Digital Talent Bench
Talent Bench — AI Agents mapped to 2026–2030 market roles
Roles · Feedback · Teamwork · 7 Skills for Production AI Agents
ReACT Pattern — /adlc Command Flow
Reason → Act → Observe → Answer — PDCA convergence until ≥99.5% & ≥95% agreement
📝
REASON
planner
PDCA: PlanTHINK
🔧
ACTION
doer
PDCA: DoBUILD
✅
OBSERVE
feedback
PDCA: CheckTEST
📊
ANSWER
presenter
PDCA: ActMONITOR
ReACT
PDCA Convergence Target
Autonomous loops until ≥99.5% pass rate · ≥95% agent agreement
99.5%
Pass Rate
95%
Agreement
Gap Analysis Grid
Agent-to-role coverage by category
Critical Thinking Lens
Apply BEFORE any non-trivial recommendation, design decision, or completion claim — the 5W1H matrix, 9 reflection questions, and 5 critical-thinker behaviours every Enterprise team / subagent / talent-bench role inherits via the critical-thinking skill.
5W1H Matrix — pick one cell per dimension and answer it
Who8 starter prompts
- ·Who benefits from this?
- ·Who is this harmful to?
- ·Who makes decisions about this?
- ·Who is most directly affected?
- ·Who have you also heard discuss this?
- ·Who would be the best person to consult?
- ·Who will be the key people in this?
- ·Who deserves recognition for this?
What8 starter prompts
- ·What are the strengths/weaknesses?
- ·What is another perspective?
- ·What is another alternative?
- ·What would be a counter-argument?
- ·What is the best/worst case scenario?
- ·What is most/least important?
- ·What can we do to make a positive change?
- ·What is getting in the way of our action?
Where8 starter prompts
- ·Where would we see this in the real world?
- ·Where are there similar concepts/situations?
- ·Where is there the most need for this?
- ·Where in the world would this be a problem?
- ·Where can we get more information?
- ·Where do we go for help with this?
- ·Where will this idea take us?
- ·Where are the areas for improvement?
When8 starter prompts
- ·When is this acceptable/unacceptable?
- ·When would this benefit our society?
- ·When would this cause a problem?
- ·When is the best time to take action?
- ·When will we know we've succeeded?
- ·When has this played a part in our history?
- ·When can we expect this to change?
- ·When should we ask for help with this?
Why8 starter prompts
- ·Why is this a problem/challenge?
- ·Why is it relevant to me/others?
- ·Why is this the best/worst scenario?
- ·Why are people influenced by this?
- ·Why should people know about this?
- ·Why has it been this way for so long?
- ·Why have we allowed this to happen?
- ·Why is there a need for this today?
How8 starter prompts
- ·How is this similar to ___ ?
- ·How does this disrupt things?
- ·How do we know the truth about this?
- ·How will we approach this safely?
- ·How does this benefit us/others?
- ·How does this harm us/others?
- ·How will we see this in the future?
- ·How can we change this for our good?
9 Reflection Questions — before any recommendation
1How do we know we're solving the right problem?
2How do we know we're solving the problem in the right way? (rigor vs efficiency)
3If we don't know the sources of our problem, how can we determine the root cause?
4How can we break the key question down into smaller questions we can analyse further?
5Once we have one or more hypotheses, how do we structure work to evaluate them?
6What shortcuts might we take under constraints (time pressure) without compromising rigor?
7Does the evidence sufficiently support the conclusions?
8How do we know when we are done? When is the solution good enough?
9How do I communicate the solution clearly and logically to all stakeholders?
5 Critical-Thinker Behaviours — how to embody the lens
#1
Raise mindful questions
Formulate them clearly and precisely.
#2
Collect and assess relevant information
Validate how it might answer the question.
#3
Arrive at well-reasoned conclusions
Test them against relevant criteria and standards.
#4
Think open-mindedly
Recognise and assess assumptions, implications, and practical consequences within alternative systems of thought.
#5
Communicate effectively
Work with others to figure out solutions to complex problems.
Source: HITL discipline (2026-05-15) · Skill SSOT:
.claude/skills/governance/critical-thinking/SKILL.md · Hover any role badge to see the per-role critical-thinking question.Skill Taxonomy Explorer
0 Tier-1 families · 0 skills — click a card or use the filter
Click any card to drill down into the full T2/T3 skill detail and agent mappings.
ONE PLATFORM · FIVE SUB-PRODUCTS
ADLC Framework
ADLC v3.7.3 · 38 agents · 144 commands · 133 skills · 46 hooks · 22 rules · DORA 4/4 Elite
38 agents144 commands133 skills46 hooks22 rulesDORA 4/4 Elite
HOW IT WORKS — 7-PHASE DELIVERY LOOP
THINK
Assumptions surfaced, scope confirmed
/adlc.plan▶
PLAN
Specs become INVEST stories
/ceremony:plan▶
BUILD
Specialists write code with file-lock
/adlc▶
REVIEW
Code reviewer checks quality gates
/adlc▶
TEST
Automated + evidence-gated validation
/adlc▶
SHIP
HITL approves · git, terraform, deploy
git commit▶
REFLECT
DORA collected, retro evidence written
/ceremony:retroTRIGGER TABLE — SAY IT, IT HAPPENS
SPECIALIST ROSTER — TOP 12 UNIVERSAL AGENTS
ENGINEERING PHILOSOPHY
Test-first (RED-GREEN-REFACTOR)
Write a failing test before any implementation code. Rule 6 in coding-discipline.md — prevents testing theater where 128/128 tests pass but the wheel crashes.
Systematic over ad-hoc (PDCA)
Define success criteria before first edit, loop until verified. Rule 4 — transforms 'make it work' into a verifiable goal with evidence.
Evidence over claims (no NATO)
detect-nato-violation.sh blocks any 'complete/done/finished' without a path in tmp/. Completion is proved, not reported.
Simplicity first (KISS + surgical edits)
Maximum 200 LOC per module, no abstractions for single-use code (Rule 2), every changed line traces to the request (Rule 3).
ADOPT IN 3 STEPS — under 5 minutes
Add the framework as a git submodule. All 38 agents, 144 commands, 22 rules, and 46 hooks become active immediately — scoped to your project via CLAUDE.md.local.
1
Add submodule
git submodule add git@github.com:1xOps/adlc-framework.git .adlcPin to a tag — e.g. v3.7.3
2
Symlink config
ln -s .adlc/.claude .claude && ln -s .adlc/.specify .specifyAgents and rules become active immediately
3
Override personas
cp .adlc/.claude/templates/CLAUDE.md.local.template CLAUDE.md.local5-min edit: personas, AWS profiles, quality gates, PII boundary
ADOPT vs BUILD — what's free, what you own
Browse the Agent Marketplace
All 37 enterprise agents available as installable components
Explore in Marketplace →