All authors
Claude Skills by ihabkhaled
github.com/ihabkhaled51 skills1 installs116 views
- 14 Ai Native Development1. Create `skills/<name>.md` with the YAML frontmatter (name, summary, task_keywords, applies_to, required_rules, required_context, affected_workspaces, required_tests, required_docs, validation_lane) and the standard body sections. See [skills/README.md](../../skills/README.md). 2. Ensure `task_keywords` will let the context resolver surface it. 3. Link to the rules it enforces and the reviewers it invokes. After any change that affects generated facts, run `npm run knowledge:build` and `npm...Votes: 0GitHub stars: 24
- All The MedicineUse 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.Votes: 0GitHub stars: 6
- Anti GamingUse when commands, labels, agents, counters, or classifications change while the same underlying behavior continues.Votes: 0GitHub stars: 6
- Anti OverthinkingUse when analysis paralysis, speculative branching, repeated replanning, premature architecture work, or indecision blocks a reversible implementation or test.Votes: 0GitHub stars: 6
- Attention ResetUse when objective switching, novelty chasing, repeated context switching, optional branches, or ADHD-like distraction as a behavioral analogy interrupts delivery.Votes: 0GitHub stars: 6
- Blocker ValidatorUse when BLOCKED is proposed after difficulty, uncertainty, unfamiliar code, a slow operation, or a small number of failed attempts.Votes: 0GitHub stars: 6
- Bounded InvestigationUse when debugging, architecture inspection, research, or repository exploration risks becoming open-ended, recursive, speculative, or disconnected from a decision.Votes: 0GitHub stars: 6
- Completion EvidenceUse when DONE is proposed with unrun tests, missing requirements, inferred success, happy-path-only proof, or unresolved required findings.Votes: 0GitHub stars: 6
- Completion GateUse when requested behavior appears complete, remaining work is optional, perfectionism delays delivery, or the agent continues auditing, refining, testing, or researching after proof.Votes: 0GitHub stars: 6
- Context BalanceUse when context is overloaded or compression may have removed requirements, constraints, evidence, blockers, or decisions.Votes: 0GitHub stars: 6
- Context CompressionUse when a long session, large tool output, repeated discussion, or handoff needs a compact state that preserves decisions and enables continuation.Votes: 0GitHub stars: 6
- Context RefreshUse when active context is large, stale, contradictory, repeatedly reread, or no longer represents current source and task state.Votes: 0GitHub stars: 6
- Context RouterUse when choosing which repository instructions, architecture, domain knowledge, files, tests, or deep guidance to load for a task without reading everything.Votes: 0GitHub stars: 6
- Critic ControllerUse when reviewers or judges repeat rounds, invent requirements, block on style, expand scope, or continue after correctness, security, regression, and explicit requirements are satisfied.Votes: 0GitHub stars: 6
- Deadlock RecoveryUse when no productive next action can be selected because dependencies, authority, contradictory constraints, missing access, or unresolved evidence block progress.Votes: 0GitHub stars: 6
- Decision ReadinessUse when an important implementation, architecture, security, data, or delivery decision rests on unresolved critical unknowns.Votes: 0GitHub stars: 6
- Direct CommunicationUse when answers, progress updates, explanations, or questions risk verbosity, repetition, indirect wording, vague conclusions, or conversational loops.Votes: 0GitHub stars: 6
- Evidence FloorUse when mandatory behavior, integration, security, migration, or data requirements lack the appropriate kind of proof.Votes: 0GitHub stars: 6
- Evidence GateUse when files, services, commands, tests, APIs, configuration, architecture, publication, or runtime results are assumed without an authoritative repository or tool source.Votes: 0GitHub stars: 6
- Executive FunctionUse when a task needs explicit control of objective, scope, priority, nesting, retries, verification, progress, drift, recovery, or termination.Votes: 0GitHub stars: 6
- Executive OverrideUse when an AI-Psychiatry budget expires while new evidence shows a narrow extension is required for correctness, security, or completion.Votes: 0GitHub stars: 6
- Failure LearningUse after a non-trivial, recurring, or expensive failure when a concise evidenced lesson could prevent future repeated investigation.Votes: 0GitHub stars: 6
- False Progress DetectorUse when status reports emphasize tools, files, commits, plans, tokens, or agents while requirements and evidence remain unchanged.Votes: 0GitHub stars: 6
- Framework Red TeamUse when an agent-control framework needs adversarial testing for fake productivity, loops, recursion, evidence gaps, or vague wording.Votes: 0GitHub stars: 6
