josix

Applies 1/2/3-strike adjustment rules to plan.json based on a single workout's analysis dict. Mutates plan only when thresholds fire. Called after every workout log.

Renders today's workout card from plan.json and daily_state.json as a Markdown block. Use for every /run-today invocation. No writes — pure read-and-render.

Conversationally captures a completed workout (duration, distance, RPE, HR, splits, notes) and writes it to workouts.json. Triggers analyze-workout and adapt-plan downstream. Use for /run-log.

Inserts a post-race or injury-flag recovery block into plan.json: 4 days rest + 3 easy jog days (post-race), or 3 rest + 1 recovery (red-flag-fatigue), or 7 rest days (injury). Use after /run-race-recap or when adapt-plan returns red_flag_recovery.

Web-search-backed Q&A for novel coaching questions outside the plan's standard logic: heat acclimation, recovery from illness, pacing strategies for unique courses. Use for /run-research and when the Coach cannot answer from training data alone.

Aggregates the past 7 days of completed workouts: total mileage, quality session adherence, fatigue indicators (RPE creep, HR drift). Decides hold/advance/recovery for the next week. Use for /run-week.

Pulls recent run activities from the garmin-givemydata MCP server: triggers garmin_sync to refresh the local SQLite, queries activity IDs in the requested date range, fetches per-activity detail (with splits, HR zones, weather, running dynamics), normalizes to workouts.json schema via garmin_normalize.py, deduplicates by garmin_activity_id with preferred_source tiebreaker, and runs the same analyze-workout + adapt-plan pipeline as manual logging. Requires users.integrations.garmin.connected = true.

Pulls recent run activities from the Strava MCP server, normalizes them to the workouts.json schema using strava_normalize.py helpers, deduplicates by strava_activity_id with preferred_source tiebreaker, and runs the same analyze-workout + adapt-plan pipeline as manual logging. Requires users.integrations.strava.connected = true.

Search prior session history to recall how similar work was handled before. Use when you want to leverage a past approach, check prior experience on a topic, answer "how was this handled before", or cross-verify current handling against precedent from earlier sessions.

This skill should be used when looking up which agents own or consume specific skills, understanding skill-agent relationships, or routing tasks based on skill ownership.

This skill should be used when the user provides a vague request, asks to clarify requirements, structure a task, or refine a prompt for multi-agent orchestration.

This skill should be used when handling verification steps, quality gates, pre-commit checks, test failures, lint errors, build verification, or mandatory validation before task completion.

This skill should be used when handling agent model selection, tool access permissions, behavioral guardrails, MCP tool preferences, or any question about what agents can/cannot do.

Turn any codebase into a beautiful, interactive single-page HTML course that teaches how the code works to non-technical people. Use this skill whenever someone wants to create an interactive course, tutorial, or educational walkthrough from a codebase or project. Also trigger when users mention 'turn this into a course,' 'explain this codebase interactively,' 'teach this code,' 'interactive tutorial from code,' 'codebase walkthrough,' 'learn from this codebase,' or 'make a course from this project.' This skill produces a stunning, self-contained HTML file with scroll-based navigation, animated visualizations, embedded quizzes, and code-with-plain-English side-by-side translations.

This skill should be used when classifying tasks, routing to agents, determining complexity, or handling task routing, agent selection, verification requirements, and multi-component changes.

This skill should be used when querying the user's personal knowledge base (cross-project personal knowledge graph) for prior learnings, notes, or decisions that apply across projects.

Generate a personalized 24-week Japanese study plan structure based on the learner's goal, level, daily time budget, and topic preferences.

Synthesize the past week's task history, self-ratings, and mistake patterns into a compressed weekly summary with weak areas, strong areas, and a recommended focus for the next week.

Generate an ordered list of daily study tasks tailored to the learner's current week focus, recent performance, and available time.

Produce a structured listening comprehension drill from data/listening.json, including transcript segments, key vocabulary callouts, comprehension questions, and a summary task.

Create a shadowing drill from listening or speaking content, with sentence-by-sentence guidance, rhythm cues, and repetition instructions.

Deliver a structured speaking task from data/speaking.json, with hint scaffolding, target patterns, and a timer target — revealing the sample answer only after the learner attempts.

Analyze a learner's Japanese answer and return a corrected version, a natural native version, a list of mistakes with Chinese explanations, and brief coaching advice.

Select grammar patterns from data/grammar.json tailored to the learner's current week focus and recent performance, with examples and a practice prompt.

