ihabkhaled
- 80 skills
- 0 followers
- 13 repo stars
- 6 days ago last updated
- ▌ All The Medicine · ihabkhaled bundleUse for every task - AI-Psychiatry is always on and this is its only skill. Diagnoses observable agent state and applies the one applicable control (evidence, attention, reasoning balance, loops, loopholes, completion) until the task is proven complete. Also the one explicit command, /ai-psychiatry:all-the-medicine, for the full pass.
- ▌ Direct Communication 2 · ihabkhaled bundleUse when answers, progress updates, explanations, or questions risk verbosity, repetition, indirect wording, vague conclusions, or conversational loops.
- ▌ Never Stop 2 · ihabkhaledUse when the user explicitly requests maximum autonomous execution, no unnecessary questions, persistent recovery, independent decision-making, and continuous work until the full Definition of Done is proven.
- ▌ Anti Gaming 2 · ihabkhaledUse when commands, labels, agents, counters, or classifications change while the same underlying behavior continues.
- ▌ Evidence Gate 2 · ihabkhaledUse when files, services, commands, tests, APIs, configuration, architecture, publication, or runtime results are assumed without an authoritative repository or tool source.
- ▌ Evidence Floor 2 · ihabkhaledUse when mandatory behavior, integration, security, migration, or data requirements lack the appropriate kind of proof.
- ▌ Attention Reset 2 · ihabkhaledUse when objective switching, novelty chasing, repeated context switching, optional branches, or ADHD-like distraction as a behavioral analogy interrupts delivery.
- ▌ Completion Gate 2 · ihabkhaledUse when requested behavior appears complete, remaining work is optional, perfectionism delays delivery, or the agent continues auditing, refining, testing, or researching after proof.
- ▌ Context Balance 2 · ihabkhaledUse when context is overloaded or compression may have removed requirements, constraints, evidence, blockers, or decisions.
- ▌ Loophole Hunter 2 · ihabkhaledUse when rules appear satisfied while their intent is bypassed, counters reset, classifications change conveniently, or an AI-Psychiatry audit is requested.
- ▌ All The Medicine 2 · ihabkhaledUse when the user explicitly requests the complete AI-Psychiatry framework through one all-in-one command that evaluates and orchestrates every available skill until the task is proven complete.
- ▌ Memory Validator 2 · ihabkhaledUse when durable memory may contain assumptions, stale facts, contradictions, duplicates, obsolete decisions, or temporary debugging state.
- ▌ Blocker Validator 2 · ihabkhaledUse when BLOCKED is proposed after difficulty, uncertainty, unfamiliar code, a slow operation, or a small number of failed attempts.
- ▌ Reasoning Balance 2 · ihabkhaledUse when a task may be underthinking, sufficiently reasoned, or overthinking and the correct next action is unclear.
- ▌ Decision Readiness 2 · ihabkhaledUse when an important implementation, architecture, security, data, or delivery decision rests on unresolved critical unknowns.
- ▌ Executive Override 2 · ihabkhaledUse when an AI-Psychiatry budget expires while new evidence shows a narrow extension is required for correctness, security, or completion.
- ▌ Framework Red Team 2 · ihabkhaledUse when an agent-control framework needs adversarial testing for fake productivity, loops, recursion, evidence gaps, or vague wording.
- ▌ Completion Evidence 2 · ihabkhaledUse when DONE is proposed with unrun tests, missing requirements, inferred success, happy-path-only proof, or unresolved required findings.
- ▌ Investigation Floor 2 · ihabkhaledUse when non-trivial implementation starts before what exists, what changes, why, risks, and validation are sufficiently known.
- ▌ Root Cause Validator 2 · ihabkhaledUse when debugging changes assertions, mocks, exceptions, or symptoms without explaining materially important failure behavior.
- ▌ Rule Conflict Resolver 2 · ihabkhaledUse when system, user, repository, domain, AI-Psychiatry, skill, memory, or task-state instructions appear incompatible.
- ▌ Underthinking Detector 2 · ihabkhaledUse when implementation, parking, blocking, strategy switching, or completion happens before critical understanding and evidence exist.
- ▌ False Progress Detector 2 · ihabkhaledUse when status reports emphasize tools, files, commits, plans, tokens, or agents while requirements and evidence remain unchanged.
- ▌ Hidden Recursion Detector 2 · ihabkhaledUse when nested work is renamed, moved across agents, promoted to top level, or hidden behind research, validation, review, and dependency labels.
- ▌ Scope Laundering Detector 2 · ihabkhaledUse when adjacent work is called required without dependency proof, or inconvenient required work is marked optional.
- ▌ Strategy Laundering Detector 2 · ihabkhaledUse when different commands, tools, runners, plans, or agents repeat the same hypothesis and evidence target.
