tkolleh
UserMy personal directory of AI Agent skills
Categories
Indexed Skills (24)
analyzing-architecture
Detects repository context, maps dependencies (enterprise-specific or general), and generates/persists architectural documentation.
diagram
Generates technical diagrams using the D2 language, with automatic color-contrast verification and diagram-type detection.
eng-career-goals-writer
Seasoned engineering manager and career coach. Helps engineers translate tasks into SMART performance goals aligned with team and org strategy.
git-commit-helper
Intelligent commit message generator that enforces Conventional Commits and links changes to Jira issues for traceability.
jira
Manage Jira issues, sprints, and epics via CLI — jira-cli (ankitpokhrel/jira-cli) for bearer/basic-auth instances, acli (Atlassian's official CLI) for OAuth-only Jira Cloud tenants. Trigger on: jira, jira-cli, acli, ticket, issue key (e.g. PROJ-123), work item, epic, sprint, transition/move ticket, comment on ticket, assign ticket, JQL, create bug/story, "what's on my board", "my open issues". Use when the user wants to find, read, create, update, transition, comment on, assign, or link Jira issues/work items — or list sprints/epics/boards — via CLI, including setups with more than one Jira instance behind different auth models. Do not use for Todoist, GitHub Issues, Linear, or generic project planning with no Jira involvement.
jq
Trigger on: jq, jq filter, jq query, process JSON, filter JSON, transform JSON, extract from JSON, parse API response JSON, NDJSON, pretty-print JSON, jq select, group_by JSON, update JSON file with jq. Specialized procedure for complex JSON processing with the jq CLI. Prefer over ad-hoc Python/Node one-offs for extract, filter, format, aggregate, or in-place JSON transforms. Do not use for binary files, CSV/XML conversion, or general scripting unrelated to JSON.
newrelic-cli
Query and manage New Relic observability data using the newrelic CLI across all your organization's accounts. Trigger on: newrelic, nrql, apm, deployment marker, alert policy, observability query, error rate, throughput, latency, SLO/SLI.
oli-storage-manager
A unified data management skill using 'oli' to interface with S3, GCS, Azure, and other remote storage with built-in safety guardrails.
smart-init
Trigger on: init, CLAUDE.md, AGENTS.md, setup repo, onboard, generate docs, project documentation for agents, bootstrap, new project setup. Evidence-guided AGENTS.md generator that makes AI coding agent runs ~28% faster and ~16% cheaper by eliminating exploratory navigation. Always produces a tool-agnostic root AGENTS.md plus a thin CLAUDE.md that imports it via `@AGENTS.md`, per Anthropic's documented memory-import convention.
sourcegraph-search
Search code, commits, and diffs across millions of open source and private repositories using the Sourcegraph CLI (src).
wt-remove
Sync untracked session artifacts to the target worktree, consolidate key findings using /zk-merge, then close the current branch and remove the worktree. Pass an optional argument summarising the purpose of this session.
zk-merge
Summarizes current session consolidating memories, tasks, and key findings into a Zettelkasten note.
visualize
Trigger on: chart, plot, visualize data, bar chart, line chart, scatter plot, pie chart, line graph, Vega-Lite, make a chart from CSV/JSON/table. Generates charts (bar, line, scatter, pie) from CSV, JSON, or pasted tabular data using Vega-Lite, with automatic column-type detection and chart-type recommendation. Use when the user wants a data visualization from a table or file — not for architecture/sequence diagrams (use diagram), network graphs, or design/art images.
color-accessibility
Trigger on: check contrast, WCAG contrast, accessible colors, readable text color, fix low-contrast, dimmed text color, palette accessibility, pastel color, textcolor for background, make this color readable, UI theme contrast, Neovim highlight contrast. Evaluate, fix, and generate accessible fg/bg pairs with the pastel CLI and color-accessibility/main.py (WCAG AA/AAA). Use whenever the user changes colors for UI, CSS, terminal, or editor themes — do not guess contrast; measure it.
save-zk
Only when the user explicitly invokes `save-zk` or `/save-zk`. Do not use for generic save, summarize, commit, worktree teardown, daily-briefing, or notebook search. Distills this session into one Session Note (create or Living-Head update) and appends a best-effort back-link on today's Daily Note.
rigorous-review
Rigorous, evidence-backed code review for high-stakes changes. Trigger on: rigorous review, thorough review, deep review, review this PR properly, review before merge, high-stakes review, "is this actually safe to merge", regulated or compliance code review, batch-review these PRs. Every finding carries quoted evidence, a concrete failure scenario, and must survive an adversarial refutation pass; every review states what was checked and found clean. Use when a wrong call is expensive and a false finding costs credibility. Do not use for a quick pass over a small diff, for generating commit messages, for CI failure triage, or for reviewing your own work-in-progress before it is ready.
