backlog-technical-project-manager
Technical project management for Backlog.md workstreams using coordinated sub-agents. Use only when the user explicitly asks Codex to take over one or more existing Backlog.md tasks (for example: "act as TPM", "coordinate these tasks", "delegate to sub-agents"). Orchestrate planning, implementation, and finalization; manage dependencies and overlapping code areas; review and approve sub-agent plans before implementation.
90
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly defines a specific TPM coordination role with Backlog.md integration. It provides explicit trigger phrases, concrete actions, and a well-defined scope that distinguishes it from general project management or coding skills. The 'Use only when' clause with example phrases is particularly effective for skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Orchestrate planning, implementation, and finalization; manage dependencies and overlapping code areas; review and approve sub-agent plans before implementation.' | 3 / 3 |
Completeness | Clearly answers both what ('Technical project management...using coordinated sub-agents', 'Orchestrate planning...') AND when ('Use only when the user explicitly asks...') with explicit trigger examples in parentheses. | 3 / 3 |
Trigger Term Quality | Includes natural trigger phrases users would say: 'act as TPM', 'coordinate these tasks', 'delegate to sub-agents', plus domain terms like 'Backlog.md', 'workstreams', and 'sub-agents'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific niche: 'Backlog.md workstreams', 'sub-agents', 'TPM' role. The explicit constraint 'Use only when the user explicitly asks' further reduces conflict risk with general task management skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured TPM coordination skill with strong actionability and workflow clarity. It provides concrete commands, explicit approval gates, and a living checklist of common mistakes. The main weakness is moderate verbosity - some sections could be tightened without losing clarity, and the monolithic structure could benefit from splitting detailed sections into referenced files.
Suggestions
Consider extracting the 'Sub-Agent Brief Template' into a separate AGENT_BRIEF.md file and referencing it, reducing the main skill's length
Tighten the 'Common Agent Mistakes' section by using a more compact format (e.g., table with Symptom | Guardrail columns) to reduce token usage while preserving the valuable content
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but contains some redundancy. The sub-agent brief template is comprehensive but could be tightened. Some sections like workspace rules include bash examples that are helpful but slightly verbose. | 2 / 3 |
Actionability | Provides concrete, executable guidance throughout: specific bash commands for workspace setup, explicit workflow steps, clear templates for sub-agent briefs, and actionable checklists. The common mistakes section includes specific symptoms and guardrails. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with clear sequencing: coordination workflow → sub-agent workspace setup → plan approval gate → finalization gate. Includes explicit validation checkpoints (plan approval before implementation, verification evidence before Done status) and feedback loops for error recovery. | 3 / 3 |
Progressive Disclosure | References external workflow resources appropriately (backlog:// URIs), but the skill itself is somewhat monolithic. The sub-agent brief template and common mistakes section could potentially be split into separate files for better organization, though the current structure is navigable. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- MrLesk/Backlog.md
- Commit
037c5d1
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.