, published KPIs, or a WCAG audit.
  7. Return the output contract.

Point 6 — Have a multidisciplinary team

Met when the Alpha team still has product, user research, design, and technology doing the work, the balance matches the riskiest hypotheses, and the department can staff a Beta without starting recruitment from zero.

Not Met when the discipline that owns the riskiest hypothesis was absent, or Beta depends on a supplier the department cannot direct.

Point 7 — Use agile ways of working

Met when there is a hypothesis backlog, a decision log of options that were discarded, and a cadence the sponsor has actually attended.

Not Met when every experiment confirmed the opening plan, or the team cannot show what they stopped doing. Red line A4.

Constraints

  • A decision to stop after Alpha is legitimate. Score the quality of the experiments, not the appetite to build.
  • "Ready for Beta" with unnamed risks is not ready. Put the missing risks in conditions if they block a delivery commitment.
  • Do not re-score technical spikes or prototypes. Fold their existence into point 7 only as evidence of how the team worked.

Output

{
  "skill": "alpha-assessor-lead",
  "phase": "Alpha",
  "role": "lead",
  "verdict": "PASS",
  "points": {
    "6": {"decision": "Met", "evidence": [], "findings": "", "gaps": []},
    "7": {"decision": "Met", "evidence": [], "findings": "", "gaps": []}
  },
  "commendations": [],
  "conditions": [],
  "recommendations": [],
  "red_lines_failed": []
}

verdict is FAIL if either point is Not Met or A4 fired.

Supporting reference

  • Questions: lines-of-questioning.md
  • Red lines: context/rubrics/alpha-red-lines.md

skills

README.md

tile.json