share
$
npx mdskill add terrylica/cc-skills/share> **Self-Evolving Skill**: This skill improves through use. If instructions are wrong, parameters drifted, or a workaround was needed — fix this file immediately, don't defer. Only update for real, reproducible issues.
SKILL.md
.github/skills/shareView on GitHub ↗
--- name: share description: STUB — bundle, sanitize, upload Claude Code sessions to Cloudflare R2, emit 7-day presigned URL. allowed-tools: Bash, Read, AskUserQuestion --- # chronicle:share (stub) > **Self-Evolving Skill**: This skill improves through use. If instructions are wrong, parameters drifted, or a workaround was needed — fix this file immediately, don't defer. Only update for real, reproducible issues. **Status:** stub. This skill is scaffolded but not functional. Target workflow documented below; implementation is pending. ## Planned workflow 1. **Preflight** — verify `brotli`, `aws`, `op`, `bun` installed; verify R2 bucket reachable; verify 1Password access. 2. **Bundle** — run `scripts/bundle.sh` to enumerate session JSONL under `~/.claude/projects/<encoded-cwd>/` and stage them with a manifest. See [Plugin CLAUDE.md](../../CLAUDE.md#phase-1-bundle--implemented) for the CLI and manifest schema. 3. **Sanitize** — run `scripts/sanitize.sh <STAGING_DIR>`. Wraps the upstream `sanitize_sessions.py`, auto-discovers it, fingerprints it, mutates the manifest. See [Plugin CLAUDE.md](../../CLAUDE.md#phase-2-sanitize--implemented). 4. **Compress** — Brotli-9 sanitized files. 5. **Upload** — `aws s3 cp` to R2 endpoint, credentials from 1Password. 6. **Presign** — `aws s3 presign --expires-in 604800` (7 days, matches Terry's own pipeline). 7. **Emit** — print URL; optionally pipe to `tlg:send-media` for direct Telegram posting. ## Plugin docs [Plugin CLAUDE.md](../../CLAUDE.md) — architecture, roadmap, boundary with upstream cc-skills. ## Post-Execution Reflection After this skill completes (once it is no longer a stub), reflect before closing the task: 0. **Locate yourself.** — Find this SKILL.md's canonical path before editing. 1. **What failed?** — Fix the instruction that caused it. 2. **What worked better than expected?** — Promote to recommended practice. 3. **What drifted?** — Fix any script, reference, or dependency that no longer matches reality. 4. **Log it.** — Evolution-log entry with trigger, fix, and evidence. Do NOT defer. The next invocation inherits whatever you leave behind.
More from terrylica/cc-skills
- academic-pdf-to-gfmConvert academic PDF papers to GitHub-renderable GFM markdown with math equations. TRIGGERS - PDF, GitHub markdown, math
- adaptive-wfo-epochAdaptive epoch selection for Walk-Forward Optimization. TRIGGERS - WFO epoch, epoch selection, WFE optimization, overfitting epochs.
- adr-code-traceabilityAdd ADR references to code for traceability. TRIGGERS - ADR traceability, code reference, document decision in code.
- adr-graph-easy-architectASCII architecture diagrams for ADRs via graph-easy. TRIGGERS - ADR diagram, architecture diagram, ASCII diagram.
- agent-reach>
- agentic-process-monitorMonitor background processes from Claude Code using sentinel files, heartbeat liveness, and subagent polling. Best practices and.
- alpha-forge-preshipAlpha Forge quality gates for PR review - RNG determinism, URL validation, parameter validation, manifest sync.
- article-extractorExtract MQL5 articles and documentation. TRIGGERS - MQL5 articles, MetaTrader docs, mql5.com resources.
- ascii-diagram-validatorValidate ASCII diagram alignment in markdown. TRIGGERS - diagram alignment, ASCII art, box-drawing diagrams.
- asciinema-analyzerSemantic analysis of asciinema recordings. TRIGGERS - analyze cast, keyword extraction, find patterns in recordings.