plan-harder
Use when user specfically says 'plan harder'.
60
49%
Does it follow best practices?
Impact
Pending
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 ('plan harder') without describing any capabilities, actions, or purpose of the skill. While the explicit trigger phrase provides some selection guidance, Claude would have no understanding of what this skill actually does or what domain it covers. The description also contains a typo ('specfically').
Suggestions
Add concrete capability descriptions explaining what the skill does (e.g., 'Creates detailed, structured project plans with milestones, dependencies, and risk assessments').
Expand trigger terms beyond the single phrase to include related natural language variations (e.g., 'detailed planning', 'thorough plan', 'comprehensive project plan').
Fix the typo 'specfically' to 'specifically' to maintain professional quality.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions or capabilities whatsoever. It does not describe what the skill does, only when to use it. | 1 / 3 |
Completeness | The 'what does this do' component is entirely missing. While there is a 'when' clause, the complete absence of any capability description makes this fundamentally incomplete. | 1 / 3 |
Trigger Term Quality | It includes one specific trigger phrase ('plan harder') that a user would literally say, but provides no other natural keyword variations or related terms. | 2 / 3 |
Distinctiveness Conflict Risk | The very specific trigger phrase 'plan harder' reduces conflict risk with other skills, but the lack of any described functionality makes it unclear what domain this occupies, which could cause confusion rather than overlap. | 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 (user clarification, gotcha review, subagent review), and concrete examples distinguishing good from bad task decomposition. The main weakness is the inlined plan template which adds significant length and could be extracted to a separate file. Overall, the skill is highly actionable and provides Claude with a clear, repeatable process.
Suggestions
Extract the plan template into a separate file (e.g., PLAN-TEMPLATE.md) and reference it from the main skill to improve conciseness and progressive disclosure.
Consider trimming the template slightly — fields like 'Rollback Plan' and 'Estimated Complexity' could be noted as optional to reduce cognitive load for simpler tasks.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary verbosity, such as the full plan template which is quite long. The process steps are reasonably lean, but the template section could be referenced as a separate file rather than inlined. Some sections like the task requirements examples are well done and earn their tokens. | 2 / 3 |
Actionability | The skill provides highly concrete, actionable guidance: specific phase-by-phase process, clear examples of good vs bad task decomposition, a filename generation algorithm, explicit tool usage (request_user_input, subagent), and a complete plan template with exact markdown structure to follow. | 3 / 3 |
Workflow Clarity | The multi-phase workflow is clearly sequenced (Phase 0-5) with explicit validation checkpoints: Phase 1 clarifies requirements before planning, Phase 4 identifies gotchas after saving and triggers user input if issues found, Phase 5 sends to a subagent for review. The feedback loops (gotchas → user input → update, review → incorporate) are well-defined. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and phases, but the full plan template is inlined rather than referenced as a separate file. For a skill of this length (~100+ lines), the template could be split into a separate TEMPLATE.md file to keep the main skill leaner and improve navigation. | 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
633b7e0
- 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.