CtrlK
BlogDocsLog inGet started
Tessl Logo

plan-tree

Maintain a structured planning document tree made of roadmap/status files, implementation status or handoff TODO files, topic notes, decision records, open questions, ideas/inspiration pools, and repository/file-structure hygiene plans. Use when Codex needs to create, reorganize, audit, or update a multi-file plan, design-doc folder, roadmap tree, active implementation-status file, repo cleanup/filesystem plan, ADR/decision log, ideas inbox, or linked planning knowledge base; reconcile Done/In Progress/Next state; resume work from TODO/handoff state; move resolved questions into decisions; promote ideas into formal plan artifacts; or keep plan documents and file-structure planning internally consistent without making this project-specific.

66

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./useful_tools/codex_skills/plan-tree/SKILL.md

The canonical home for this skill is plan-tree in SeemSeam/claude_codex_bridge

SKILL.md
Quality
Evals
Security

Quality

Content

62%Weight 40%Scale 1-5

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

The body has excellent workflow sequencing with real validation checkpoints and concrete templates, but it is noticeably redundant across sections and far too monolithic — 365 lines that should be an overview plus a few on-demand references. No bundle files exist to offload any of this content.

Suggestions

Deduplicate the 'keep active files small / move history out' rule, which is stated in at least five sections (Execution Contract, Scaling Large Trees, Retrieval Units, Status Maintenance, History And Archival) — state it once and cross-reference.

Move the large-tree scaling rules, history/archival policies, and the three document templates into one-level-deep reference files (e.g., references/scaling.md, references/templates.md), keeping SKILL.md as a concise overview with clearly signaled links.

Trim the Final Checks section to a short checklist of checks not already enforced by earlier sections, or move it to a reference file invoked at Step 7, since it currently restates most of the document.

DimensionReasoningScore

Conciseness

The ~365-line body repeats the same rules across sections: 'keep active files small' appears in Execution Contract, Scaling Large Trees, Retrieval Units, Status Maintenance, and History And Archival; the 25+ bullet Final Checks section restates nearly every earlier rule; 'Workflow Detail' re-expands steps already given. The duplication is systemic rather than occasional padding.

2 / 5

Actionability

Guidance is concrete for an instruction-only skill: exact filenames ('implementation-status.md', 'topics/repository-cleanup-and-filesystem-plan.md'), a directory template, and copy-paste-ready decision-record, status-file, and cleanup-plan templates, plus explicit intent routing. Many rules remain abstract with no worked example (e.g., what a good roadmap item or retrieval header looks like), keeping it below fully executable.

4 / 5

Workflow Clarity

The 8-step numbered Execution Contract is authoritative and expanded where needed, the Resume Workflow is a clear ordered sequence, and Step 7 plus the dedicated Final Checks section provide an explicit validation checklist including inventory/backup/rollback safety checks for the destructive file delete/move operations this skill can perform.

5 / 5

Progressive Disclosure

Section headers are clear and well-ordered, but the entire skill is a single monolithic SKILL.md with no reference files; the large-tree rules, history/archival policies, and full templates clearly belong in one-level-deep references (e.g., references/scaling.md, references/templates.md) that could be loaded on demand.

3 / 5

Total

14

/

20

Passed

Description

96%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description with explicit what-and-when structure, comprehensive natural-language triggers including synonyms, and a well-defined niche. The only minor weakness is slight over-breadth in the trailing consistency/knowledge-base phrases.

DimensionReasoningScore

Specificity

The description names the domain ('structured planning document tree made of roadmap/status files... decision records, open questions, ideas/inspiration pools') and lists multiple concrete actions: 'create, reorganize, audit, or update', 'reconcile Done/In Progress/Next state', 'resume work from TODO/handoff state', 'move resolved questions into decisions', 'promote ideas into formal plan artifacts'. Coverage of the skill's operations is comprehensive rather than minor-gap.

5 / 5

Completeness

It explicitly answers both questions: the 'what' ('Maintain a structured planning document tree...') and an explicit 'Use when...' clause enumerating concrete trigger conditions. Both are clear and concrete.

5 / 5

Trigger Term Quality

Natural trigger phrases and their synonyms are comprehensively covered: 'roadmap tree', 'TODO/handoff', 'ADR/decision log', 'ideas inbox/inspiration pools', 'implementation-status file', 'repo cleanup/filesystem plan'. Terms users would actually say when needing this skill are all present; file extensions are not applicable to this domain.

5 / 5

Distinctiveness Conflict Risk

Core triggers (ADR/decision log, roadmap state reconciliation, TODO/handoff resume, ideas inbox) define a clear niche with minimal conflict risk. However, the broad tail phrases 'linked planning knowledge base' and 'keep plan documents and file-structure planning internally consistent' create minor overlap risk with general note-taking/documentation skills.

4 / 5

Total

19

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
SeemSeam/claude_codex_bridge
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.