Explore skills

Prepare release communication and check readiness. Main mode: notes with optional flags --changelog, --summary, --migration; range as v1->v2. Other modes: prepare (full pipeline: audit → all artifacts), audit (pre-release readiness: blockers, docs alignment, version consistency, CVEs), demo (story-telling release notebook in jupytext # %% format).

Interactive outline co-creation for developer advocacy content — collects format, audience profile, story arc (Problem→Journey→Insight→Action), and voice/tone; detects out-of-scope requests (FAQs, comparison tables); surfaces conflicts between user brief and audience needs. Writes approved outline to .plans/content/<slug>-outline.md for foundry:creator to execute. Use when starting a blog post, Ma

Scores content for AI slop patterns, conducting an 8-dimension audit against the Awwra anti-slop framework. It flags banned vocabulary, structural tells, formatting violations, and April 2026 second-generation slop patterns, recommended for use before posting any AI-generated content.

Optimizes oversized CLAUDE.md files using progressive disclosure by analyzing content, detecting encryption constraints, creating sub-documents, and rewriting the main file with a Sub-Documentation Table.

This specialized skill reduces AIGC detection rates for Chinese academic writing, including theses, based on experiments that lowered AI rates from over 50% to 11%. It detects and fixes typical AI writing patterns, ensuring content volume is maintained and adhering to academic standards.

This skill provides deep analysis of writing styles across platforms. It helps users study authors, deconstruct content patterns, compare styles, and generate imitation writing skills from provided text samples.

Agent ecosystem expert for creating, maintaining, and auditing agents and skills. Prevents ecosystem drift and overlap.

Periodic maintenance of institutional knowledge. Analyzes lessons for staleness, overlaps, and gaps. Keeps lessons.json healthy.

Validates documentation quality: markdown syntax, cross-references, JSON structure. WHEN TO USE: - Validating markdown files for quality issues - Checking cross-references between documents - Validating JSON structure in ecosystem files - As part of FIXED END validation in any scenario WHEN NOT TO USE: - Content quality auditing (use context-audit for that) - Making content changes (findings guide

Strategic reflection skill. Step back from daily work to think about the bigger picture of your context architecture, identify gaps, and envision improvements.

Manage the BCOS self-learning ladder: list learned rules, forget a rule, regenerate learned-rules.json from resolutions.jsonl. Mechanical-only — reads/writes derived artifacts; the actual learning happens via record_resolution.py at click time. Invoke with /learning.

Natural-language editor for .claude/quality/schedule-config.json. Users talk about maintenance scheduling in everyday language ("run audit twice a week", "turn off deep daydream", "switch dispatcher to 08:30") — this skill parses intent, validates against the schema, shows a concrete diff, asks for confirmation, and writes the change. WHEN TO USE: - User wants to change how often a job runs - User