plan-harder
Use when user specfically says 'plan harder'.
48
49%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/plan-harder/SKILL.mdQuality
Discovery
22%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 description is critically deficient because it only specifies a trigger phrase without describing any capabilities or actions the skill performs. A user or Claude selecting from multiple skills would have no idea what this skill actually does. Additionally, the description contains a typo ('specfically').
Suggestions
Add a clear 'what' clause describing the concrete actions this skill performs (e.g., 'Creates detailed, structured project plans with milestones, dependencies, and risk assessments').
Expand trigger terms beyond the single phrase 'plan harder' to include related natural language variations (e.g., 'detailed planning', 'thorough plan', 'comprehensive project plan').
Use third person voice to describe capabilities before the trigger clause (e.g., 'Generates in-depth project plans with comprehensive breakdowns. Use when user says plan harder or requests more detailed planning.').
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions or capabilities whatsoever. It does not describe what the skill does, only a trigger phrase. | 1 / 3 |
Completeness | The 'what does this do' is entirely missing. While there is a 'when' clause ('Use when user specifically says plan harder'), the complete absence of any capability description makes this fundamentally incomplete. | 1 / 3 |
Trigger Term Quality | It includes one specific trigger phrase ('plan harder') which is a natural user phrase, but provides no other keywords, variations, or context about what domain this applies to. | 2 / 3 |
Distinctiveness Conflict Risk | The very specific trigger phrase 'plan harder' is unlikely to conflict with other skills, but the lack of any domain or capability description means it's unclear what this skill is for, which could cause confusion rather than direct conflicts. | 2 / 3 |
Total | 6 / 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 planning skill with clear multi-phase workflow, good validation checkpoints (gotcha review, subagent review), and actionable guidance including concrete examples and a complete template. Its main weakness is moderate verbosity—the inline template and some explanatory text could be tightened. The good/bad task examples and filename generation rules are particularly effective.
Suggestions
Extract the plan template into a separate PLAN-TEMPLATE.md file and reference it from the main skill to improve progressive disclosure and reduce inline bulk.
Trim explanatory phrases like 'Specific, actionable items within sprints' and 'small, independent' after 'Atomic and committable'—Claude understands these concepts.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some unnecessary elaboration. The plan template section is lengthy and could be trimmed since Claude understands markdown templates. Some sections like 'Task Requirements' explain concepts Claude already knows (what 'atomic' means). However, the good/bad example contrast is valuable and earns its place. | 2 / 3 |
Actionability | The skill provides concrete, actionable guidance throughout: specific filename generation rules with examples, a complete plan template with exact markdown structure, clear good/bad task examples, and explicit tool usage (request_user_input, subagent). Each phase has specific deliverables and actions. | 3 / 3 |
Workflow Clarity | The 6-phase workflow (Phase 0-5) is clearly sequenced with logical dependencies. It includes validation checkpoints: Phase 4 (Gotchas) explicitly reviews the plan for issues after saving, Phase 5 sends to a subagent for review, and there are feedback loops (update plan if improvements found, use request_user_input again if issues identified). | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and phases, but the plan template is inlined as a large block that could be a separate referenced file. For a standalone skill with no bundle files, the organization is reasonable but the template section makes the file longer than ideal for an overview document. | 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
- am-will/codex-skills
- Commit
d3983b1
- 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.