all publishers

ihabkhaled

@ihabkhaled source repo

80 published skills

  1. ▌
    All The Medicine · ihabkhaled bundle
    Use 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.
    13 repo stars
  2. ▌
    Direct Communication 2 · ihabkhaled bundle
    Use when answers, progress updates, explanations, or questions risk verbosity, repetition, indirect wording, vague conclusions, or conversational loops.
    13 repo stars
  3. ▌
    Never Stop 2 · ihabkhaled
    Use 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.
    13 repo stars
  4. ▌
    Anti Gaming 2 · ihabkhaled
    Use when commands, labels, agents, counters, or classifications change while the same underlying behavior continues.
    13 repo stars
  5. ▌
    Evidence Gate 2 · ihabkhaled
    Use when files, services, commands, tests, APIs, configuration, architecture, publication, or runtime results are assumed without an authoritative repository or tool source.
    13 repo stars
  6. ▌
    Evidence Floor 2 · ihabkhaled
    Use when mandatory behavior, integration, security, migration, or data requirements lack the appropriate kind of proof.
    13 repo stars
  7. ▌
    Attention Reset 2 · ihabkhaled
    Use when objective switching, novelty chasing, repeated context switching, optional branches, or ADHD-like distraction as a behavioral analogy interrupts delivery.
    13 repo stars
  8. ▌
    Completion Gate 2 · ihabkhaled
    Use when requested behavior appears complete, remaining work is optional, perfectionism delays delivery, or the agent continues auditing, refining, testing, or researching after proof.
    13 repo stars
  9. ▌
    Context Balance 2 · ihabkhaled
    Use when context is overloaded or compression may have removed requirements, constraints, evidence, blockers, or decisions.
    13 repo stars
  10. ▌
    Loophole Hunter 2 · ihabkhaled
    Use when rules appear satisfied while their intent is bypassed, counters reset, classifications change conveniently, or an AI-Psychiatry audit is requested.
    13 repo stars
  11. ▌
    All The Medicine 2 · ihabkhaled
    Use 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.
    13 repo stars
  12. ▌
    Memory Validator 2 · ihabkhaled
    Use when durable memory may contain assumptions, stale facts, contradictions, duplicates, obsolete decisions, or temporary debugging state.
    13 repo stars
  13. ▌
    Blocker Validator 2 · ihabkhaled
    Use when BLOCKED is proposed after difficulty, uncertainty, unfamiliar code, a slow operation, or a small number of failed attempts.
    13 repo stars
  14. ▌
    Reasoning Balance 2 · ihabkhaled
    Use when a task may be underthinking, sufficiently reasoned, or overthinking and the correct next action is unclear.
    13 repo stars
  15. ▌
    Decision Readiness 2 · ihabkhaled
    Use when an important implementation, architecture, security, data, or delivery decision rests on unresolved critical unknowns.
    13 repo stars
  16. ▌
    Executive Override 2 · ihabkhaled
    Use when an AI-Psychiatry budget expires while new evidence shows a narrow extension is required for correctness, security, or completion.
    13 repo stars
  17. ▌
    Framework Red Team 2 · ihabkhaled
    Use when an agent-control framework needs adversarial testing for fake productivity, loops, recursion, evidence gaps, or vague wording.
    13 repo stars
  18. ▌
    Completion Evidence 2 · ihabkhaled
    Use when DONE is proposed with unrun tests, missing requirements, inferred success, happy-path-only proof, or unresolved required findings.
    13 repo stars
  19. ▌
    Investigation Floor 2 · ihabkhaled
    Use when non-trivial implementation starts before what exists, what changes, why, risks, and validation are sufficiently known.
    13 repo stars
  20. ▌
    Root Cause Validator 2 · ihabkhaled
    Use when debugging changes assertions, mocks, exceptions, or symptoms without explaining materially important failure behavior.
