Claude Skills · Coding

Spec Literal Execution

ashutoshsinghpr7/wikiskill

Apply ONLY the spec clauses literally — no aggregation, dedup, or cleanup transforms; each input record maps to its own output line.

★ 108 MIT Synced 1 hour ago View SKILL.md

At a glance

Coding Manual install MIT v1.0.0

This skill is for Coding and helps you execute specifications literally, map input records to output lines, and apply spec clauses without transformation.

Install git clone --depth 1 https://github.com/ashutoshsinghpr7/wikiskill cp -r wikiskill/skills/spec-literal-execution ~/.claude/skills/spec-literal-execution
Can use Not declared by the author

data-transformationSpecification DrivenNo AggregationRecord MappingLiteral ExecutionData Integrity

Also in ashutoshsinghpr7/wikiskill

View the repo

Sandbox approval policy blocks execute_code and python3 -c; use read_file/write_file + manual transforms instead of retrying both runners.

Search Miss Binary Code Review & Testing

ripgrep/search_files silently skips binary-detected files — verify empty search results with grep -a / file / xxd before concluding 'not fou...

Trace Harness Launch Failure Code Review & Testing

Empty session traces mean launch failure, not agent behavior — verify api_call_count/tool_call_count and stdout.txt before analyzing.

Verify Output Readback Code Review & Testing

After write_file, re-read the deliverable (or ls + hexdump/line-print) and re-check the last format clauses before finishing.

Wikiskill Evolve Productivity

Run the WikiSkill self-evolution loop (arXiv 2608.27454) on a Hermes workspace — raw→maintainer→proposer→gate with strict R_val > R_best gat...

Wikiskill Maintainer Productivity

Consolidate traces into the persistent wiki (WikiSkill).

Wikiskill Proposer Productivity

Propose skills from wiki patterns and traces (WikiSkill).

Other Coding skills

Karpathy Guidelines multica-ai/andrej-karpathy-skills

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make...

Webapp Testing anthropics/skills

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI be...

MCP Builder anthropics/skills

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-design...

Claude API anthropics/skills

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model...

Web Artifacts Builder anthropics/skills

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS,...

Improve Codebase Architecture mattpocock/skills

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.