← All creators

joshft

User

The agent that writes the code never reviews it. Spec-driven TDD with agent separation, adversarial QA, and dynamic rigor for Claude Code.

31 indexed · 0 Featured · 61 stars · avg score 88
Prolific

Categories

Indexed Skills (31)

AI & Automation Solid

cdevadv

10th Man / Devil's Advocate. Challenges the assumptions, architecture, and strategies that every other agent accepts as true. Periodic deep analysis — not every feature.

61 Updated yesterday
joshft
Code & Development Solid

cpostmortem

Post-merge bug analysis. Use when a bug escapes to production. Traces which phase missed it and strengthens the workflow.

61 Updated yesterday
joshft
Testing & QA Solid

credteam

Live adversarial red team assessment against a running system. Goal-directed penetration testing with source code access. Requires isolated environment.

61 Updated yesterday
joshft
AI & Automation Solid

cverify

Verify implementation matches spec. Check rule coverage, undocumented dependencies, architecture compliance. Writes verification report and drift debt. Run after /ctdd completes.

61 Updated yesterday
joshft
AI & Automation Solid

carchitect

Structured architecture definition. Two modes — reverse-engineer from existing code or greenfield directed discovery. Produces .correctless/ARCHITECTURE.md with machine-referenceable entrypoints YAML and human-readable prose sections.

61 Updated yesterday
joshft
Code & Development Solid

cauto

Semi-auto mode. Orchestrates the full implementation pipeline after human-approved spec review. Runs ctdd, simplify, cverify, cupdate-arch, cdocs, then creates a PR. After /cauto completes, verify the workflow reached the expected end state — if it didn't, re-invoke /cauto to resume.

61 Updated yesterday
joshft
AI & Automation Solid

ccontribute

Open source contribution workflow. Learns the target project's conventions, patterns, and CI requirements before writing code. Generates a PR that matches what maintainers expect.

61 Updated yesterday
joshft
Code & Development Solid

cdebug

Structured bug investigation workflow. Root cause analysis, hypothesis testing, TDD fix with agent separation, escalation after 3 failed attempts. Use when stuck on a bug.

61 Updated yesterday
joshft
AI & Automation Solid

cdocs

Update project documentation after a feature lands. Updates README, .correctless/AGENT_CONTEXT.md, .correctless/ARCHITECTURE.md, and feature docs. Run before merging.

61 Updated yesterday
joshft
AI & Automation Solid

cexplain

Guided codebase exploration with mermaid diagrams and prose walkthroughs.

61 Updated yesterday
joshft
AI & Automation Solid

chelp

Quick help — shows the workflow pipeline, available commands, and current status.

61 Updated yesterday
joshft
Code & Development Solid

cmaintain

Maintainer review for incoming PRs. Use when you need to decide whether to merge a contribution. Checks scope, conventions, and maintenance burden.

61 Updated yesterday
joshft
AI & Automation Solid

cmetrics

Project health and ROI dashboard. Use monthly or when evaluating workflow effectiveness. Shows bugs caught, token cost, and trends.

61 Updated yesterday
joshft
AI & Automation Solid

cmodel

Generate an Alloy formal model of security-relevant behavior and run the Alloy Analyzer. Use after /cspec for features with state machines, protocol handling, or trust boundaries.

61 Updated yesterday
joshft
AI & Automation Solid

cmodelupgrade

Compare current model+HARNESS_VERSION pipeline metrics against stored baselines and produce a per-feature regression report. Use after Anthropic ships a model upgrade or when /cspec/cstatus surfaces a harness version_bumped advisory. Read-only on the fingerprint store; writes only the baseline file.

61 Updated yesterday
joshft
Code & Development Solid

cpr-review

Review an incoming PR. Use when someone opens a PR against your project. Checks architecture, security, tests, and antipatterns.

61 Updated yesterday
joshft
Data & Documents Solid

cprune

Documentation and artifact pruning skill. Detects stale entries and orphaned artifacts, archives documentation (never deletes), cleans ephemeral artifacts. Two modes — autonomous for /cauto pipeline, interactive for direct invocation.

61 Updated yesterday
joshft
Code & Development Solid

cquick

Quick fix with TDD — no spec/review for small changes. Branch, test, implement, commit.

61 Updated yesterday
joshft
Code & Development Solid

crefactor

Structured refactoring with behavioral equivalence enforcement. Tests must pass before AND after. Any test change requires explicit approval. Writes characterization tests for low-coverage code.

61 Updated yesterday
joshft
AI & Automation Solid

crelease

Automate version bumping, changelog generation, and release tagging from specs.

61 Updated yesterday
joshft
Code & Development Solid

creview-spec

Multi-agent adversarial review of a spec. Spawns red team, assumptions auditor, testability auditor, design contract checker, and UX auditor. Use after /cspec or /cmodel.

61 Updated yesterday
joshft
Code & Development Solid

creview

Skeptically review a spec for unstated assumptions, untestable rules, missing edge cases, security gaps, and UX failures. Run after /cspec.

61 Updated yesterday
joshft
Testing & QA Solid

csetup

Initialize Correctless and run a project health check. Detects stack, configures workflow, bootstraps docs, checks security/quality/CI/testing hygiene, and offers to fix gaps. Adapts to project maturity — greenfield, early-stage, or mature.

61 Updated yesterday
joshft
Testing & QA Solid

cspec

Create a structured specification with testable invariants for a new feature. Researches current best practices before writing invariants. Adapts format to workflow intensity.

61 Updated yesterday
joshft
AI & Automation Solid

cstatus

Show current Correctless workflow state, available commands, and suggested next steps. Run anytime to see where you are.

61 Updated yesterday
joshft
AI & Automation Solid

csummary

Feature summary. Use after /cdocs to see what the workflow caught, or mid-feature to check progress.

61 Updated yesterday
joshft
Testing & QA Solid

ctdd

Enforced TDD workflow. Write failing tests from spec rules, then implement. Use after /creview approves a spec.

61 Updated yesterday
joshft
AI & Automation Solid

ctriage

Bulk triage deferred findings backlog. Presents findings one at a time with disposition options.

61 Updated yesterday
joshft
AI & Automation Solid

cupdate-arch

Update .correctless/ARCHITECTURE.md after features land. Use after /cdocs or when the codebase structure has changed.

61 Updated yesterday
joshft
AI & Automation Solid

cwtf

Audit the workflow itself. Use when you suspect agents shortcut or after a bug escapes despite the workflow running. Checks phase execution, rule coverage, and agent thoroughness.

61 Updated yesterday
joshft
DevOps & Infrastructure Solid

cdashboard

Generate a self-contained HTML dashboard with metrics and artifact browser. Opens via file:// protocol.

61 Updated yesterday
joshft

Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.