alloy-structural-analysis
Formal model-checking layer over Allium specs using Alloy 6 + Electrod + nuXmv. Trigger on: "rigorous structural analysis", "model-check this spec", "verify this Allium spec formally", "check for structural divergence with Alloy", "run the Alloy loop", "does the code actually satisfy this spec", temporal/CTL/LTL property checking on a spec, or when weed/allium surface a divergence that needs a deeper formal check than pattern-matching can give. Translates Allium spec obligations into Alloy models, invokes electrod.nuxmv for real temporal model-checking (not Alloy's default bounded SAT backend), parses receipt.json/stdout for verdicts, and on a genuine counterexample hands off to ast-grep/serena to locate the corresponding code. Do not use for spec-vs-code divergence without a formal-verification need (use `weed`), for parsing/checking Allium syntax alone (use `allium check`/`model`/`plan` directly), or for structural code search with no spec/model angle (use `ast-grep`/`serena` directly).
morphir
Translate pure business/decision logic (Scala, Java, or similar) into Morphir IR via hand-authored Elm, then verify the translation with a hand-traced decision table against the source code. Trigger on: "model this in Morphir", "translate this logic to Morphir IR", "morphir-elm", "decision table verification", "verify this Elm model against the source", "morphir-elm make/gen/develop", or when a codebase's pure rule/eligibility/comparison logic needs a formal, language-agnostic representation for review or downstream generation. Covers `morphir.json` project shape, `morphir-elm` CLI subcommands and their traps, and the decision-table technique for verifying an Elm model's behavior matches its source — a fixture-based equivalence check, not exhaustive state-space search. Do not use for parsing/checking a domain spec's own syntax (that's a spec-authoring tool's job, not this skill's), for exhaustive state-space model-checking of a specification (see `alloy-structural-analysis` if that toolchain is available — a
scala
Enforces required tool order for Scala/Java projects. Compile/test: use the `bloop` CLI directly (bloop compile, bloop test) — never `sbt compile`/`sbt test`. Search/navigate: scalex first, then ast-grep, then a semantic/LSP-aware tool if one is available, then grep/ripgrep as last resort — this order is unconditional, even for single-file lookups. Trigger on: "compile this", "run the tests", "bloop compile", "sbt test", "build the project", "find where X is defined", "who implements this trait", "find usages of", "search this Scala codebase", or any Scala/Java compile, test, or code-search request.
design-doc
Collaboratively drafts a Technical Design Document (TDD) as a Staff-level engineering thought partner, through a paced back-and-forth rather than a single generated document. Trigger on: "write a TDD", "write a tech design doc", "help me draft a design doc", "technical design document", "collaborate on a TDD", "design doc for this feature", "let's design this before we build it", or when a user describes a feature with real architectural, integration, or cross-team risk and hasn't yet written anything down. Note: TDD here means Technical Design Document, not Test-Driven Development — use this skill for up-front design writing, not for red-green-refactor coding workflows.
project-instructor
You are an elite pedagogical agent that guides users to complete complex projects while ensuring deep mental development and concept mastery.
qmd-search
Answers user questions by searching a local Markdown repository using the `qmd` (Quick Markdown Search) CLI toolkit. Use this skill whenever the user asks a question that should be answered from local notes or documentation — including queries like "what do my notes say about X", "find anything about Y in my knowledge base", "search my docs for Z", or any question where the answer likely lives in a local Markdown collection. Also use this when the user asks to look something up, retrieve a concept, or synthesize information from their Zettelkasten or local doc repo. Trigger even if the user doesn't mention "notes" or "qmd" explicitly — the key signal is that they want to retrieve knowledge from a local corpus rather than from training data.
structured-memory
Defines how an agent should manage its own structured, persistent memory across whatever memory backends are configured in this environment — durable cross-session stores, project- or workspace-scoped notes, and short-lived task-tracking state. Use this whenever memory itself is the subject of the task — the user asks to remember, save, recall, forget, or reinforce something explicitly; asks to audit, clean up, consolidate, deduplicate, or curate existing memory; asks what belongs in long-term memory vs. task state vs. project-scoped notes, or what counts as durable "cross-project" knowledge; reports that a stored memory is wrong, stale, or contradicts something else; or whenever about to write any memory longer than one short, single-fact sentence — some memory backends silently corrupt or truncate multi-clause writes with no error signal, and the write-format rules here prevent that class of data loss. Also consult this before treating a subagent's or web research's claims as settled fact worth persisting.
daily-briefing
Daily orientation and chief-of-staff briefing. Pulls from Slack (saved items), Gmail (important/starred), Google Calendar (today's events), Jira CLI (configured projects), and Todoist CLI, validates every action item, synthesizes a prioritized briefing using three consequence-based tiers, then produces a decisive hour-by-hour day shape anchored to the user's energy and focus windows. Appends to the daily Zettelkasten note on confirmation. Use this skill whenever the user types /daily-briefing, says "orient me for the day", "morning briefing", "what's on my plate today", "daily standup prep", "chief of staff", or any variant of wanting a cross-source daily work summary.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.