AB dev-workflow
Master orchestrator for the full autonomous development lifecycle. Use this skill whenever the user mentions starting a new feature, has an idea to implement, wants to plan development, says "quero desenvolver", "tenho uma ideia", "nova feature", "começar uma issue", "próxima issue", or asks what the next step in development is. This skill coordinates all phases and delegates to existing skills (PRD, Issues, Code Review) where available, filling in QA Planning, Development, Testing, and PR management. Trigger even if the user only mentions one phase — this skill decides what comes next and runs autonomously via Claude Code.
As a process B 65/100 · Nearly there — weak spots: result and completion, inputs and preconditions, consistency
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 65/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 7 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 40Consistency. Frontmatter name (dev-workflow) differs from the folder (eb-dev-workflow)
- 70When it triggers. States when to use, but not when not to
- 85Steps. 18 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Failures and branches. 5 branches, has a failure section
- 100Execution cost. Instruction body is 2206 tokens
- low 14 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 631: enough signal without eating the budget
- +4Structure: 22 headings
- +3Step-by-step instructions: 18 items
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.