Local Agentic Workforce Builder Pack
by John Barros
Architects human-supervised local AI operations with shared memory, SOP playbooks, and strict approval gates.
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
48 skills found
by John Barros
Architects human-supervised local AI operations with shared memory, SOP playbooks, and strict approval gates.
Strip AI linguistic tells and monotonous structures to make text and TTS scripts sound written by a real person.
by Matthew King
Punchy, honest, useful articles that read human, not AI, in a voice you will be proud to publish.
Strips the AI fingerprint from prose by enforcing human-like rhythm, asymmetry, and concrete word choice.
by Romeo Apps
Secure local password broker for AI agents with human-in-the-loop GUI and encrypted storage.
by Ivan Fodjo
Deterministic tiered governance and human-in-the-loop guardrails for AI agent write-actions.
Removes the academic-AI fingerprint from clinical and scientific writing to produce expert-level scholarly prose.
A seven-step auditing system that identifies and flags machine-like prose patterns without stripping your original voice.
by Tradeplier
Detect unauthorized drift in your agent's always-loaded files: SHA-256 baselines on a heartbeat, human-gated re-seed by Telegram tap.
by Tradeplier
Gate agent writes behind human approval: single-use tokens, typed fallback when buttons fail, datastore-agnostic by design.
Test an AI or rules-based resume screener for outcome changes, score drift, missing evidence, sensitive-term leakage, and human-review gaps.
Map supported product claims to current channel rules, required artifacts, human-authored fields, and a fail-closed submission-readiness gate.
by Kuan Ee Lau
Turn a weighted hiring rubric and redacted CV text into a locator-backed evidence matrix, unresolved-evidence flags, and mandatory human-review queue.
Flag avoidable oversharing, self-congratulation, forced intimacy, disclosure, and exaggerated claims without punishing sincerity or harmless awkwardness.
Separate observed mutuality and curiosity from inconsistency, intensity, projection, and insufficient evidence without compatibility scores or diagnosis.
Separate possible indirect hostility from brevity, formality, conflict avoidance, cultural variation, and ordinary frustration without declaring intent.
Return the single best-supported detail that deserves one more question, with benign and concerning explanations.
Scan supplied context for overlooked vulnerable people, practical needs, overload, exclusion, and preventable harm without gender stereotypes.
Map who may be affected, how consequences may spread, and which safer alternatives reduce permanence, exposure, or coercion.
Check whether a proposed message or action fits the audience, timing, privacy, power dynamics, and recent context.
Reconcile deletion-request evidence across systems, subprocessors, retention exceptions, and backup replay before human review.
Classify a consequential people-facing action as suitable for automation, revision, delay, human review, human delivery, or no automation.
Rewrite a consequential message without changing its verified facts, decision, boundary, or policy.
Separate information gaps from authority, emotional, safety, and consequence reasons for human takeover, then prepare a compact handoff packet.