BA dev_software_developer
Software Developer Project Skill — coordination, workflow, and team interoperation for FE and BE developer agents working on managed software projects. Use this skill whenever a developer agent needs to: pick up and work tasks from an Asana board, understand how to interact with the project manager or engineer, create branches and PRs following team standards, escalate technical blockers to the engineering agent, hand off completed work to QA for review, manage task status and communication through Asana, understand what the team expects from them as a developer on the project, or orient themselves to a new project with an existing Implementation Plan and SRS. Also handles the Asana heartbeat queue check — checking the appropriate dev queue (Frontend Dev Queue or Backend Dev Queue) across all active projects in USER.md, picking up ready tasks, and sending sessions_send nudges when coordination is needed. Triggers on: starting a dev task, Asana task workflow, PR creation, QA handoff, engineer escalation, branch naming, task status updates, blocker reporting, API contract coordination, or heartbeat queue check. This skill does NOT make git calls directly (requires a separately installed Git skill), does NOT make Asana API calls directly (requires a separately installed Asana skill), and does NOT handle language or framework-specific coding (requires relevant stack skills). It is purely about how the developer agent operates as a team member within the project structure.
As a process A 82/100 · Runs to the end — weak spots: result and completion, consistency
How to improve
- Shorten the description to 1024 characters.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1492 chars, limit 1024 - warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
body-longSKILL.md body ≈ 7046 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 82/100
- 40Result and completion. Does not say what the result is
- 40Consistency. Frontmatter name (dev_software_developer) differs from the folder (project-dev)
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 7046 tokens
- 100Tools and files. No external tools needed
- 100Steps. 87 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 20 branches, has a failure section
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1492: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 45 headings
- +3Step-by-step instructions: 87 items
- +4Has examples (14 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 45.