    13 repo stars
  21. ▌
    Rule Conflict Resolver 2 · ihabkhaled
    Use when system, user, repository, domain, AI-Psychiatry, skill, memory, or task-state instructions appear incompatible.
    13 repo stars
  22. ▌
    Underthinking Detector 2 · ihabkhaled
    Use when implementation, parking, blocking, strategy switching, or completion happens before critical understanding and evidence exist.
    13 repo stars
  23. ▌
    False Progress Detector 2 · ihabkhaled
    Use when status reports emphasize tools, files, commits, plans, tokens, or agents while requirements and evidence remain unchanged.
    13 repo stars
  24. ▌
    Hidden Recursion Detector 2 · ihabkhaled
    Use when nested work is renamed, moved across agents, promoted to top level, or hidden behind research, validation, review, and dependency labels.
    13 repo stars
  25. ▌
    Scope Laundering Detector 2 · ihabkhaled
    Use when adjacent work is called required without dependency proof, or inconvenient required work is marked optional.
    13 repo stars
  26. ▌
    Strategy Laundering Detector 2 · ihabkhaled
    Use when different commands, tools, runners, plans, or agents repeat the same hypothesis and evidence target.
    13 repo stars
  27. ▌
    Never Stop · ihabkhaled
    Use 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.
    13 repo stars
  28. ▌
    Anti Gaming · ihabkhaled bundle
    Use when commands, labels, agents, counters, or classifications change while the same underlying behavior continues.
    13 repo stars
  29. ▌
    Goal Lock · ihabkhaled
    Use when the requested outcome is unclear, silently changing, being reinterpreted by discoveries, or disconnected from the active implementation.
    13 repo stars
  30. ▌
    Evidence Gate · ihabkhaled
    Use 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.
    13 repo stars
  31. ▌
    Evidence Floor · ihabkhaled bundle
    Use when mandatory behavior, integration, security, migration, or data requirements lack the appropriate kind of proof.
    13 repo stars
  32. ▌
    Resume Task · ihabkhaled
    Use when continuing work from saved task state, a compacted session, a handoff, or a new agent without rereading the entire repository.
    13 repo stars
  33. ▌
    Scope Guard · ihabkhaled
    Use when newly discovered work, technical debt, refactors, audits, optimizations, or reviewer suggestions threaten to expand the user-authorized task.
    13 repo stars
  34. ▌
    Attention Reset · ihabkhaled
    Use when the agent changes objectives, chases optional discoveries, context-switches repeatedly, abandons the active item, or shows ADHD-like distraction as a behavioral analogy.
    13 repo stars
  35. ▌
    Completion Gate · ihabkhaled
    Use when requested behavior appears complete, optional polishing continues, perfectionism delays delivery, reviewers suggest non-blocking work, or the agent cannot stop after proof.
    13 repo stars
  36. ▌
    Context Balance · ihabkhaled bundle
    Use when context is overloaded or compression may have removed requirements, constraints, evidence, blockers, or decisions.
    13 repo stars
  37. ▌
    Loophole Hunter · ihabkhaled bundle
    Use when rules appear satisfied while their intent is bypassed, counters reset, classifications change conveniently, or an AI-Psychiatry audit is requested.
    13 repo stars
  38. ▌
    Handoff Task · ihabkhaled
    Use when work moves to another agent, session, person, or environment and the recipient needs enough state to continue without a sprawling narrative.
    13 repo stars
  39. ▌
    Memory Validator · ihabkhaled bundle
    Use when durable memory may contain assumptions, stale facts, contradictions, duplicates, obsolete decisions, or temporary debugging state.
    13 repo stars
  40. ▌
    Loop Detector · ihabkhaled
    Use when commands, searches, file reads, edits, tests, critics, plans, context reloads, or strategies repeat without new evidence or acceptance progress.
    13 repo stars
  41. ▌
    Blocker Validator · ihabkhaled bundle
    Use when BLOCKED is proposed after difficulty, uncertainty, unfamiliar code, a slow operation, or a small number of failed attempts.
