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
—
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 a strong skill description that clearly defines a specific niche (TPM coordination for Backlog.md workstreams), provides concrete actions, and includes an explicit 'Use only when' clause with realistic trigger examples. The description is concise yet comprehensive, uses third-person voice appropriately, and is highly distinguishable from other potential skills.
| 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.' These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (technical project management using coordinated sub-agents, orchestrating planning/implementation/finalization, managing dependencies, reviewing plans) and 'when' (explicit 'Use only when...' clause with concrete trigger examples like 'act as TPM', 'coordinate these tasks'). | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would actually say: 'act as TPM', 'coordinate these tasks', 'delegate to sub-agents', 'Backlog.md tasks'. These are realistic phrases a user would use when invoking this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: Backlog.md-specific TPM coordination using sub-agents. The 'Use only when' constraint with explicit trigger phrases like 'act as TPM' and 'delegate to sub-agents' makes it very unlikely to conflict with other 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-crafted TPM coordination skill with strong actionability and workflow clarity. It provides concrete commands, clear approval gates, and explicit validation checkpoints with error recovery paths. The main weakness is that the document is somewhat long for a single file—the sub-agent brief template and common mistakes section could benefit from being extracted into separate referenced files to improve progressive disclosure and reduce token cost.
Suggestions
Extract the Sub-Agent Brief Template and Common Agent Mistakes sections into separate referenced files (e.g., AGENT_BRIEF.md, COMMON_MISTAKES.md) to reduce the main SKILL.md token footprint and improve progressive disclosure.
Tighten the Sub-Agent Brief Template by removing instructions that duplicate TPM Operating Constraints (e.g., reading workflow resources is already stated in constraint #1).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long but most content is operational guidance Claude wouldn't inherently know (project-specific workspace rules, clone conventions, agent brief templates). Some sections like the Sub-Agent Brief Template are verbose and could be tightened—e.g., 'Read all four authoritative Backlog.md workflow resources before planning or coding' repeats what's already stated in TPM Operating Constraints. The Common Agent Mistakes section earns its place as institutional knowledge, but a few entries could be more concise. | 2 / 3 |
Actionability | The skill provides concrete, executable commands (git clone, mkdir, bun i, git remote set-url), specific naming conventions (tasks/<taskId>-<short-slug>), exact resource URIs (backlog://workflow/overview), and detailed step-by-step procedures for sub-agent briefs, plan approval, and finalization gates. The guidance is specific and directly usable rather than abstract. | 3 / 3 |
Workflow Clarity | The multi-step coordination workflow is clearly sequenced with explicit validation checkpoints: Plan Approval Gate (review before implementation), Finalization Gate (verify before marking done), and feedback loops (reject completion claims lacking proof, escalate blocked verification). The sub-agent brief template has a clear step 6 'wait for approval' gate and step 9 'if verification is blocked, escalate' recovery path. Destructive/batch operations are protected by isolation rules and verification requirements. | 3 / 3 |
Progressive Disclosure | The skill references external Backlog.md workflow resources (backlog://workflow/*) which is good progressive disclosure, but the SKILL.md itself is a monolithic document with no bundle files to offload detail into. The Sub-Agent Brief Template and Common Agent Mistakes sections are lengthy and could be split into separate referenced files. Without bundle files, all content is inline, making the single file quite long. | 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
7af19f8
- 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.