- Goal LockUse when the requested outcome is unclear, silently changing, being reinterpreted by discoveries, or disconnected from the active implementation.Votes: 0GitHub stars: 6
- Handoff TaskUse when work moves to another agent, session, person, or environment and the recipient needs enough state to continue without a sprawling narrative.Votes: 0GitHub stars: 6
- Hidden Recursion DetectorUse when nested work is renamed, moved across agents, promoted to top level, or hidden behind research, validation, review, and dependency labels.Votes: 0GitHub stars: 6
- Investigation FloorUse when non-trivial implementation starts before what exists, what changes, why, risks, and validation are sufficiently known.Votes: 0GitHub stars: 6
- Knowledge MaintainerUse when repository architecture, rules, skills, commands, context routing, manifests, or generated AI knowledge change and dependent sources may become stale.Votes: 0GitHub stars: 6
- Livelock RecoveryUse when activity is high but requirements, blockers, tests, and deliverables remain unchanged across repeated edit, search, test, review, or planning cycles.Votes: 0GitHub stars: 6
- Loop DetectorUse when commands, searches, file reads, edits, tests, critics, plans, context reloads, or strategies repeat without new evidence or acceptance progress.Votes: 0GitHub stars: 6
- Loophole HunterUse when rules appear satisfied while their intent is bypassed, counters reset, classifications change conveniently, or an AI-Psychiatry audit is requested.Votes: 0GitHub stars: 6
- Memory CuratorUse when deciding whether task discoveries, decisions, preferences, architecture, failures, or lessons deserve durable repository memory.Votes: 0GitHub stars: 6
- Memory ValidatorUse when durable memory may contain assumptions, stale facts, contradictions, duplicates, obsolete decisions, or temporary debugging state.Votes: 0GitHub stars: 6
- Multi Agent CoordinatorUse when two or more agents work concurrently, delegation may recurse, responsibilities overlap, dependencies can deadlock, or a coordinator must preserve scope and termination.Votes: 0GitHub stars: 6
- Never StopUse 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.Votes: 0GitHub stars: 6
- Progress AuditUse when status is unclear, activity is high, completion estimates feel unreliable, or the agent may be mistaking reading, reasoning, tools, or churn for progress.Votes: 0GitHub stars: 6
- Reasoning BalanceUse when a task may be underthinking, sufficiently reasoned, or overthinking and the correct next action is unclear.Votes: 0GitHub stars: 6
- Repository Map UpdateUse when packages, services, ownership boundaries, entrypoints, tests, commands, or dependencies changed and the compact repository map needs a focused update.Votes: 0GitHub stars: 6
- Resume TaskUse when continuing work from saved task state, a compacted session, a handoff, or a new agent without rereading the entire repository.Votes: 0GitHub stars: 6
- Root Cause ValidatorUse when debugging changes assertions, mocks, exceptions, or symptoms without explaining materially important failure behavior.Votes: 0GitHub stars: 6
- Rule Conflict ResolverUse when system, user, repository, domain, AI-Psychiatry, skill, memory, or task-state instructions appear incompatible.Votes: 0GitHub stars: 6
- Scope GuardUse when newly discovered work, technical debt, refactors, audits, optimizations, or reviewer suggestions threaten to expand the user-authorized task.Votes: 0GitHub stars: 6
- Scope Laundering DetectorUse when adjacent work is called required without dependency proof, or inconvenient required work is marked optional.Votes: 0GitHub stars: 6
- Strategy Laundering DetectorUse when different commands, tools, runners, plans, or agents repeat the same hypothesis and evidence target.Votes: 0GitHub stars: 6
- Strategy ResetUse when three same-strategy attempts fail, two approaches oscillate without evidence, or the current abstraction and evidence source cannot resolve the blocker.Votes: 0GitHub stars: 6
- Targeted TestingUse when selecting development and final validation commands so evidence is sufficient without repeatedly running expensive or irrelevant suites.Votes: 0GitHub stars: 6
- Task BootstrapUse when beginning any plan, audit, investigation, modification, review, test, or expensive tool action before the primary objective and completion conditions are explicit.Votes: 0GitHub stars: 6
- Underthinking DetectorUse when implementation, parking, blocking, strategy switching, or completion happens before critical understanding and evidence exist.Votes: 0GitHub stars: 6
- Verification ControllerUse when deciding what evidence is required, whether previous proof remains valid, or whether repeated testing has become reassurance rather than necessary verification.Votes: 0GitHub stars: 6