    13 repo stars
  42. ▌
    Executive Control · ihabkhaled
    Use when a coding agent is distracted, overthinking, repeatedly checking, recursively investigating, hallucinating repository facts, looping, expanding scope, or failing to stop after completion.
    13 repo stars
  43. ▌
    Install Framework · ihabkhaled bundle
    Use 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.
    13 repo stars
  44. ▌
    Reasoning Balance · ihabkhaled bundle
    Use when a task may be underthinking, sufficiently reasoned, or overthinking and the correct next action is unclear.
    13 repo stars
  45. ▌
    Stop Overthinking · ihabkhaled
    Use when analysis paralysis, speculative branch explosion, repeated replanning, architecture rabbit holes, or indecision prevents a bounded implementation or evidence-producing action.
    13 repo stars
  46. ▌
    Context Router · ihabkhaled
    Use when choosing which repository instructions, architecture, domain knowledge, files, tests, or deep guidance to load for a task without reading everything.
    13 repo stars
  47. ▌
    Memory Curator · ihabkhaled
    Use when deciding whether task discoveries, decisions, preferences, architecture, failures, or lessons deserve durable repository memory.
    13 repo stars
  48. ▌
    Progress Audit · ihabkhaled
    Use when status is unclear, activity is high, completion estimates feel unreliable, or the agent may be mistaking reading, reasoning, tools, or churn for progress.
    13 repo stars
  49. ▌
    Strategy Reset · ihabkhaled
    Use when three same-strategy attempts fail, two approaches oscillate without evidence, or the current abstraction and evidence source cannot resolve the blocker.
    13 repo stars
  50. ▌
    Task Bootstrap · ihabkhaled
    Use when beginning any plan, audit, investigation, modification, review, test, or expensive tool action before the primary objective and completion conditions are explicit.
    13 repo stars
  51. ▌
    Decision Readiness · ihabkhaled bundle
    Use when an important implementation, architecture, security, data, or delivery decision rests on unresolved critical unknowns.
    13 repo stars
  52. ▌
    Executive Override · ihabkhaled bundle
    Use when an AI-Psychiatry budget expires while new evidence shows a narrow extension is required for correctness, security, or completion.
    13 repo stars
  53. ▌
    Framework Red Team · ihabkhaled bundle
    Use when an agent-control framework needs adversarial testing for fake productivity, loops, recursion, evidence gaps, or vague wording.
    13 repo stars
  54. ▌
    Context Refresh · ihabkhaled
    Use when active context is large, stale, contradictory, repeatedly reread, or no longer represents current source and task state.
    13 repo stars
  55. ▌
    Completion Evidence · ihabkhaled bundle
    Use when DONE is proposed with unrun tests, missing requirements, inferred success, happy-path-only proof, or unresolved required findings.
    13 repo stars
  56. ▌
    Investigation Floor · ihabkhaled bundle
    Use when non-trivial implementation starts before what exists, what changes, why, risks, and validation are sufficiently known.
    13 repo stars
  57. ▌
    Failure Learning · ihabkhaled
    Use after a non-trivial, recurring, or expensive failure when a concise evidenced lesson could prevent future repeated investigation.
    13 repo stars
  58. ▌
    Targeted Testing · ihabkhaled
    Use when selecting development and final validation commands so evidence is sufficient without repeatedly running expensive or irrelevant suites.
    13 repo stars
  59. ▌
    Direct Communication · ihabkhaled bundle
    Use when answers, progress updates, explanations, or questions risk verbosity, repetition, indirect wording, vague conclusions, or conversational loops.
    13 repo stars
  60. ▌
    Root Cause Validator · ihabkhaled bundle
    Use when debugging changes assertions, mocks, exceptions, or symptoms without explaining materially important failure behavior.
