cwtf

Solid

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.

AI & Automation 61 stars 2 forks Updated yesterday MIT

Install

View on GitHub

Quality Score: 88/100

Stars 20%
60
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# /cwtf — Workflow Accountability > **Shared constraints apply.** Before executing, read `_shared/constraints.md` from the parent of this skill's base directory. All constraints there apply to this skill. Every other skill watches the code. This skill watches the agents watching the code. It answers: **"Did the workflow actually do what the skill instructions said it should do?"** Invoke with: `/cwtf` (analyzes the most recent or current workflow) or `/cwtf {phase}` (analyzes a specific phase) ## Important: Not Punitive This report identifies gaps, not blame. "QA checked 4 of 6 rules" is a fact, not an accusation. The QA agent may have had good reason — context overflow, rate limiting, or the 2 unchecked rules were trivially satisfied by the implementation. Present findings with context, not judgment. Let the user decide what matters. Frame gaps as: "R-003 was not checked during QA. This may indicate context overflow, rate limiting, or that the agent prioritized higher-risk rules." NOT: "The QA agent FAILED to check R-003." ## Progress Visibility (MANDATORY) Accountability analysis takes 5-10 minutes. The user must see progress throughout. **Before starting**, create a task list: 1. Load workflow state and spec 2. Check phase execution 3. Analyze rule coverage 4. Check agent thoroughness (QA) 5. Check agent thoroughness (review) 6. Detect deviations 7. Generate verdict **Between each step**, print a 1-line status: "Phase execution verified — all 7 phases ran. Checki...

Details

Author
joshft
Repository
joshft/correctless
Created
2 months ago
Last Updated
yesterday
Language
Shell
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

autonomous-workflow

Execute complete feature development cycles autonomously — from task intake through tested PR delivery — using isolated Git worktrees. Phase-based workflow (0–7) with optional companion skills for planning, quality gates, TDD, UX, code quality, docs, and CI verification. Companions skip silently if not installed. Triggers on "implement autonomously", "end-to-end", "in isolation", "in a worktree", or independent feature work. Invoke with /autonomous-workflow.

4 Updated 2 days ago
mthines
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
AI & Automation Listed

autonomous-workflow

Execute development workflows through Explore-Plan-Code-Verify phases with task-driven tracking, Tier 1/2/3 action classification, decision journaling, and bounded debug loops. Use when executing any development workflow autonomously or orchestrating multi-step implementation tasks. This skill MUST be consulted because skipping phases causes rework, and unbounded verification loops cause agents to loop forever on unsolvable problems.

5 Updated 3 days ago
synaptiai
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 Listed

code-quality-workflow

Use when assessing or improving code quality, maintainability, performance, or security hygiene - provides workflows for analysis, code review, and systematic improvements with validation steps.

15 Updated 2 days ago
NickCrew