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.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with executable commands, clear gated workflows, and explicit validation/feedback loops, but it is somewhat verbose with repetition and monolithic rather than progressively disclosed across reference files.

Suggestions

Tighten redundancy around workspace isolation — consolidate the 'Never share a working directory' rule and the closing 'Enforce isolation' line into one statement to reduce repeated tokens.

Split the Sub-Agent Brief Template and Common Agent Mistakes into separate reference files (e.g. references/sub-agent-brief.md, references/common-mistakes.md) and link to them from the body to improve progressive disclosure.

Trim the Common Agent Mistakes entries to the essential symptom + guardrail pair, removing prose, so the living checklist stays lean as it grows.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes Claude's competence (no explaining of git/PRs/sub-agents), but it is lengthy with some redundancy — isolation is enforced in multiple places ('Never share a working directory', 'Enforce isolation: each worker agent...') and the Common Agent Mistakes section is detailed, so not every token earns its place.	2 / 3
Actionability	Provides concrete executable commands (mkdir/git clone/bun i snippet, 'git remote set-url origin https://github.com/MrLesk/Backlog.md.git', 'tasks/<taskId>-<short-slug>' branch naming, 'task_view', '-a @{your-name}') plus copy-paste-ready templates, matching the score-3 anchor for fully executable guidance.	3 / 3
Workflow Clarity	Clear multi-step sequences with explicit validation checkpoints (Plan Approval Gate, Finalization Gate checklists, 'do not set Done without verification evidence', escalation when verification is blocked), including feedback loops for the parallel/batch operations, matching the score-3 anchor.	3 / 3
Progressive Disclosure	No bundle files are provided and all content is inline in a single ~170-line file; sections are well-labeled but content such as the Sub-Agent Brief Template and Common Agent Mistakes could be split into separate reference files, fitting the score-2 anchor where content that should be separate is inline.	2 / 3
	Total	10 / 12 Passed

Description

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.

The description is specific, uses natural third-person trigger language, and clearly answers both what the skill does and when to invoke it, with a distinctive niche unlikely to conflict with other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions such as 'Orchestrate planning, implementation, and finalization; manage dependencies and overlapping code areas; review and approve sub-agent plans', matching the score-3 anchor for multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers both what it does (orchestrate, manage dependencies, review/approve plans) and when to use it ('Use only when the user explicitly asks Codex to take over...'), satisfying the score-3 anchor for both what AND when with explicit triggers.	3 / 3
Trigger Term Quality	Includes natural phrases a user would actually say ('act as TPM', 'coordinate these tasks', 'delegate to sub-agents', 'take over one or more existing Backlog.md tasks'), giving good coverage of common variations per the score-3 anchor.	3 / 3
Distinctiveness Conflict Risk	Targets a narrow niche (Backlog.md TPM via coordinated sub-agents) with distinct, unlikely-to-conflict triggers, matching the score-3 anchor for a clear niche with distinct triggers.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: MrLesk/Backlog.md
Commit: 591fe82

Reviewed: about 24 hours ago

Table of Contents

Discovery Implementation Validation

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.