This skill should be used when the user asks to draft a bug report, file a new issue, report a bug in a project, draft a feature request, propose a feature, write up an issue for a project, or open an issue about a problem or improvement. Trigger phrases include: "draft a bug report", "file a new issue", "report a bug in X", "draft a feature request", "propose a feature", "write up an issue for X", "open an issue about". All output from this skill is a DRAFT for the user's review — never posted automatically.

This skill should be used when the orchestrator needs to classify a user's open-source contribution intent into one of the nine supported scenarios. Trigger phrases include: "find an issue to contribute", "check project status", "draft a question to maintainers", "understand contribution norms", "set up the project locally", "claim an issue", "give feedback on a PR", "respond to PR review", "draft a bug report", "file a new issue", "propose a feature", and close variants of each.

This skill should be used when the user asks to learn how to contribute to an open-source project, understand a project's governance, find out about CLA or DCO requirements, learn the correct commit or PR title format, or find out where project decisions happen. Trigger phrases include: "how do I contribute to X", "what are the contribution norms", "do I need to sign a CLA", "what's the DCO", "where do decisions happen", "what's the governance model", "CONTRIBUTING guide", "how should I format my PR title", "what mailing list should I use".

This skill should be used when the user asks to set up their local development environment for an open-source project. Trigger phrases include: "set up the project locally", "how do I clone and build X", "help me get the dev environment running", "how do I run the tests for X", "I can't get the build to work", "set up apache/airflow locally", "set up apache/spark locally", "what are the prerequisites for X".

This skill should be used when the user asks to find or match an issue or PR suited to them in a target open-source project. Trigger phrases include: "find an issue to work on", "match me to a task", "suggest a good first issue", "what can I contribute", "find a PR I can help with", "show me newcomer-friendly issues", and close variants. The skill runs after oss-researcher has gathered raw issue/PR data and applies the matching/ranking logic on top of it.

This skill should be used when the user asks to draft a question to maintainers, draft PR feedback on someone else's in-progress pull request, draft a reply to review comments on their own PR, or draft a claim comment for an issue they want to take. Trigger phrases include: "draft a question to maintainers", "I want to ask about this issue", "draft PR feedback", "help me review this PR", "draft a review reply", "respond to maintainer feedback", "draft a claim comment", "I want to take this issue". All output from this skill is a DRAFT for the user's review — never posted automatically.

This skill should be used when indexing or searching a corpus with the pi-serini Lucene BM25 retriever, tuning BM25 k1/b parameters for long documents, handling missing Java 21 / pyserini dependencies, or when corpus scale demands a production-grade Lucene index.

Compare six retrieval strategies — contextual retrieval (TF-IDF/BM25/RRF fusion), its LLM-enriched lexical+ctx variant, turbovec (dense ANN), pi-serini (Lucene BM25), hybrid (lexical + dense fused with RRF), and tree-sitter (AST-boundary chunking with enclosing scope context) — with a stdlib-only offline core and graceful degradation when optional backends are missing. Use when the user wants to compare retrieval strategies on their project, search project files, or set up the retrieval engine.

This skill should be used when indexing or searching a code/script corpus with the tree-sitter retriever, wanting AST-boundary chunk spans plus an enclosing function/class breadcrumb on hits, or handling the RuntimeError raised when the treesitter extra is not installed.

This skill should be used when indexing or searching a corpus with the turbovec dense ANN retriever, choosing quantized embedding-based retrieval over lexical matching, handling the RuntimeError raised when the turbovec + local extras are not installed, or when keyword search misses paraphrases and synonyms (vocabulary-mismatch problems).

This skill should be used when combining lexical, dense, and Lucene retrieval rankings via reciprocal rank fusion, choosing which single retrieval method fits a task, deciding whether to add LLM/heuristic contextualization before indexing, or when a single retrieval method returns unsatisfying results and rankings should be combined.

This skill should be used when indexing or searching a corpus with the contextual lexical retriever (TF-IDF + BM25 fused with reciprocal-rank fusion), optionally enriching document text with LLM-generated context before indexing, or when a zero-dependency offline search over project files is needed.

This skill should be used when syncing local tasks/*.md into a GitHub Project (one-way push), or when initializing the GitHub Project and its fields via --init.

This skill should be used when prioritizing tasks, building a daily plan, building a weekend plan, or ranking work across the task domains using the fixed priority ladder.