Afegits recentment
Els últims skills afegits al catàleg. Descobreix les novetats!
jtbd
igor1309
Apply Jobs-to-be-Done as a product-development framing. Three explicit modes: discover (Christensen/Moesta — switch interviews, forces of progress), decompose (Ulwick/ODI — job statements, job map, outcome statements, opportunity scores), and frame (Klement — job stories for the backlog). Activates when the user says "JTBD", "jobs to be done", "job statement", "job story", "switch interview", "forces of progress", "outcome statement", "opportunity score", "what job is the customer hiring this for", or asks for positioning/audience/scope decisions framed by JTBD. Hard-enforces grammars and refuses to silently mix the Christensen and Ulwick vocabularies.
job-search-strategy
igor1309
Comprehensive job search strategy toolkit for analyzing job postings, discovering hidden insights, interviewing candidates to match skills, developing targeted skills, and executing creative outreach strategies. Use when helping candidates strategize their job search, prepare tailored applications, or develop competitive advantages in their job hunt.
ios-simulator-install
igor1309
Install built iOS app on simulator for manual testing or deep link validation. Use when user requests to run or launch the app on simulator (not for xcodebuild test). Reads Bundle ID and Primary Simulator ID from .claude/AGENTS.md.
intake
igor1309
Use when starting work on a task — assigned implementation, bug report, vague requirement, or open-ended exploration — even if the user doesn't say "intake" or "research." Trigger phrases: "/intake", "here's your task", "implement this", "fix this bug", "there's a bug", "explore X", "before we commit", or a bare task reference (step number, PR, doc path). Planning or coding from shallow context produces wrong solutions; this skill forces a deliberate context-capture step before any downstream work begins. Stops cleanly — no auto-transition to planning or implementation.
implementation-plan
igor1309
Use when authoring, editing, or validating implementation plans under any docs/plans path; defines task/phase/step vocabulary, required execution declarations, and the acceptance checklist that catches invalid worktree, branch, and push-policy declarations before execution starts.
handoff
igor1309
Use to hand off ongoing work to a fresh session, or to resume from a handoff in a new one — "write a handoff", "hand off this work", "resume", "continue where we left off". On write, compacts the conversation (reasoning, decisions, dead-ends, next step) into a short doc under a per-project name in the OS temp dir, artifacts referenced by path not copied. On resume, reads the newest back.
feature-spec-protocol
igor1309
Use when creating a feature specification through an ordered clarification protocol that asks one question at a time, avoids hidden assumptions, and fills the spec incrementally.
composition-root
igor1309
Composition root wiring rules — interface-only boundaries, layered assembly, naming discipline, and wiring tests
code-review-discipline
igor1309
Use before declaring any implementation complete or reporting results (self-review is unprompted), when reviewing a diff or someone else's code, before writing down any fail/warning finding, and when turning review findings into an implementation plan. Triggers on "review the diff", "self-review", "review this code", "adversarial review", "before I call this done", "is this a finding", "fail/warning", "regression risk", "test seam", "plan from the findings".
arch-spec-review
igor1309
Review architecture specifications for completeness, appropriate abstraction level, separation of concerns, implicit architectural risk, and the intentionality of mature architecture decisions. Use when reviewing top-level, implementation-agnostic architecture documents that define system boundaries, responsibilities, flows, constraints, and rationale without prescribing implementation details.
adr-governance
igor1309
ADR structure, review standards, and implementation plan requirements
add-openclaw-agent
igor1309
Use when adding a new specialized OpenClaw agent to a gateway deployment (a repo-reviewer, a notifier, or an on-demand assistant reachable via Telegram). Encodes the decision order, the directory + CI-sync layout, the one-bot/one-topic Telegram routing, and two non-obvious verified runtime constraints (forum-topic file delivery and web-search providers) so you don't re-derive them per agent. Triggers on "add an OpenClaw agent", "new OpenClaw bot", "create an agent that runs on the gateway".
assistant-authored-study-drills
igor1309
Orchestrate assistant-authored MCQ practice drills — provenance, cadence, difficulty shaping, coverage, two-contour balance (meaning and course nomenclature), source-grounding, and live quality repair. Defers item-quality, button delivery, and oral construction to their owning skills.
agonara-membership
igor1309
Read and reason about Agonara program participation — your own program memberships, invitations addressed to you (accept or decline them), effective participation for an identity, and membership history. Use when an agent needs to know which programs an identity belongs to, in what role, or to act on a program invitation. The shared, role-neutral participation model that curator, student, and admin skills build on; it is not curation, learning state, or admin recovery.
