agentic workflow
by Sinu
A risk-aware, evidence-based engineering lifecycle protocol for robust agentic task execution and safety.
New: Skill bounties are live. Post a request, fund the bounty, and creators compete for 7 days to build it -> See open bounties
THE AGENSI STORE
25 skills found
by Sinu
A risk-aware, evidence-based engineering lifecycle protocol for robust agentic task execution and safety.
by Roy Yuen
Design and audit complex multi-agent workflows with rigorous ownership, evidence gates, and failure recovery policies.
by Roy Yuen
Enforce explicit context discipline, artifact-gated transitions, and verification evidence for AI agent workflows.
One-line summary description Stop your agent from claiming "done" before it's proven. A verification gate that classifies each change by risk (payment, auth, database, user-facing), picks the tests that actually cover it, demands evidence, maps regression risk, and outputs an honest pass/fail report. Turns "looks good to me" into "here's what I ran, and here's what's still unverified."
Runs an ordered evidence-integrity gate over any AI draft — grade sources, ground claims, verify technical assertions, stress-test — then returns one PASS/REVISE/FAIL ship decision.
Turn a messy investment idea into an evidence-first thesis audit with weak points, disconfirming data, and next research actions.
by Al1as
A high-discipline decision-governance layer to prevent AI agents from acting on poor evidence or conflicting goals.
Audit AI-assisted medical and pharma content for compliance-readiness before it enters formal MLR review or journal submission. It checks claim substantiation and on-label scope, reference integrity (the acute AI risk: fabricated or misrepresented citations), fair balance and safety, AI-use disclosure, ICMJE authorship and GPP, COI and funding, data integrity and patient privacy, and adverse-event flags — then returns a PASS / REVISE / BLOCK verdict with the must-fix list. A readiness pre-check built for the regulated reality of medical communications — not a replacement for formal review.
by Corey Jacobs
Automated compatibility testing and evidence generation for MCP servers against Codex and Qwen clients.
An evidence-based 7-pillar security gate for AI-assisted apps to prevent leaks, IDOR, and infrastructure gaps.
by NORTHSTAR
Cross-check shipment documents for critical mismatches before release.
Reconcile SDK, required-reason API, data-use, privacy-manifest, and questionnaire evidence before an App Store release.
Reconcile Android target API, developer verification, app registration, signing identity, distribution scope, extension, and console evidence.
Verify customer-specific invoice fields, attachments, destination, submission receipt, acceptance status, correction version, and aging start.
Map supported product claims to current channel rules, required artifacts, human-authored fields, and a fail-closed submission-readiness gate.
Block unsupported resume claims, invented metrics, and unattributed first-person founder statements.
Rank evidence-backed distribution tests by buyer intent, rules, attribution, access, budget, and qualified outcome gates.
Find direction, logical-CSS, interpolation, icon-mirroring, and render-evidence gaps before an RTL release.
Reconcile price, availability, and evidence-backed claim meaning across multilingual commerce surfaces.
Audit one completed channel test against its predeclared qualified gate, attribution, owner exclusion, budgets, changed variables, and cooldown.
Reconcile owner-defined AI transparency scope with labels, notices, technical markings, and release claims.
Gate a release on consistent SBOM, VEX, identifier, relationship, and artifact-digest evidence.
Verify an AI coding task against required rows, dependencies, evidence, artifacts, and real external boundaries before the agent declares completion or hands off.
by Jiangdongbo
Navigate international labor disputes with statutory calculations, evidence checklists, and procedural guidance.