Observed Signal · Jun 14, 2026 · Technical Release · Source: DEV Community · Impact: 1/5 · Sentiment: Neutral
Two Claude Code Skills Fix Agent Guessing and Reviews
A developer published two open-source Claude Code skills — 'spec' and 'review-audit' — designed to reduce common failures of coding agents. 'spec' prompts the user with a 13-section template and multiple-choice questions to resolve ambiguities up front, performs a fresh-context self-check, and enforces executable acceptance criteria. 'review-audit' is a read-only, single-pass audit covering six axes (correctness, wiring, security, test efficacy, spec compliance, regression) and requires concrete file:line or run evidence before marking an axis audited; it runs in the caller's context. Both skills are distributed as single prompt files (Apache-2.0), have no dependencies, make no network calls or telemetry, and are available on GitHub (dualform-labs). Installation instructions clone each repo into ~/.claude/skills/.
Open-source developer tools for LLM agents improve engineering workflows but have limited direct impact on the broader AdTech/MarTech industry.
Track GitHub Signals & Market Shifts in Real-Time
Polaris7 autonomous intelligence agents track regulatory filings, primary sources, executive changes, and deal flow 24/7. Create your free Explorer workspace to monitor these entities.
Key Takeaways & Evidence Grounding
- Developer published two open-source Claude Code skills: 'spec' and 'review-audit'.
- Both skills are single prompt files, Apache-2.0 licensed, with no dependencies and no network calls or telemetry.
- 'spec' clarifies ambiguous tasks via a 13-section template and multiple-choice questions, uses a fresh-context self-check, and requires executable acceptance criteria.
- 'review-audit' performs a read-only audit across six axes (correctness, wiring, security, test efficacy, spec compliance, regression) and requires concrete file:line or run evidence to mark an axis audited.
- Repositories: https://github.com/dualform-labs/spec-skill and https://github.com/dualform-labs/review-audit; install by copying skills into ~/.claude/skills/.
Connected Companies & Entities
1 Entity mappedOntology Mapping & Concepts
Related Market Signals & Shifts
Recent verified developments and strategic activity across this market segment.
Review: mattpocock/skills — Engineer's Claude Skills, 160k Stars
This article reviews the public GitHub repository mattpocock/skills, a .claude directory opened by TypeScript educator Matt Pocock that contains about 36 Claude Code "skills" grouped into engineering and productivity categories. The repo has attracted over 160,000 GitHub stars because it exposes real, working prompts and workflows used by an experienced engineer rather than a polished product. The review highlights standout skills (diagnosing-bugs, tdd, grilling, codebase-design), describes the v1.1 update (including the promotion of wayfinder and several renames), and explains installation options (npx installer or clone+symlink) plus guidance on remixing individual skills rather than adopting the whole set.
Generate Claude Code Skills from Git History
A developer guide describing how to generate reliable, auto‑triggering Claude Code skills by mining your git history and conversation/correction artifacts. The post explains commands to surface frequent commit types and commonly touched files, argues that git logs reveal real task frequency while conversation history (memory files, CLAUDE.md commits, workflow/docs commits) reveals constraints and friction, and gives a minimal SKILL.md structure plus three concrete skill examples (blog-article, veille-debug, blog-fix). The author emphasizes precise trigger descriptions, one-skill-per-context, and encoding non-obvious rules to reduce false positives and repeated re-explanations across agent sessions.
How to write effective Claude Code SKILL.md
This technical guide explains the SKILL.md format for Claude Code skills, focusing on how to make skills reliably trigger. It describes the two-stage loading model (description always visible; body loads only on use), recommended frontmatter fields (name, description, disable-model-invocation, allowed-tools), argument substitution syntax, and the recommended 500-line limit with supporting files for large references or scripts. The post also covers common triggering problems and fixes, subagent contexts (context: fork) for noisy procedures, and notes that SKILL.md follows the Agent Skills open standard used by multiple coding agents. Publication date: 2026-07-22.
Track Real-Time Market Signals & Shifts
Set up custom watchlists to receive automated, evidence-grounded executive digests whenever material signals or shifts occur across your tracked landscape.