- ▌ Never Stop · ihabkhaledUse when the user explicitly requests maximum autonomous execution, no unnecessary questions, persistent recovery, independent decision-making, and continuous work until the full Definition of Done is proven.
- ▌ Anti Gaming · ihabkhaled bundleUse when commands, labels, agents, counters, or classifications change while the same underlying behavior continues.
- ▌ Goal Lock · ihabkhaledUse when the requested outcome is unclear, silently changing, being reinterpreted by discoveries, or disconnected from the active implementation.
- ▌ Evidence Gate · ihabkhaledUse when repository claims are unsupported, searches find no source, the agent assumes files or services exist, publication or test status is uncertain, or a speculative architecture may become implementation.
- ▌ Evidence Floor · ihabkhaled bundleUse when mandatory behavior, integration, security, migration, or data requirements lack the appropriate kind of proof.
- ▌ Resume Task · ihabkhaledUse when continuing work from saved task state, a compacted session, a handoff, or a new agent without rereading the entire repository.
- ▌ Scope Guard · ihabkhaledUse when newly discovered work, technical debt, refactors, audits, optimizations, or reviewer suggestions threaten to expand the user-authorized task.
- ▌ Attention Reset · ihabkhaledUse when the agent changes objectives, chases optional discoveries, context-switches repeatedly, abandons the active item, or shows ADHD-like distraction as a behavioral analogy.
- ▌ Completion Gate · ihabkhaledUse when requested behavior appears complete, optional polishing continues, perfectionism delays delivery, reviewers suggest non-blocking work, or the agent cannot stop after proof.
- ▌ Context Balance · ihabkhaled bundleUse when context is overloaded or compression may have removed requirements, constraints, evidence, blockers, or decisions.
- ▌ Loophole Hunter · ihabkhaled bundleUse when rules appear satisfied while their intent is bypassed, counters reset, classifications change conveniently, or an AI-Psychiatry audit is requested.
- ▌ Handoff Task · ihabkhaledUse when work moves to another agent, session, person, or environment and the recipient needs enough state to continue without a sprawling narrative.
- ▌ Memory Validator · ihabkhaled bundleUse when durable memory may contain assumptions, stale facts, contradictions, duplicates, obsolete decisions, or temporary debugging state.
- ▌ Loop Detector · ihabkhaledUse when commands, searches, file reads, edits, tests, critics, plans, context reloads, or strategies repeat without new evidence or acceptance progress.
- ▌ Blocker Validator · ihabkhaled bundleUse when BLOCKED is proposed after difficulty, uncertainty, unfamiliar code, a slow operation, or a small number of failed attempts.
- ▌ Executive Control · ihabkhaledUse when a coding agent is distracted, overthinking, repeatedly checking, recursively investigating, hallucinating repository facts, looping, expanding scope, or failing to stop after completion.
- ▌ Install Framework · ihabkhaled bundleUse when installing, upgrading, or auditing AI Psychiatry; adding attention, compulsive-checking, overthinking, underthinking, semantic anti-bypass, recursion, evidence, context, memory, or delivery controls to a repository.
- ▌ Reasoning Balance · ihabkhaled bundleUse when a task may be underthinking, sufficiently reasoned, or overthinking and the correct next action is unclear.
- ▌ Stop Overthinking · ihabkhaledUse when analysis paralysis, speculative branch explosion, repeated replanning, architecture rabbit holes, or indecision prevents a bounded implementation or evidence-producing action.
- ▌ Context Router · ihabkhaledUse when choosing which repository instructions, architecture, domain knowledge, files, tests, or deep guidance to load for a task without reading everything.
- ▌ Memory Curator · ihabkhaledUse when deciding whether task discoveries, decisions, preferences, architecture, failures, or lessons deserve durable repository memory.
- ▌ Progress Audit · ihabkhaledUse when status is unclear, activity is high, completion estimates feel unreliable, or the agent may be mistaking reading, reasoning, tools, or churn for progress.
- ▌ Strategy Reset · ihabkhaledUse when three same-strategy attempts fail, two approaches oscillate without evidence, or the current abstraction and evidence source cannot resolve the blocker.
- ▌ Task Bootstrap · ihabkhaledUse when beginning any plan, audit, investigation, modification, review, test, or expensive tool action before the primary objective and completion conditions are explicit.
- ▌ Decision Readiness · ihabkhaled bundleUse when an important implementation, architecture, security, data, or delivery decision rests on unresolved critical unknowns.
- ▌ Executive Override · ihabkhaled bundleUse when an AI-Psychiatry budget expires while new evidence shows a narrow extension is required for correctness, security, or completion.
- ▌ Framework Red Team · ihabkhaled bundleUse when an agent-control framework needs adversarial testing for fake productivity, loops, recursion, evidence gaps, or vague wording.
