Menu
SkillsMP has collected 3,441 skills from vamseeachanta/workspace-hub. Open a skill to review its source and details.
Showing 40 of 3,441 collected skills.
Write outbound email and external messages in Vamsee Achanta's voice — a subtle offer to help, never bold or rash claims. Load before drafting ANY email, LinkedIn/Collide reply, proposal note, or outreach sent under his name.
Save/publish analysis or computation results from ANY ecosystem repo to Hugging Face as a queryable, viewer-renderable dataset. Use when the user wants to "save results to hugging face", "publish dataset to HF", "hugging face data saving", "save analysis…
Clone, create, fork, configure, and manage GitHub repositories. Manage remotes, secrets, releases, and workflows. Works with gh CLI or falls back to git + GitHub REST API via curl.
Diagnose and fix a machine whose equivalence-state fingerprint publish is absent, stale, or gate-length slow (the wh#3500 pre-push RUN_ALL deadlock signature). Use when the equality matrix shows PUBLISH-GATED / PUBLISH-STALE / MISSING-EVIDENCE on the…
Bootstrap a registered private client wiki from the committed generic template.
Build worldenergydata drill-down pages (field hub, well timelines, insight/norm pages) with the proven validate-first playbook, the fractal IA grammar, honesty rules, and the exact wed CI gotchas.
Diagnose and reduce git repository bloat — multi-GB .git, slow git status/fetch/clone caused by large binaries committed to history. Consolidates packs and enables the untracked-cache (always-safe wins), then plans an operator-gated history rewrite that…
Mandatory planning workflow for ALL GitHub issues — plan, review, approve, then implement.
Surface SPECIFIC FILES on the shared drives (/mnt/ace, /mnt/dde) relevant to the current task — the FILE-level complement to ecosystem-data-sources (domain-catalog level). Extracts query terms from work context, runs the drive-index CLI once, presents ranked…
Proactively surface what DATA the ecosystem already has for an engineering domain — before starting analysis, points to the consolidated data-source catalog, any latent ACE_SHARE project precedent, and the domain-database issue that curates it. Use when work…
Weekly sync that diffs new Deckhand API paths (workflows) against a saved snapshot and opens HITL draft PRs to keep the resume, LinkedIn, website api-catalog, and repo READMEs in step with the live API catalog. Never publishes or merges.
Create, manage, triage, and close GitHub issues. Search existing issues, add labels, assign people, and link to PRs. Works with gh CLI or falls back to git + GitHub REST API via curl.
Class-level Gmail and email operations: multi-account setup, OAuth, triage, extraction, archiving, attachments, unsubscribe, and touchbase workflows.
Operate and reason about the 'session analysis & memory curation' line item of the machine-equality matrix — the per-box engine that analyzes every AI-provider session log + curates the memory delta, its daily-freshness verdict (green ≤12h / orange >12h / red…
Run the weekly marketing/BD review that turns activity into tracked, advancing opportunities. Pull a funnel snapshot against the KPI spine, enforce pipeline hygiene, focus on priority + at-risk deals, and end with written, owned action items. Guards against…
Produce and refresh branded, single-page capability one-pagers, pamphlets, and management decks/plans — brief → who/what/why-us + concrete proof → segment tailoring → brand/voice + claims check → clean layout → render HTML to PDF. Reuses an approved-claims…
Produce a planned, on-voice content pipeline from a few content pillars — map each piece to a funnel stage + persona, atomize one core asset into many derivatives, schedule with owner/status, attach a distribution plan, and pass a quality gate. Built for…
Run the LinkedIn organic funnel — reactions/likes → page follows → engaged followers → conversations. Covers the concrete platform levers (invite-to-follow, the Premium-page auto-invite of reactors, comment-gating, newsletters, page CTA buttons,…
Turn a marketing/BD objective into a measurable, time-boxed campaign plan with ICP, message + proof, channel mix, asset list, a conversion funnel + flowchart, KPI targets with a named tracking mechanism, and an owner/RACI. The spine the other marketing skills…
Build warm-first, ICP-matched outreach sequences that book conversations and drive vendor/supplier registrations and RFQs. Validate the list against the ICP, research a real trigger per contact, run a multi-touch multi-channel cadence with reply branching,…
Bring THE CURRENT computer back to ecosystem + machine-equality equivalence — clean repo-hygiene drift (dirty trees, stale branches/worktrees/stashes) and remediate every non-OK equality-matrix verdict. Report-first; destructive actions are guard-gated and…
Query the cross-provider topic-memory corpus by keyword (and optional class) instead of grepping ~180 files. Use when you need to check "what have we learned about X" before solving a problem.
Conventions for creating consistent Mermaid diagrams including decision node layout, edge ordering, and flowchart direction rules.
Generate interactive validation reports with quality scoring, missing data analysis, and type checking. Combines Pandas validation, Plotly visualization, and YAML configuration for comprehensive data quality reporting.
Guide AI model selection based on task complexity, cost constraints, and latency requirements
Sub-skill of modular-architecture-documentation: 1. Module Definition Framework (+9).
Sub-skill of modular-architecture-documentation: Overview (+6).
Sub-skill of repo-structure: Tier Classification (Determines Which Rules Apply).
Automate invoice generation for engineering consulting services using YAML configuration and Word document templates.
Sub-skill of complexity-scorer: 3. Context-Aware Scoring (+1).
Score task complexity using keyword matching, heuristic analysis, and configurable threshold rules
Batch translate engineering Excel calculation files from Spanish to English preserving formulas
Convert OrcaFlex .dat binary model files to enriched YAML fixtures using worldenergydata public databases (vessel fleet, riser components, pipe schedules). All stages run on licensed-win-1. Output committed to digitalmodel as test fixtures.
Convert engineering Excel workbooks to Python code using Codex Desktop cowork on Windows. Benchmarked superior output with 24 vs 7 functions and 81 vs 53 tests for Ballymore jumper.
Convert engineering Excel workbooks to Python code using Codex Desktop cowork on Windows. Proven superior quality vs Linux openpyxl extraction (24 vs 7 functions, 81 vs 53 tests). Validated on Ballymore jumper installation analysis.
Convert Excel calculation spreadsheets to Python code — extract formulas, build dependency graphs, generate pytest tests using cell values as assertions, and produce dark-intelligence archive YAMLs.
DEPRECATED — superseded by gmail-extract-and-act. Extract emails from Gmail to /mnt/ace/<repo>/, archive to repos, commit, then delete. Uses archive-everything model.
Periodic relationship maintenance via email — identify contacts due for outreach, draft personalized check-ins, queue for user approval. Supports per-account tone and cadence.
Normalize, classify, and manage contact databases across 3 Gmail accounts. Clean CSV exports, deduplicate, tag categories, flag touchbase/unsubscribe candidates.
The email-as-queue workflow — extract structured data from emails, act on it, track thread state, and delete emails when topics complete. Email is transient; extracted data is persistent.