    13 repo stars
  61. ▌
    Anti Overthinking · ihabkhaled
    Use when analysis paralysis, speculative branching, repeated replanning, premature architecture work, or indecision blocks a reversible implementation or test.
    13 repo stars
  62. ▌
    Critic Controller · ihabkhaled
    Use when reviewers or judges repeat rounds, invent requirements, block on style, expand scope, or continue after correctness, security, regression, and explicit requirements are satisfied.
    13 repo stars
  63. ▌
    Deadlock Recovery · ihabkhaled
    Use when no productive next action can be selected because dependencies, authority, contradictory constraints, missing access, or unresolved evidence block progress.
    13 repo stars
  64. ▌
    Livelock Recovery · ihabkhaled
    Use when activity is high but requirements, blockers, tests, and deliverables remain unchanged across repeated edit, search, test, review, or planning cycles.
    13 repo stars
  65. ▌
    Executive Function · ihabkhaled
    Use when a task needs explicit control of objective, scope, priority, nesting, retries, verification, progress, drift, recovery, or termination.
    13 repo stars
  66. ▌
    Rule Conflict Resolver · ihabkhaled bundle
    Use when system, user, repository, domain, AI-Psychiatry, skill, memory, or task-state instructions appear incompatible.
    13 repo stars
  67. ▌
    Underthinking Detector · ihabkhaled bundle
    Use when implementation, parking, blocking, strategy switching, or completion happens before critical understanding and evidence exist.
    13 repo stars
  68. ▌
    Context Compression · ihabkhaled
    Use when a long session, large tool output, repeated discussion, or handoff needs a compact state that preserves decisions and enables continuation.
    13 repo stars
  69. ▌
    False Progress Detector · ihabkhaled bundle
    Use when status reports emphasize tools, files, commits, plans, tokens, or agents while requirements and evidence remain unchanged.
    13 repo stars
  70. ▌
    Knowledge Maintainer · ihabkhaled
    Use when repository architecture, rules, skills, commands, context routing, manifests, or generated AI knowledge change and dependent sources may become stale.
    13 repo stars
  71. ▌
    Bounded Investigation · ihabkhaled
    Use when debugging, architecture inspection, research, or repository exploration risks becoming open-ended, recursive, speculative, or disconnected from a decision.
    13 repo stars
  72. ▌
    Repository Map Update · ihabkhaled
    Use when packages, services, ownership boundaries, entrypoints, tests, commands, or dependencies changed and the compact repository map needs a focused update.
    13 repo stars
  73. ▌
    Hidden Recursion Detector · ihabkhaled bundle
    Use when nested work is renamed, moved across agents, promoted to top level, or hidden behind research, validation, review, and dependency labels.
    13 repo stars
  74. ▌
    Scope Laundering Detector · ihabkhaled bundle
    Use when adjacent work is called required without dependency proof, or inconvenient required work is marked optional.
    13 repo stars
  75. ▌
    Multi Agent Coordinator · ihabkhaled
    Use when two or more agents work concurrently, delegation may recurse, responsibilities overlap, dependencies can deadlock, or a coordinator must preserve scope and termination.
    13 repo stars
  76. ▌
    Verification Controller · ihabkhaled
    Use when deciding what evidence is required, whether previous proof remains valid, or whether repeated testing has become reassurance rather than necessary verification.
    13 repo stars
  77. ▌
    Stop Compulsive Verification · ihabkhaled
    Use 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.
    13 repo stars
  78. ▌
    Strategy Laundering Detector · ihabkhaled bundle
    Use when different commands, tools, runners, plans, or agents repeat the same hypothesis and evidence target.
    13 repo stars
  79. ▌
    Recover From Deadlock Livelock · ihabkhaled
    Use when actions repeat without progress, strategies oscillate, the same failure reaches three attempts, four cycles produce no outcome, or no valid next action exists.
    13 repo stars
  80. ▌
    Flatten Recursive Investigation · ihabkhaled
    Use 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.
    13 repo stars