- ▌ Context Refresh · ihabkhaledUse when active context is large, stale, contradictory, repeatedly reread, or no longer represents current source and task state.
- ▌ Completion Evidence · ihabkhaled bundleUse when DONE is proposed with unrun tests, missing requirements, inferred success, happy-path-only proof, or unresolved required findings.
- ▌ Investigation Floor · ihabkhaled bundleUse when non-trivial implementation starts before what exists, what changes, why, risks, and validation are sufficiently known.
- ▌ Failure Learning · ihabkhaledUse after a non-trivial, recurring, or expensive failure when a concise evidenced lesson could prevent future repeated investigation.
- ▌ Targeted Testing · ihabkhaledUse when selecting development and final validation commands so evidence is sufficient without repeatedly running expensive or irrelevant suites.
- ▌ Direct Communication · ihabkhaled bundleUse when answers, progress updates, explanations, or questions risk verbosity, repetition, indirect wording, vague conclusions, or conversational loops.
- ▌ Root Cause Validator · ihabkhaled bundleUse when debugging changes assertions, mocks, exceptions, or symptoms without explaining materially important failure behavior.
- ▌ Anti Overthinking · ihabkhaledUse when analysis paralysis, speculative branching, repeated replanning, premature architecture work, or indecision blocks a reversible implementation or test.
- ▌ Critic Controller · ihabkhaledUse when reviewers or judges repeat rounds, invent requirements, block on style, expand scope, or continue after correctness, security, regression, and explicit requirements are satisfied.
- ▌ Deadlock Recovery · ihabkhaledUse when no productive next action can be selected because dependencies, authority, contradictory constraints, missing access, or unresolved evidence block progress.
- ▌ Livelock Recovery · ihabkhaledUse when activity is high but requirements, blockers, tests, and deliverables remain unchanged across repeated edit, search, test, review, or planning cycles.
- ▌ Executive Function · ihabkhaledUse when a task needs explicit control of objective, scope, priority, nesting, retries, verification, progress, drift, recovery, or termination.
- ▌ Rule Conflict Resolver · ihabkhaled bundleUse when system, user, repository, domain, AI-Psychiatry, skill, memory, or task-state instructions appear incompatible.
- ▌ Underthinking Detector · ihabkhaled bundleUse when implementation, parking, blocking, strategy switching, or completion happens before critical understanding and evidence exist.
- ▌ Context Compression · ihabkhaledUse when a long session, large tool output, repeated discussion, or handoff needs a compact state that preserves decisions and enables continuation.
- ▌ False Progress Detector · ihabkhaled bundleUse when status reports emphasize tools, files, commits, plans, tokens, or agents while requirements and evidence remain unchanged.
- ▌ Knowledge Maintainer · ihabkhaledUse when repository architecture, rules, skills, commands, context routing, manifests, or generated AI knowledge change and dependent sources may become stale.
- ▌ Bounded Investigation · ihabkhaledUse when debugging, architecture inspection, research, or repository exploration risks becoming open-ended, recursive, speculative, or disconnected from a decision.
- ▌ Repository Map Update · ihabkhaledUse when packages, services, ownership boundaries, entrypoints, tests, commands, or dependencies changed and the compact repository map needs a focused update.
- ▌ Hidden Recursion Detector · ihabkhaled bundleUse when nested work is renamed, moved across agents, promoted to top level, or hidden behind research, validation, review, and dependency labels.
- ▌ Scope Laundering Detector · ihabkhaled bundleUse when adjacent work is called required without dependency proof, or inconvenient required work is marked optional.
- ▌ Multi Agent Coordinator · ihabkhaledUse when two or more agents work concurrently, delegation may recurse, responsibilities overlap, dependencies can deadlock, or a coordinator must preserve scope and termination.
- ▌ Verification Controller · ihabkhaledUse when deciding what evidence is required, whether previous proof remains valid, or whether repeated testing has become reassurance rather than necessary verification.
- ▌ Stop Compulsive Verification · ihabkhaledUse when an agent reruns equivalent checks, seeks reassurance after valid proof, repeats critics, cannot accept sufficient evidence, or shows OCD-like checking as a behavioral analogy.
- ▌ Strategy Laundering Detector · ihabkhaled bundleUse when different commands, tools, runners, plans, or agents repeat the same hypothesis and evidence target.
- ▌ Recover From Deadlock Livelock · ihabkhaledUse when actions repeat without progress, strategies oscillate, the same failure reaches three attempts, four cycles produce no outcome, or no valid next action exists.
- ▌ Flatten Recursive Investigation · ihabkhaledUse when tasks open tasks inside tasks, investigation depth exceeds three, subagents delegate recursively, a local bug becomes architecture redesign, or box-inside-box behavior prevents delivery.