BB dev_project_manager
Comprehensive AI Project Manager skill for software development. Use this skill whenever the PM agent needs to: engage with clients about new or existing software requirements, conduct requirements elicitation, request and review technical assessments from engineers, create or update Software Requirements Specifications (SRS) documents, classify change impacts, estimate effort/cost/AI-vs-human comparisons, manage scope creep and change requests, build or update Asana project boards and tasks, provide client status updates, review engineering implementation plans against SRS, render UI mockup comparisons, or coordinate between clients and engineering agents. Also handles the Asana heartbeat queue check — checking the PM Queue for each project and sending sessions_send nudges to the appropriate agents when work is ready. Triggers on any mention of: client requirements, SRS, requirements gathering, project status, stakeholder updates, engineering review, change requests, scope management, effort estimation, cost analysis, implementation plan review, UI comparison, project kickoff, or heartbeat queue check. This skill handles all PM communication protocols, templates, and decision frameworks. It does NOT make Asana API calls directly (requires a separately installed Asana skill), does NOT send email directly (requires a separately installed Email skill), and does NOT interact with code repositories.
As a process B 74/100 · Nearly there — weak spots: result and completion, inputs and preconditions, 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: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1418 chars, limit 1024 - warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
body-longSKILL.md body ≈ 7323 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 74/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Result and completion. Does not say what the result is
- 40Consistency. Frontmatter name (dev_project_manager) differs from the folder (dev-project-manager)
- 70Execution cost. Instruction body is 7323 tokens
- 100Tools and files. No external tools needed
- 100Steps. 100 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 9 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 1418: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 41 headings
- +3Step-by-step instructions: 100 items
- +4Has examples (18 code blocks)
- +4Reference files are cited in the instructions (6 of 6)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 45.