agonara-curator-corpus
igor1309
Assist a human Agonara Program Curator — do the corpus API work on their behalf to assemble program structure, modeling what the curator hands you (a section, an idea, a document to host) into the right corpus shape and asking when the shape is unclear — create a program, propose topics and concepts as corpus candidates, add material references and relationships through navigation candidates, host readable material content for students, keep drafts separate from accepted corpus, explicitly accept or reject candidates, read accepted corpus and revisions, and read corpus events; treat your own drafts and reports as untrusted until the curator verifies each candidate against trusted state, accept per entity rather than in a batch, and declare contamination on any procedural violation. Use when a curator's assistant agent is building or refining the accepted structure of a program. The substrate the other curator skills (assessment, research) attach to.
agonara-curator-assessment
igor1309
Assist a human Agonara Program Curator to author assessment — open-answer checks, quick checks, and readiness checks via the candidate→acceptance→revision flow, define program-owned assessment criteria, link checks to learner-state targets, and keep answer keys and correctness curator-only (never student-facing). Treat your own drafts and reports as untrusted: present a numbered list, the curator verifies each candidate (and its answer key) against trusted state and approves by explicit item number before you accept, acceptance is per item not batched, and any acceptance lacking that verification is contaminated. Use when a curator's assistant agent is adding or accepting checks or criteria on a program. Builds on the corpus skill; checks attach to accepted corpus entities.
component-arch-review
igor1309
Use when reviewing an implemented component and you need a principle-driven critique focused on root causes, strategic impact, and verifiable improvement paths rather than a laundry list of code smells.
bug-analysis
igor1309
Analyze a reported bug by tracing the likely execution path, forming evidence-based root-cause hypotheses, and producing a structured debugging report. Use when the task is to investigate or explain a bug before implementing a fix.
best-free-openrouter-llm
igor1309
Use when the user wants to discover, refresh, or configure the current best free OpenRouter LLM (e.g. "what's the best free OpenRouter model right now", "set up my agent with a free model", "rotate today's free model"). Reads ranking metadata from shir-man.com and optionally emits OpenAI-compatible configuration for agents, CLIs, or scripts.
background-task-liveness
igor1309
Use when supervising a long-running background process — a build, test run, CI pipeline, deploy, or data job — and you need to choose what to poll, how often, how to tell a slow run from a wedged one, and how to keep monitor state across a teardown. Triggers on "monitor the build", "is it still running", "the build is hanging", "watch the deploy", "poll CI", "arm a monitor", "wedged", "stalled", "no output for a while", "background task".
arch-reviewer
igor1309
Structured, detached evaluation of component or system architecture clarity and intent. Use when reviewing early-stage or medium-fidelity design docs, component boundaries, or system flow sketches to assess whether they communicate ownership, direction, and rationale clearly.
arch-doc-review
igor1309
Checklist for reviewing architecture and design docs in PRs
agonara-student
igor1309
Assist a human Agonara Student through the instance's HTTP API — discover and preview programs without creating state, self-join/leave/rejoin and act on invitations, resume learning and follow the next step, navigate accepted concepts and materials and read hosted material content where present, present checks and relay the student's own quick, open, and readiness answers, and read feedback, results, and the evidence behind progress. Owns the API, the assessment-integrity boundary (an agent may help a student learn but must never produce, choose, or submit the student's assessment evidence), and the MCQ item-quality bar — the craft of explaining a topic and diagnosing why an area is weak is owned by agonara-coach. The student sees only accepted corpus and its own state — never curator drafts, answer keys, correctness metadata, or evaluator internals. Use when an agent acts as a student's assistant against an Agonara instance — the API, boundary, and checks substrate the coach and drill skills build on.
agonara-curator-research
igor1309
Assist a human Agonara Program Curator to ground and expand a program — record external sources with justifying metadata, read coverage-gap diagnostics as draft guidance, and generate, trace, and explicitly accept or reject LLM-assisted curation suggestions. Report sources, gaps, and suggestions only from live API reads, never from memory; present suggestions as a numbered list and act only on the item numbers the curator picks after verifying origin. Use when a curator's assistant agent is researching a program: adding sources, finding gaps, or reviewing generated suggestions. Suggestions and gaps are draft material until accepted; accepting a suggestion only materializes a draft candidate, never accepted corpus.